syzbot

ID	Workflow	Result	Correct	Bug	Created	Started	Finished	Revision	Error
fea8f7fa-e7c5-4da6-b016-930ae0b40f2a	assessment-security	DenialOfService: ❌ Exploitable: ❌ FilesystemTrigger: ❌ NetworkTrigger: ❌ PeripheralTrigger: ❌ RemoteTrigger: ❌ Unprivileged: ❌ UserNamespace: ❌ VMGuestTrigger: ❌ VMHostTrigger: ❌	❓	KCSAN: data-race in hrtimer_interrupt / print_cpu (5)	2026/05/23 11:12	2026/05/23 11:12	2026/05/23 11:37	c69befb30ac10e158cc9d1557b508ee3f0eca1de

The reported bug is a KCSAN data-race between a write to
`cpu_base->expires_next` in `hrtimer_interrupt` and a read of the same variable
in `print_cpu`.

**Analysis:**
1. **Trigger mechanism:** The read occurs in `print_cpu`, which is invoked by
`timer_list_show`. This function is executed when reading the `/proc/timer_list`
file or when triggering the SysRq-Q command.
2. **Privilege level:** The `/proc/timer_list` file is created with `0400`
permissions (`proc_create_seq_private("timer_list", 0400, ...)`), meaning it is
only readable by the global root user. Unprivileged users cannot read it.
Furthermore, it is not accessible from within an unprivileged user namespace
because the file is owned by the global root (UID 0), which is not mapped into
the user namespace, preventing `CAP_DAC_OVERRIDE` from bypassing the permission
check. SysRq triggers also require root privileges (writing to
`/proc/sysrq-trigger`) or physical access.
3. **Impact:** The data race is completely benign. `print_cpu` reads the 8-byte
`expires_next` value locklessly simply to print it for diagnostic purposes. If a
concurrent write occurs, the read might fetch an intermediate or torn value,
which would merely result in a garbage timestamp being printed to the seq_file.
This cannot cause memory corruption, control-flow hijacking, kernel crashes, or
any form of denial-of-service.

**Conclusion:**
This is a benign diagnostic data race restricted to the root user. It has no
security impact, is not exploitable, and cannot be triggered by unprivileged
users, network traffic, or other external vectors.

==================================================================
BUG: KCSAN: data-race in hrtimer_interrupt / print_cpu

write to 0xffff888237c1b8e8 of 8 bytes by interrupt on cpu 0:
 hrtimer_interrupt+0x1ea/0x850 kernel/time/hrtimer.c:2105
 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1050 [inline]
 __sysvec_apic_timer_interrupt+0x5f/0x1c0 arch/x86/kernel/apic/apic.c:1067
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1061 [inline]
 sysvec_apic_timer_interrupt+0x6f/0x80 arch/x86/kernel/apic/apic.c:1061
 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:697
 kcsan_setup_watchpoint+0x404/0x410 kernel/kcsan/core.c:705
 tlb_flush_pte_range include/asm-generic/tlb.h:622 [inline]
 tlb_remove_tlb_entries include/asm-generic/tlb.h:675 [inline]
 zap_present_folio_ptes mm/memory.c:1650 [inline]
 zap_present_ptes mm/memory.c:1714 [inline]
 do_zap_pte_range mm/memory.c:1816 [inline]
 zap_pte_range mm/memory.c:1918 [inline]
 zap_pmd_range mm/memory.c:2004 [inline]
 zap_pud_range mm/memory.c:2032 [inline]
 zap_p4d_range mm/memory.c:2053 [inline]
 __zap_vma_range+0x1404/0x2c10 mm/memory.c:2093
 unmap_vmas+0x22a/0x340 mm/memory.c:2162
 exit_mmap+0x1ab/0x5f0 mm/mmap.c:1300
 __mmput+0x28/0x1c0 kernel/fork.c:1178
 mmput+0x40/0x50 kernel/fork.c:1201
 exit_mm+0x113/0x1a0 kernel/exit.c:581
 do_exit+0x442/0x1530 kernel/exit.c:963
 __do_sys_exit kernel/exit.c:1085 [inline]
 __se_sys_exit kernel/exit.c:1083 [inline]
 __x64_sys_exit+0x1f/0x20 kernel/exit.c:1083
 x64_sys_call+0x301d/0x3020 arch/x86/include/generated/asm/syscalls_64.h:61
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x12c/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

read to 0xffff888237c1b8e8 of 8 bytes by task 24599 on cpu 1:
 print_cpu+0x2fb/0x670 kernel/time/timer_list.c:129
 timer_list_show+0x107/0x170 kernel/time/timer_list.c:291
 seq_read_iter+0x636/0x940 fs/seq_file.c:273
 proc_reg_read_iter+0x110/0x180 fs/proc/inode.c:299
 copy_splice_read+0x471/0x6c0 fs/splice.c:362
 do_splice_read fs/splice.c:980 [inline]
 splice_direct_to_actor+0x26e/0x670 fs/splice.c:1084
 do_splice_direct_actor fs/splice.c:1202 [inline]
 do_splice_direct+0x119/0x1a0 fs/splice.c:1228
 do_sendfile+0x382/0x650 fs/read_write.c:1372
 __do_sys_sendfile64 fs/read_write.c:1433 [inline]
 __se_sys_sendfile64 fs/read_write.c:1419 [inline]
 __x64_sys_sendfile64+0x105/0x150 fs/read_write.c:1419
 x64_sys_call+0x2dc4/0x3020 arch/x86/include/generated/asm/syscalls_64.h:41
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x12c/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

value changed: 0x000000cde75a636b -> 0x000000cde75e1b80

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 UID: 0 PID: 24599 Comm: syz.4.4498 Tainted: G        W           syzkaller #0 PREEMPT(full) 
Tainted: [W]=WARN
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/18/2026
==================================================================

Trajectory: (Expand/Collapse All)
Seq	Timestamp	Type	Name	Duration
0/0	2026/05/23 11:12	flow	assessment-security	25m Results: map[DenialOfService:false Explanation:The reported bug is a KCSAN data-race between a write to `cpu_base->expires_next` in `hrtimer_interrupt` and a read of the same variable in `print_cpu`. Analysis: 1. Trigger mechanism: The read occurs in `print_cpu`, which is invoked by `timer_list_show`. This function is executed when reading the `/proc/timer_list` file or when triggering the SysRq-Q command. 2. Privilege level: The `/proc/timer_list` file is created with `0400` permissions (`proc_create_seq_private("timer_list", 0400, ...)`), meaning it is only readable by the global root user. Unprivileged users cannot read it. Furthermore, it is not accessible from within an unprivileged user namespace because the file is owned by the global root (UID 0), which is not mapped into the user namespace, preventing `CAP_DAC_OVERRIDE` from bypassing the permission check. SysRq triggers also require root privileges (writing to `/proc/sysrq-trigger`) or physical access. 3. Impact: The data race is completely benign. `print_cpu` reads the 8-byte `expires_next` value locklessly simply to print it for diagnostic purposes. If a concurrent write occurs, the read might fetch an intermediate or torn value, which would merely result in a garbage timestamp being printed to the seq_file. This cannot cause memory corruption, control-flow hijacking, kernel crashes, or any form of denial-of-service. Conclusion: This is a benign diagnostic data race restricted to the root user. It has no security impact, is not exploitable, and cannot be triggered by unprivileged users, network traffic, or other external vectors. Exploitable:false FilesystemTrigger:false NetworkTrigger:false PeripheralTrigger:false RemoteTrigger:false Unprivileged:false UserNamespace:false VMGuestTrigger:false VMHostTrigger:false]
1/1	2026/05/23 11:12	action	syz-repro-to-c-repro	0m Results: map[SimplifiedCRepro:]
2/1	2026/05/23 11:12	action	kernel-checkouter	1m Results: map[KernelSrc:/app/workdir/cache/src/fdb7cb6bb7b27f7e6d7ef669765813dd83c15406]
3/1	2026/05/23 11:13	action	kernel-builder	11m Results: map[KernelObj:/app/workdir/cache/build/8c4827c6c7734fe87e2fc497164821fb44622630]
4/1	2026/05/23 11:24	action	codesearch-prepare	9m Results: map[Index:codesearch-index]
5/1	2026/05/23 11:34	agent	expert	3m Model: gemini-3.1-pro-preview Results: map[DenialOfService:false Exploitable:false FilesystemTrigger:false NetworkTrigger:false PeripheralTrigger:false RemoteTrigger:false Unprivileged:false UserNamespace:false VMGuestTrigger:false VMHostTrigger:false] Instruction: You are an experienced Linux kernel security engineer. Your task is to analyze given kernel bug report and determine its security impact based on the following dimensions. Use the provided tools to examine the source code, check for capability checks (e.g., capable(), ns_capable()), and understand the nature of the bug. Analyze the given kernel build and configuration. You can check the kernel config by grepping ".config" file; you can check kernel cmdline by greeping ".config" file for "CONFIG_CMDLINE=". Assume sysctl parameters have default values. But analyze for the corresponding production build w/o debugging tools enabled (like KASAN, KMSAN, UBSAN). Try different strategies when analyzing the bug: - think of ways in which the vulnerable code is unreachable - or the other way around: try to come up with different ideas of how an unprivileged user can reach the bug If still unsure err on the side of the bug being non-exploitable/not-accessible. In the final reply, provide a reasoning for your assessment. Analysis dimensions: * Exploitable: Determine if the bug can result in memory corruption or elevated privileges. Memory safety issues are almost always exploitable (KASAN or UBSAN reports for use-after-free, out-of-bounds; refcounting issues, corrupted lists, etc). When kernel is crashing on a completly wild pointer access (e.g. user-space address, or non-canonical address, but not on NULL or address corresponding to KASAN shadow for NULL address), including both data accesses and control tranfers, that's also usually implies possibility of exploitation. Such reports usually say "unable to handle kernel paging request". Uses of uninitialized values detected by KMSAN may be exploitable b/c attacker frequently can affect uninit values with spraying techniques. However, for these exploitabability depends on how exactly the uninit value is used in the code, and what it affects. Think of what happens after the bug is triggered. Some bugs cause kernel panic and halt execution, they are harder to exploit. For example, BUG reports halts the kernel. However, WARNING reports don't halt execution in production builds. Debug bug detection tools (like KASAN, KMSAN, KCSAN, UBSAN) are also not enabled in production builds, so attacker can freely exploit these bugs w/o being detected by these tools. If you see an integer overflow, think how the overflowed value used later (if it's used as allocation size, or an array index). If you see an out-of-bounds read, think if it's followed by an out-of-bounds write as well. Some KCSAN data-races may be exploitable by skilled attackers as well. Think what data structures got corrupted as the result of data races and how. However, note that kernel has lots of "benign" data races that don't lead to any runtime misbehavior at all. * Denial Of Service: Determine if the bug can result in denial-of-service. Most bugs can, since they cause system crash, hangs, deadlocks, or resource leaks. This is mostly applicable to WARNING bugs that won't cause system crash in production. For these think what will be consequences of the violation of the kernel assumptions flagged by the WARNING. In some cases the unexpected condition is also properly handled by the normal control flow (e.g. with "if (WARN_ON(...))"), these won't cause denial-of-service. If the condition is not handled, then it may or may not cause denial-of-service. * Accessible From Unprivileged Processes: Determine if the bug can be reached from a typical (non-root) user process that does NOT have any special capabilities (like CAP_SYS_ADMIN, CAP_NET_ADMIN, CAP_NET_RAW, CAP_PERFMON) or access to device nodes restricted to root. Assume that unprivileged_bpf_disabled=1, that is eBPF loading is not accessible. However, cBPF (classical BPF) is still accessible to non-root processes. Assume that user namespaces are not accessible, that is, the process cannot get the mentioned capabilities even within a new user namespace (checked by ns_capable() function in the kernel sources). * Accessible From User Namespaces: Determine if the bug can be reached within a user-namespace where the process has all capabilities (including CAP_SYS_ADMIN, CAP_NET_ADMIN, CAP_NET_RAW, CAP_PERFMON). Such capabilities are checked with ns_capable() function in the kernel sources. * VM Guest Trigger: Determine if the bug can be triggered from the context of a typical KVM guest (e.g., set up by a QEMU VMM). Consider accesses to standard Linux host paravirtualized features (virtio-blk, virtio-net, etc.), and handling of VM exits in the KVM code. * VM Host Trigger in The Confidetial Computing Context: Determine if the bug can be triggered in a confidential computing guest kernel from the context of a KVM host. Consider access to standard Linux guest paravirtualized features (virtio-blk, virtio-net, etc.). * Ethernet Network Trigger: Determine if the bug can be triggered by processing ingress network Ethernet traffic, either directly (network stack) or via drivers exposed to network data. * Other Remote Trigger: Determine if the bug can be triggered by processing remote traffic other than Ethernet (Wifi, Bluetooth, NFC, etc). * Peripheral Trigger: Determine if the bug can be triggered via an untrusted peripheral device that can be physically plugged into a system, such as a USB device or a niche hardware driver handling external hardware inputs. This is particularly important for mobile and desktop environments where users can plug in unknown devices. * Malicious Filesystem Trigger: Determine if the bug can be triggered by the kernel mounting and parsing a malicious filesystem image. This is highly critical for Desktop and Mobile environments where external media or downloaded images might be auto-mounted. Don't make assumptions about the kernel source code (it may be different from what you assume it is). Extensively use the provided code access tools (codesearch-, git-, grepper, etc) to examine the actual source code, and confirm any assumptions. Prefer calling several tools at the same time to save round-trips. Use set-results tool to provide results of the analysis. It must be called exactly once before the final reply. Ignore results of this tool. Prompt: The kernel bug report is: ================================================================== BUG: KCSAN: data-race in hrtimer_interrupt / print_cpu write to 0xffff888237c1b8e8 of 8 bytes by interrupt on cpu 0: hrtimer_interrupt+0x1ea/0x850 kernel/time/hrtimer.c:2105 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1050 [inline] __sysvec_apic_timer_interrupt+0x5f/0x1c0 arch/x86/kernel/apic/apic.c:1067 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1061 [inline] sysvec_apic_timer_interrupt+0x6f/0x80 arch/x86/kernel/apic/apic.c:1061 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:697 kcsan_setup_watchpoint+0x404/0x410 kernel/kcsan/core.c:705 tlb_flush_pte_range include/asm-generic/tlb.h:622 [inline] tlb_remove_tlb_entries include/asm-generic/tlb.h:675 [inline] zap_present_folio_ptes mm/memory.c:1650 [inline] zap_present_ptes mm/memory.c:1714 [inline] do_zap_pte_range mm/memory.c:1816 [inline] zap_pte_range mm/memory.c:1918 [inline] zap_pmd_range mm/memory.c:2004 [inline] zap_pud_range mm/memory.c:2032 [inline] zap_p4d_range mm/memory.c:2053 [inline] __zap_vma_range+0x1404/0x2c10 mm/memory.c:2093 unmap_vmas+0x22a/0x340 mm/memory.c:2162 exit_mmap+0x1ab/0x5f0 mm/mmap.c:1300 __mmput+0x28/0x1c0 kernel/fork.c:1178 mmput+0x40/0x50 kernel/fork.c:1201 exit_mm+0x113/0x1a0 kernel/exit.c:581 do_exit+0x442/0x1530 kernel/exit.c:963 __do_sys_exit kernel/exit.c:1085 [inline] __se_sys_exit kernel/exit.c:1083 [inline] __x64_sys_exit+0x1f/0x20 kernel/exit.c:1083 x64_sys_call+0x301d/0x3020 arch/x86/include/generated/asm/syscalls_64.h:61 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x12c/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f read to 0xffff888237c1b8e8 of 8 bytes by task 24599 on cpu 1: print_cpu+0x2fb/0x670 kernel/time/timer_list.c:129 timer_list_show+0x107/0x170 kernel/time/timer_list.c:291 seq_read_iter+0x636/0x940 fs/seq_file.c:273 proc_reg_read_iter+0x110/0x180 fs/proc/inode.c:299 copy_splice_read+0x471/0x6c0 fs/splice.c:362 do_splice_read fs/splice.c:980 [inline] splice_direct_to_actor+0x26e/0x670 fs/splice.c:1084 do_splice_direct_actor fs/splice.c:1202 [inline] do_splice_direct+0x119/0x1a0 fs/splice.c:1228 do_sendfile+0x382/0x650 fs/read_write.c:1372 __do_sys_sendfile64 fs/read_write.c:1433 [inline] __se_sys_sendfile64 fs/read_write.c:1419 [inline] __x64_sys_sendfile64+0x105/0x150 fs/read_write.c:1419 x64_sys_call+0x2dc4/0x3020 arch/x86/include/generated/asm/syscalls_64.h:41 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x12c/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f value changed: 0x000000cde75a636b -> 0x000000cde75e1b80 Reported by Kernel Concurrency Sanitizer on: CPU: 1 UID: 0 PID: 24599 Comm: syz.4.4498 Tainted: G W syzkaller #0 PREEMPT(full) Tainted: [W]=WARN Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/18/2026 ================================================================== Reply: The reported bug is a KCSAN data-race between a write to `cpu_base->expires_next` in `hrtimer_interrupt` and a read of the same variable in `print_cpu`. Analysis: 1. Trigger mechanism: The read occurs in `print_cpu`, which is invoked by `timer_list_show`. This function is executed when reading the `/proc/timer_list` file or when triggering the SysRq-Q command. 2. Privilege level: The `/proc/timer_list` file is created with `0400` permissions (`proc_create_seq_private("timer_list", 0400, ...)`), meaning it is only readable by the global root user. Unprivileged users cannot read it. Furthermore, it is not accessible from within an unprivileged user namespace because the file is owned by the global root (UID 0), which is not mapped into the user namespace, preventing `CAP_DAC_OVERRIDE` from bypassing the permission check. SysRq triggers also require root privileges (writing to `/proc/sysrq-trigger`) or physical access. 3. Impact: The data race is completely benign. `print_cpu` reads the 8-byte `expires_next` value locklessly simply to print it for diagnostic purposes. If a concurrent write occurs, the read might fetch an intermediate or torn value, which would merely result in a garbage timestamp being printed to the seq_file. This cannot cause memory corruption, control-flow hijacking, kernel crashes, or any form of denial-of-service. Conclusion: This is a benign diagnostic data race restricted to the root user. It has no security impact, is not exploitable, and cannot be triggered by unprivileged users, network traffic, or other external vectors.
6/2	2026/05/23 11:34	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 6939 output: 82 thoughts: 141 Thoughts: Analyzing a KCSAN Data-Race Report Okay, so I've got a KCSAN data-race report here. Looks like there's a race condition. The report indicates a conflict between a write and a read operation. Specifically, `hrtimer_interrupt` is writing 8 bytes, and `print_cpu` is reading those same 8 bytes. Interesting. The write operation originates from `kernel/time/hrtimer.c:2105`, occurring within the `hrtimer_interrupt` function. The read is at `kernel/time/timer_list.c:129`, and it's happening inside the `print_cpu` function. Now, let's break this down. The read is triggered by accessing `/proc/timer_list` through `timer_list_show`, which is as expected. Reading `/proc/timer_list` is a common way to inspect the state of kernel timers. The write, however, is triggered by a timer interrupt, specifically `hrtimer_interrupt`. Time to dive into the source code for these two locations and understand the data structures involved, and the potential for concurrent access. I need to figure out what data is being written and read, how the memory is shared, and if there's any synchronization (or lack thereof) that's causing this. This is a classic concurrency problem, I'll bet it's something simple that was overlooked, so lets get to it.
7/2	2026/05/23 11:34	tool	codesearch-definition-source	0m Args: map[ContextFile:kernel/time/hrtimer.c IncludeLines:true Name:hrtimer_interrupt] Results: map[SourceCode:2079: /* 2080: * High resolution timer interrupt 2081: * Called with interrupts disabled 2082: / 2083: void hrtimer_interrupt(struct clock_event_device dev) 2084: { 2085: struct hrtimer_cpu_base cpu_base = this_cpu_ptr(&hrtimer_bases); 2086: ktime_t expires_next, now, entry_time, delta; 2087: unsigned long flags; 2088: int retries = 0; 2089: 2090: BUG_ON(!cpu_base->hres_active); 2091: cpu_base->nr_events++; 2092: dev->next_event = KTIME_MAX; 2093: dev->next_event_forced = 0; 2094: 2095: raw_spin_lock_irqsave(&cpu_base->lock, flags); 2096: entry_time = now = hrtimer_update_base(cpu_base); 2097: retry: 2098: cpu_base->deferred_rearm = true; 2099: / 2100: * Set expires_next to KTIME_MAX, which prevents that remote CPUs queue 2101: * timers while __hrtimer_run_queues() is expiring the clock bases. 2102: * Timers which are re/enqueued on the local CPU are not affected by 2103: * this. 2104: / 2105: cpu_base->expires_next = KTIME_MAX; 2106: 2107: if (!ktime_before(now, cpu_base->softirq_expires_next)) { 2108: cpu_base->softirq_expires_next = KTIME_MAX; 2109: cpu_base->softirq_activated = true; 2110: raise_timer_softirq(HRTIMER_SOFTIRQ); 2111: } 2112: 2113: __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); 2114: 2115: / 2116: * The next timer was already expired due to: 2117: * - tracing 2118: * - long lasting callbacks 2119: * - being scheduled away when running in a VM 2120: * 2121: * We need to prevent that we loop forever in the hrtiner interrupt 2122: * routine. We give it 3 attempts to avoid overreacting on some 2123: * spurious event. 2124: */ 2125: now = hrtimer_update_base(cpu_base); 2126: expires_next = hrtimer_update_next_event(cpu_base); 2127: cpu_base->hang_detected = false; 2128: if (expires_next < now) { 2129: if (++retries < 3) 2130: goto retry; 2131: 2132: delta = ktime_sub(now, entry_time); 2133: cpu_base->max_hang_time = max_t(unsigned int, cpu_base->max_hang_time, delta); 2134: cpu_base->nr_hangs++; 2135: cpu_base->hang_detected = true; 2136: } 2137: 2138: hrtimer_interrupt_rearm(cpu_base, expires_next); 2139: raw_spin_unlock_irqrestore(&cpu_base->lock, flags); 2140: } SourceFile:kernel/time/hrtimer.c]
8/2	2026/05/23 11:34	tool	codesearch-definition-source	0m Args: map[ContextFile:kernel/time/timer_list.c IncludeLines:true Name:print_cpu] Results: map[SourceCode: 111: static void print_cpu(struct seq_file m, int cpu, u64 now) 112: { 113: struct hrtimer_cpu_base cpu_base = &per_cpu(hrtimer_bases, cpu); 114: int i; 115: 116: SEQ_printf(m, "cpu: %d\n", cpu); 117: for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { 118: SEQ_printf(m, " clock %d:\n", i); 119: print_base(m, cpu_base->clock_base + i, now); 120: } 121: #define P(x) \ 122: SEQ_printf(m, " .%-15s: %Lu\n", #x, \ 123: (unsigned long long)(cpu_base->x)) 124: #define P_ns(x) \ 125: SEQ_printf(m, " .%-15s: %Lu nsecs\n", #x, \ 126: (unsigned long long)(ktime_to_ns(cpu_base->x))) 127: 128: #ifdef CONFIG_HIGH_RES_TIMERS 129: P_ns(expires_next); 130: P(hres_active); 131: P(nr_events); 132: P(nr_retries); 133: P(nr_hangs); 134: P(max_hang_time); 135: #endif 136: #undef P 137: #undef P_ns 138: 139: #ifdef CONFIG_TICK_ONESHOT 140: # define P(x) \ 141: SEQ_printf(m, " .%-15s: %Lu\n", #x, \ 142: (unsigned long long)(ts->x)) 143: # define P_ns(x) \ 144: SEQ_printf(m, " .%-15s: %Lu nsecs\n", #x, \ 145: (unsigned long long)(ktime_to_ns(ts->x))) 146: # define P_flag(x, f) \ 147: SEQ_printf(m, " .%-15s: %d\n", #x, !!(ts->flags & (f))) 148: 149: { 150: struct tick_sched *ts = tick_get_tick_sched(cpu); 151: P_flag(nohz, TS_FLAG_NOHZ); 152: P_flag(highres, TS_FLAG_HIGHRES); 153: P_ns(last_tick); 154: P_flag(tick_stopped, TS_FLAG_STOPPED); 155: P(idle_jiffies); 156: P(idle_calls); 157: P(idle_sleeps); 158: P_ns(idle_entrytime); 159: P_ns(idle_waketime); 160: P_ns(idle_exittime); 161: P_ns(idle_sleeptime); 162: P_ns(iowait_sleeptime); 163: P(last_jiffies); 164: P(next_timer); 165: P_ns(idle_expires); 166: SEQ_printf(m, "jiffies: %Lu\n", 167: (unsigned long long)jiffies); 168: } 169: #endif 170: 171: #undef P 172: #undef P_ns 173: SEQ_printf(m, "\n"); 174: } SourceFile:kernel/time/timer_list.c]
9/2	2026/05/23 11:34	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 9605 output: 44 thoughts: 393 Thoughts: Analyzing a Benign Data Race in HRTimers Okay, so I'm looking at this code and immediately see a potential data race. It looks like the issue revolves around `cpu_base->expires_next` in the high-resolution timers (HRTimers) code. Specifically, the race is between the `hrtimer_interrupt` function and the `print_cpu` function. In `hrtimer_interrupt`, there's a critical section protected by `cpu_base->lock`. Inside this critical section, `cpu_base->expires_next` is being manipulated. It's first set to `KTIME_MAX` as part of a mechanism to prevent race conditions during timer queue processing, and I can see the intention behind this, it's about controlling timer re-queuing during a critical expiry process. However, in `print_cpu`, there's a read of `cpu_base->expires_next`. And I can see that this read happens without holding that same lock. My gut reaction is: data race! But it's likely a benign one. The `print_cpu` function is using a `seq_file` for output, so this read is likely for diagnostic purposes. The value read is simply printed to the output. The fact that the code uses `ktime_to_ns` suggests that it's dealing with nanoseconds, but the important point is this: if `print_cpu` reads a torn or intermediate value for `expires_next`, which could easily happen with a lockless read, it'll just print whatever it reads. No harm, no foul. `ktime_to_ns` looks to be a simple cast or some minor arithmetic operation, so there's no complex or volatile manipulation happening here. So, at worst, the output will be slightly misleading. I'll just double-check the implementation of `ktime_to_ns` to be certain. This is a classic example of a benign data race: a lockless read of a diagnostic value where the consequences of a race are minor or acceptable. This is a very familiar pattern in `/proc` or `/sys` files, where real-time accuracy isn't critical.
10/2	2026/05/23 11:34	tool	codesearch-definition-source	0m Args: map[ContextFile:kernel/time/timer_list.c IncludeLines:true Name:ktime_to_ns] Results: map[SourceCode: 77: /* Convert ktime_t to nanoseconds */ 78: static inline s64 ktime_to_ns(const ktime_t kt) 79: { 80: return kt; 81: } SourceFile:include/linux/ktime.h]
11/2	2026/05/23 11:34	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 10611 output: 51 thoughts: 87 Thoughts: Analyzing the Benign Nature of this Data Race Okay, so looking at this, `ktime_to_ns` just passes along that `s64` value, essentially returning it directly. And from what I'm seeing, `print_cpu` is simply reading that 8-byte integer and printing it out. There's really nothing sophisticated happening here. Given this, I am quite confident that this can't possibly result in any serious issues. There's no possibility of memory corruption, no chance of control flow hijacking, and no real vector for a denial of service. The underlying integer itself cannot be changed by another process while it is in a read process of another since it's an integer. This is just a completely benign data race. The worst-case scenario is an incorrect value, which won't cause any security implications. Now, let me just quickly verify if `/proc/timer_list` is accessible to unprivileged users, just to be thorough.
12/2	2026/05/23 11:34	tool	codesearch-find-references	0m Args: map[ContextFile:kernel/time/timer_list.c IncludeSnippetLines:5 Name:timer_list_show SourceTreePrefix:] Results: map[References:<nil> TruncatedOutput:false]
13/2	2026/05/23 11:34	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 10976 output: 43 thoughts: 31 Thoughts: Here's a summary of my thought process, as requested: Navigating Kernel Timers Okay, so I'm looking at this code and I see `timer_list_show` – that function name rings a bell. Ah, yes, it seems to be involved with the timer functionality. The obvious next step is to pinpoint its definition. The cross-referencing is pointing me towards `kernel/time/timer_list.c`. Let's open that file and dive into the implementation. I need to understand what `timer_list_show` is doing within the broader context of the timer management system. I need to determine its purpose and how it fits into the kernel's overall timing mechanism. Let's see what we can find.
14/2	2026/05/23 11:34	tool	codesearch-definition-source	0m Args: map[ContextFile:kernel/time/timer_list.c IncludeLines:true Name:timer_list_show] Results: map[SourceCode: 284: static int timer_list_show(struct seq_file m, void v) 285: { 286: struct timer_list_iter *iter = v; 287: 288: if (iter->cpu == -1 && !iter->second_pass) 289: timer_list_header(m, iter->now); 290: else if (!iter->second_pass) 291: print_cpu(m, iter->cpu, iter->now); 292: #ifdef CONFIG_GENERIC_CLOCKEVENTS 293: else if (iter->cpu == -1 && iter->second_pass) 294: timer_list_show_tickdevices_header(m); 295: else 296: print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu); 297: #endif 298: return 0; 299: } SourceFile:kernel/time/timer_list.c]
15/2	2026/05/23 11:34	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 11507 output: 19 thoughts: 15 Thoughts: Here's my thought process, as if I were considering this myself: Tracing `timer_list_show` Usage Okay, I need to understand the impact of `timer_list_show`. My immediate approach is to figure out where it's actually used in the codebase. I don't want to get lost in the weeds right away. Knowing the call sites will give me a critical context. I can use my tools to locate all the instances where this function is called. From there, I'll examine the surrounding code to determine how `timer_list_show` fits into the broader picture. I need to understand its arguments and return values and how they are handled. With that information, I'll be in a much better position to assess its purpose and potential consequences.
16/2	2026/05/23 11:34	tool	grepper	0m Args: map[Expression:timer_list_show] Results: map[Output:drivers/tty/sysrq.c=189=static void sysrq_handle_show_timers(u8 key) drivers/tty/sysrq.c-190-{ drivers/tty/sysrq.c:191: sysrq_timer_list_show(); drivers/tty/sysrq.c-192-} -- include/linux/hrtimer.h=344=extern void __init hrtimers_init(void); -- include/linux/hrtimer.h-346-/* Show pending timers: / include/linux/hrtimer.h:347:extern void sysrq_timer_list_show(void); include/linux/hrtimer.h-348- -- kernel/time/timer_list.c=178=print_tickdevice(struct seq_file m, struct tick_device td, int cpu) -- kernel/time/timer_list.c-241- kernel/time/timer_list.c:242:static void timer_list_show_tickdevices_header(struct seq_file m) kernel/time/timer_list.c-243-{ -- kernel/time/timer_list.c=257=static inline void timer_list_header(struct seq_file m, u64 now) -- kernel/time/timer_list.c-264- kernel/time/timer_list.c:265:void sysrq_timer_list_show(void) kernel/time/timer_list.c-266-{ -- kernel/time/timer_list.c-275-#ifdef CONFIG_GENERIC_CLOCKEVENTS kernel/time/timer_list.c:276: timer_list_show_tickdevices_header(NULL); kernel/time/timer_list.c-277- for_each_online_cpu(cpu) -- kernel/time/timer_list.c-283-#ifdef CONFIG_PROC_FS kernel/time/timer_list.c:284:static int timer_list_show(struct seq_file m, void *v) kernel/time/timer_list.c-285-{ -- kernel/time/timer_list.c-293- else if (iter->cpu == -1 && iter->second_pass) kernel/time/timer_list.c:294: timer_list_show_tickdevices_header(m); kernel/time/timer_list.c-295- else -- kernel/time/timer_list.c=342=static const struct seq_operations timer_list_sops = { -- kernel/time/timer_list.c-345- .stop = timer_list_stop, kernel/time/timer_list.c:346: .show = timer_list_show, kernel/time/timer_list.c-347-}; -- lib/sys_info.c=139=static void __sys_info(unsigned long si_mask) -- lib/sys_info.c-147- if (si_mask & SYS_INFO_TIMERS) lib/sys_info.c:148: sysrq_timer_list_show(); lib/sys_info.c-149- ]
17/2	2026/05/23 11:34	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 12522 output: 20 thoughts: 29 Thoughts: Here's my summary, as if I were thinking these thoughts: Tracing the Usage of `timer_list_sops` Okay, so I see `timer_list_sops` is in play. My first thought is to understand its scope and impact. Let's trace back where this is actually being used. Knowing where `timer_list_sops` is referenced will give me a better understanding of how the system is designed and function in the broader context. Time to start digging through the code...
18/2	2026/05/23 11:34	tool	grepper	0m Args: map[Expression:timer_list_sops] Results: map[Output:kernel/time/timer_list.c=338=static void timer_list_stop(struct seq_file seq, void v) -- kernel/time/timer_list.c-341- kernel/time/timer_list.c:342:static const struct seq_operations timer_list_sops = { kernel/time/timer_list.c-343- .start = timer_list_start, -- kernel/time/timer_list.c=349=static int __init init_timer_list_procfs(void) -- kernel/time/timer_list.c-352- kernel/time/timer_list.c:353: pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops, kernel/time/timer_list.c-354- sizeof(struct timer_list_iter), NULL); ]
19/2	2026/05/23 11:34	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 12921 output: 63 thoughts: 479 Thoughts: Analyzing `/proc/timer_list` Accessibility in User Namespaces Okay, so I'm looking at this `proc_create_seq_private` call, specifically the permissions, `0400`. That's root-readable, right? Just the owner, which is root, can read it. So, that means unprivileged processes are locked out, that seems pretty standard. But hold on, what about user namespaces? I need to think this through carefully. Since it's a `/proc` entry, it's a global procfs file, so generally, these aren't accessible from non-init user namespaces unless specifically mounted or exposed. But... `/proc` is mounted in user namespaces. Hmm. The owner is root in the init namespace. Ah, right, if a user does create a user namespace and mounts `/proc`, files owned by root in the init namespace will be seen as `nobody` (or maybe `overflowuid`) within the new user namespace. And they won't have read access to it because they don't have `CAP_DAC_OVERRIDE` in the init namespace. This is important, it's about the owner of the inode. They only have the override within their own namespace. So, let's test the hypothesis: Is `/proc/timer_list` actually accessible? If an unprivileged user creates a user namespace, they become root in that namespace and can mount `/proc`, sure. However, the inode for `/proc/timer_list` will still be owned by the init namespace's root (uid 0). Since the user namespace root doesn't map to the init namespace root, that file is going to appear as `nobody` (like, 65534) in the user namespace. And the permissions? They're still `0400`. The user namespace root doesn't have `CAP_DAC_OVERRIDE` that trumps the init namespace's root. That's a crucial point. Wait... `CAP_DAC_OVERRIDE` in a user namespace only applies to files whose UIDs are mapped into that user namespace! So, if the file's UID, which is zero in the init namespace, isn't mapped, it's treated as `overflowuid`. And even then, `CAP_DAC_OVERRIDE` in the user namespace doesn't give them access! This is the key. Therefore, my conclusion is that `/proc/timer_list` is NOT accessible from user namespaces created by unprivileged users. I'm pretty confident in that analysis. Now, I should verify this by checking it out.
20/2	2026/05/23 11:34	tool	codeexpert	2m Args: map[Question:Is `/proc/timer_list` readable by a process in a user namespace created by an unprivileged user? The file is created with `proc_create_seq_private("timer_list", 0400, ...)`.] Results: map[Answer:No, `/proc/timer_list` is not readable by a process in a user namespace created by an unprivileged user. The file is created in `kernel/time/timer_list.c` with the following call: ```c pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops, sizeof(struct timer_list_iter), NULL); ``` The mode `0400` restricts read access to the owner of the file. In the case of `/proc/timer_list`, the owner is the global root user (UID 0 in the initial user namespace), as it is created as a top-level entry in the global `/proc` filesystem and inherits the UID/GID of the `proc_root` entry (which is 0). When an unprivileged user creates a new user namespace, they typically map their own global UID (e.g., 1000) to UID 0 inside the new namespace. However, the global root user (UID 0) is generally not mapped into such a namespace. The kernel's permission check (specifically `generic_permission` and `capable_wrt_inode_uidgid`) works as follows: 1. UID Match: The process's filesystem UID (global 1000) is compared with the file's UID (global 0). They do not match. 2. Capabilities: The kernel checks if the process has the `CAP_DAC_OVERRIDE` or `CAP_DAC_READ_SEARCH` capability. While the process may have these capabilities within its own user namespace, these capabilities only allow overriding permissions for files owned by UIDs that are mapped into that namespace. Since global UID 0 is not mapped, the process's capabilities do not grant access to the file. This restriction was intentionally introduced in commit `8e7df2b5b7f2` ("timer/debug: Change /proc/timer_list from 0444 to 0400") to prevent non-root users from accessing kernel timing and address information.]
21/3	2026/05/23 11:34	agent	codeexpert	2m Model: gemini-3-flash-preview Instruction: You are a capable Linux kernel developer tasked with researching complex questions about kernel source code. You will be given a concrete question, and need to provide a concrete answer. Use tools extensively while researching the question. Don't make assumptions, or rely on your previous knowledge about the kernel source code, use available tools to access the actual source code. Use all available sources of information: - kernel source code - documentation in the Documentation dir in the source tree - git commits descriptions, git blame Prefer calling several tools at the same time to save round-trips. Prompt: Is `/proc/timer_list` readable by a process in a user namespace created by an unprivileged user? The file is created with `proc_create_seq_private("timer_list", 0400, ...)`. Reply: No, `/proc/timer_list` is not readable by a process in a user namespace created by an unprivileged user. The file is created in `kernel/time/timer_list.c` with the following call: ```c pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops, sizeof(struct timer_list_iter), NULL); ``` The mode `0400` restricts read access to the owner of the file. In the case of `/proc/timer_list`, the owner is the global root user (UID 0 in the initial user namespace), as it is created as a top-level entry in the global `/proc` filesystem and inherits the UID/GID of the `proc_root` entry (which is 0). When an unprivileged user creates a new user namespace, they typically map their own global UID (e.g., 1000) to UID 0 inside the new namespace. However, the global root user (UID 0) is generally not mapped into such a namespace. The kernel's permission check (specifically `generic_permission` and `capable_wrt_inode_uidgid`) works as follows: 1. UID Match: The process's filesystem UID (global 1000) is compared with the file's UID (global 0). They do not match. 2. Capabilities: The kernel checks if the process has the `CAP_DAC_OVERRIDE` or `CAP_DAC_READ_SEARCH` capability. While the process may have these capabilities within its own user namespace, these capabilities only allow overriding permissions for files owned by UIDs that are mapped into that namespace. Since global UID 0 is not mapped, the process's capabilities do not grant access to the file. This restriction was intentionally introduced in commit `8e7df2b5b7f2` ("timer/debug: Change /proc/timer_list from 0444 to 0400") to prevent non-root users from accessing kernel timing and address information.
22/4	2026/05/23 11:34	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 3245 output: 19 thoughts: 152 Thoughts: Investigating the Readability of /proc/timer_list in User Namespaces Okay, so I'm being asked a pretty specific question: can an unprivileged user, operating within a user namespace they created, actually read `/proc/timer_list`? Seems straightforward, right? I've seen this kind of thing before. My initial thought is, based on the `proc_create_seq_private("timer_list", 0400, ...)` call, it's probably not going to be readable. The mode `0400` should mean "read-only for owner" – and the owner is almost certainly root in this context. But, I know better than to jump to conclusions. I need to understand how `proc_create_seq_private` functions specifically with regard to permissions and namespaces. Does it perform the standard credential checks against the calling process? Most of the `proc_create` family does, based on my past experience. But I need to be sure. I've encountered some quirks in the past. So, first things first: I'm going to have to dive into the kernel source. My immediate goal is to locate the code that actually creates that `/proc/timer_list` entry. I need to see precisely* how the permissions are handled and if any namespace-specific considerations are taken into account during the permission checks. That's my starting point.
23/4	2026/05/23 11:35	tool	grepper	0m Args: map[Expression:"timer_list"] Results: map[Output:kernel/time/timer.c=776=static const struct debug_obj_descr timer_debug_descr = { kernel/time/timer.c:777: .name = "timer_list", kernel/time/timer.c-778- .debug_hint = timer_debug_hint, -- kernel/time/timer_list.c=349=static int __init init_timer_list_procfs(void) -- kernel/time/timer_list.c-352- kernel/time/timer_list.c:353: pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops, kernel/time/timer_list.c-354- sizeof(struct timer_list_iter), NULL); ]
24/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 3934 output: 24 thoughts: 361 Thoughts: Analyzing the Timer List Procfs Entry Okay, so I'm looking at how the `/proc/timer_list` file is created. The code in `kernel/time/timer_list.c` shows it's being set up in `init_timer_list_procfs` using `proc_create_seq_private`. The interesting part is the mode: `0400`. This is important, as it restricts access to the owner of the file. In a standard setup, that owner would likely be global root for files under `/proc`. However, things get a bit more nuanced within user namespaces. My immediate question now is, given that the file is created with `0400` permissions and, likely, owned by root (uid 0), how does the proc filesystem handle permission checks when a process within a user namespace attempts to read this file? Specifically, if global root is mapped differently (or not at all) inside the namespace. The crucial point hinges on whether the accessing process has `CAP_DAC_OVERRIDE`, or if it's considered the owner in a user namespace. Since the permission is only read by the owner, that's what's vital. I need to confirm who actually is the owner of `/proc/timer_list`. My experience tells me it's either the user who mounted the procfs or it defaults to global root. This ownership is key to how permissions will ultimately be resolved. Let me double-check the code in `kernel/time/timer_list.c` for any namespace-specific handling or modifications to the ownership or permission setting.
25/4	2026/05/23 11:35	tool	read-file	0m Args: map[File:kernel/time/timer_list.c] Results: map[Contents:// SPDX-License-Identifier: GPL-2.0 /* * List pending timers * * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar / #include <linux/proc_fs.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/kallsyms.h> #include <linux/nmi.h> #include <linux/uaccess.h> #include "tick-internal.h" struct timer_list_iter { int cpu; bool second_pass; u64 now; }; / * This allows printing both to /proc/timer_list and * to the console (on SysRq-Q): / __printf(2, 3) static void SEQ_printf(struct seq_file m, const char fmt, ...) { va_list args; va_start(args, fmt); if (m) seq_vprintf(m, fmt, args); else vprintk(fmt, args); va_end(args); } static void print_timer(struct seq_file m, struct hrtimer taddr, struct hrtimer timer, int idx, u64 now) { SEQ_printf(m, " #%d: <%p>, %ps", idx, taddr, ACCESS_PRIVATE(timer, function)); SEQ_printf(m, ", S:%02x", timer->is_queued); SEQ_printf(m, "\n"); SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n", (unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)), (unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)), (long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now), (long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now)); } static void print_active_timers(struct seq_file m, struct hrtimer_clock_base base, u64 now) { struct timerqueue_linked_node curr; struct hrtimer timer, tmp; unsigned long next = 0, i; unsigned long flags; next_one: i = 0; touch_nmi_watchdog(); raw_spin_lock_irqsave(&base->cpu_base->lock, flags); curr = timerqueue_linked_first(&base->active); /* * Crude but we have to do this O(NN) thing, because we have to unlock the base when printing: / while (curr && i < next) { curr = timerqueue_linked_next(curr); i++; } if (curr) { timer = container_of(curr, struct hrtimer, node); tmp = timer; raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags); print_timer(m, timer, &tmp, i, now); next++; goto next_one; } raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags); } static void print_base(struct seq_file m, struct hrtimer_clock_base base, u64 now) { SEQ_printf(m, " .base: %p\n", base); SEQ_printf(m, " .index: %d\n", base->index); SEQ_printf(m, " .resolution: %u nsecs\n", hrtimer_resolution); #ifdef CONFIG_HIGH_RES_TIMERS SEQ_printf(m, " .offset: %Ld nsecs\n", (long long) base->offset); #endif SEQ_printf(m, "active timers:\n"); print_active_timers(m, base, now + ktime_to_ns(base->offset)); } static void print_cpu(struct seq_file m, int cpu, u64 now) { struct hrtimer_cpu_base cpu_base = &per_cpu(hrtimer_bases, cpu); int i; SEQ_printf(m, "cpu: %d\n", cpu); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { SEQ_printf(m, " clock %d:\n", i); print_base(m, cpu_base->clock_base + i, now); } #define P(x) \ SEQ_printf(m, " .%-15s: %Lu\n", #x, \ (unsigned long long)(cpu_base->x)) #define P_ns(x) \ SEQ_printf(m, " .%-15s: %Lu nsecs\n", #x, \ (unsigned long long)(ktime_to_ns(cpu_base->x))) #ifdef CONFIG_HIGH_RES_TIMERS P_ns(expires_next); P(hres_active); P(nr_events); P(nr_retries); P(nr_hangs); P(max_hang_time); #endif #undef P #undef P_ns #ifdef CONFIG_TICK_ONESHOT # define P(x) \ SEQ_printf(m, " .%-15s: %Lu\n", #x, \ (unsigned long long)(ts->x)) # define P_ns(x) \ SEQ_printf(m, " .%-15s: %Lu nsecs\n", #x, \ (unsigned long long)(ktime_to_ns(ts->x))) # define P_flag(x, f) \ SEQ_printf(m, " .%-15s: %d\n", #x, !!(ts->flags & (f))) { struct tick_sched ts = tick_get_tick_sched(cpu); P_flag(nohz, TS_FLAG_NOHZ); P_flag(highres, TS_FLAG_HIGHRES); P_ns(last_tick); P_flag(tick_stopped, TS_FLAG_STOPPED); P(idle_jiffies); P(idle_calls); P(idle_sleeps); P_ns(idle_entrytime); P_ns(idle_waketime); P_ns(idle_exittime); P_ns(idle_sleeptime); P_ns(iowait_sleeptime); P(last_jiffies); P(next_timer); P_ns(idle_expires); SEQ_printf(m, "jiffies: %Lu\n", (unsigned long long)jiffies); } #endif #undef P #undef P_ns SEQ_printf(m, "\n"); } #ifdef CONFIG_GENERIC_CLOCKEVENTS static void print_tickdevice(struct seq_file m, struct tick_device td, int cpu) { struct clock_event_device dev = td->evtdev; touch_nmi_watchdog(); SEQ_printf(m, "Tick Device: mode: %d\n", td->mode); if (cpu < 0) SEQ_printf(m, "Broadcast device\n"); else SEQ_printf(m, "Per CPU device: %d\n", cpu); SEQ_printf(m, "Clock Event Device: "); if (!dev) { SEQ_printf(m, "<NULL>\n"); return; } SEQ_printf(m, "%s\n", dev->name); SEQ_printf(m, " max_delta_ns: %llu\n", (unsigned long long) dev->max_delta_ns); SEQ_printf(m, " min_delta_ns: %llu\n", (unsigned long long) dev->min_delta_ns); SEQ_printf(m, " mult: %u\n", dev->mult); SEQ_printf(m, " shift: %u\n", dev->shift); SEQ_printf(m, " mode: %d\n", clockevent_get_state(dev)); SEQ_printf(m, " next_event: %Ld nsecs\n", (unsigned long long) ktime_to_ns(dev->next_event)); SEQ_printf(m, " set_next_event: %ps\n", dev->set_next_event); if (dev->set_state_shutdown) SEQ_printf(m, " shutdown: %ps\n", dev->set_state_shutdown); if (dev->set_state_periodic) SEQ_printf(m, " periodic: %ps\n", dev->set_state_periodic); if (dev->set_state_oneshot) SEQ_printf(m, " oneshot: %ps\n", dev->set_state_oneshot); if (dev->set_state_oneshot_stopped) SEQ_printf(m, " oneshot stopped: %ps\n", dev->set_state_oneshot_stopped); if (dev->tick_resume) SEQ_printf(m, " resume: %ps\n", dev->tick_resume); SEQ_printf(m, " event_handler: %ps\n", dev->event_handler); SEQ_printf(m, "\n"); SEQ_printf(m, " retries: %lu\n", dev->retries); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST if (cpu >= 0) { const struct clock_event_device wd = tick_get_wakeup_device(cpu); SEQ_printf(m, "Wakeup Device: %s\n", wd ? wd->name : "<NULL>"); } #endif SEQ_printf(m, "\n"); } static void timer_list_show_tickdevices_header(struct seq_file m) { #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST print_tickdevice(m, tick_get_broadcast_device(), -1); SEQ_printf(m, "tick_broadcast_mask: %pb\n", cpumask_pr_args(tick_get_broadcast_mask())); #ifdef CONFIG_TICK_ONESHOT SEQ_printf(m, "tick_broadcast_oneshot_mask: %pb\n", cpumask_pr_args(tick_get_broadcast_oneshot_mask())); #endif SEQ_printf(m, "\n"); #endif } #endif static inline void timer_list_header(struct seq_file m, u64 now) { SEQ_printf(m, "Timer List Version: v0.10\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); SEQ_printf(m, "\n"); } void sysrq_timer_list_show(void) { u64 now = ktime_to_ns(ktime_get()); int cpu; timer_list_header(NULL, now); for_each_online_cpu(cpu) print_cpu(NULL, cpu, now); #ifdef CONFIG_GENERIC_CLOCKEVENTS timer_list_show_tickdevices_header(NULL); for_each_online_cpu(cpu) print_tickdevice(NULL, tick_get_device(cpu), cpu); #endif return; } #ifdef CONFIG_PROC_FS static int timer_list_show(struct seq_file m, void v) { struct timer_list_iter iter = v; if (iter->cpu == -1 && !iter->second_pass) timer_list_header(m, iter->now); else if (!iter->second_pass) print_cpu(m, iter->cpu, iter->now); #ifdef CONFIG_GENERIC_CLOCKEVENTS else if (iter->cpu == -1 && iter->second_pass) timer_list_show_tickdevices_header(m); else print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu); #endif return 0; } static void move_iter(struct timer_list_iter iter, loff_t offset) { for (; offset; offset--) { iter->cpu = cpumask_next(iter->cpu, cpu_online_mask); if (iter->cpu >= nr_cpu_ids) { #ifdef CONFIG_GENERIC_CLOCKEVENTS if (!iter->second_pass) { iter->cpu = -1; iter->second_pass = true; } else return NULL; #else return NULL; #endif } } return iter; } static void timer_list_start(struct seq_file file, loff_t offset) { struct timer_list_iter iter = file->private; if (!offset) iter->now = ktime_to_ns(ktime_get()); iter->cpu = -1; iter->second_pass = false; return move_iter(iter, offset); } static void timer_list_next(struct seq_file file, void v, loff_t offset) { struct timer_list_iter iter = file->private; ++offset; return move_iter(iter, 1); } static void timer_list_stop(struct seq_file seq, void v) { } static const struct seq_operations timer_list_sops = { .start = timer_list_start, .next = timer_list_next, .stop = timer_list_stop, .show = timer_list_show, }; static int __init init_timer_list_procfs(void) { struct proc_dir_entry *pe; pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops, sizeof(struct timer_list_iter), NULL); if (!pe) return -ENOMEM; return 0; } __initcall(init_timer_list_procfs); #endif ]
26/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 8344 output: 43 thoughts: 99 Thoughts: Okay, here's my summary, tailored to an expert like myself: Investigating `proc_create_seq_private` and Permissions Right, so I've got a file created with `0400` permissions. Nothing too surprising there. The key, however, is that `proc_create_seq_private` function is employed in its creation. My immediate thought is, I need to understand how that specific function handles the user and group IDs (UID/GID) for the newly created proc entry. My gut says that if `proc_create_seq_private` doesn't explicitly set them, it'll default to root (0). That's the typical behavior, and I need to confirm this. Time to dive into the source code to get the definitive answer. I'll need to locate the definition of `proc_create_seq_private` -- `fs/proc/generic.c` seems like the most likely place, or wherever the relevant procfs code resides for my kernel version. I'll focus on how the UID/GID are set or defaulted during the creation process. That should tell me if I need to explicitly set them to avoid running afoul of security constraints.
27/4	2026/05/23 11:35	tool	codesearch-definition-source	0m Args: map[ContextFile:fs/proc/generic.c IncludeLines:true Name:proc_create_seq_private] Results: map[SourceCode: 634: struct proc_dir_entry proc_create_seq_private(const char name, umode_t mode, 635: struct proc_dir_entry parent, const struct seq_operations ops, 636: unsigned int state_size, void data) 637: { 638: struct proc_dir_entry p; 639: 640: p = proc_create_reg(name, mode, &parent, data); 641: if (!p) 642: return NULL; 643: p->proc_ops = &proc_seq_ops; 644: p->seq_ops = ops; 645: p->state_size = state_size; 646: return proc_register(parent, p); 647: } SourceFile:fs/proc/generic.c]
28/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 9000 output: 41 thoughts: 21 Thoughts: Here's my take on the thought process, as requested: Deconstructing the Process Creation Okay, so the code's jumping into `proc_create_reg`. That function name rings a bell, but let's not rely on memory alone. I need to understand what's happening at this core level. This feels like the pivotal point for the process creation, the function that's responsible for the registration aspects of the procedure, and that likely involves setting up the data structures and context needed for the new process within the kernel's process table or its equivalent. We need to dig into this `proc_create_reg` to figure out its inner workings. Let's see what that function does.
29/4	2026/05/23 11:35	tool	codesearch-definition-source	0m Args: map[ContextFile:fs/proc/generic.c IncludeLines:true Name:proc_create_reg] Results: map[SourceCode: 566: struct proc_dir_entry proc_create_reg(const char name, umode_t mode, 567: struct proc_dir_entry *parent, void data) 568: { 569: struct proc_dir_entry *p; 570: 571: if ((mode & S_IFMT) == 0) 572: mode \|= S_IFREG; 573: if ((mode & S_IALLUGO) == 0) 574: mode \|= S_IRUGO; 575: if (WARN_ON_ONCE(!S_ISREG(mode))) 576: return NULL; 577: 578: p = __proc_create(parent, name, mode, 1); 579: if (p) { 580: p->proc_iops = &proc_file_inode_operations; 581: p->data = data; 582: } 583: return p; 584: } SourceFile:fs/proc/generic.c]
30/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 9532 output: 40 thoughts: 8 Thoughts: Okay, here's my interpretation of that thought process, assuming I'm deep in the weeds of kernel development: Initial Assessment: Creation of a Process Entry Alright, so the core of this operation hinges on the `__proc_create` function. That immediately tells me we're dealing with the fundamental setup of a process or a related process-like entity within the kernel. I need to understand the context. Is this a new task, a thread, or perhaps a system-level process we're constructing? The name itself screams "create," so it's likely about instantiating a new process control block (PCB), or its equivalent in this architecture. My mind immediately starts ticking through the implications. I’m thinking about the arguments passed to `__proc_create`. What data structures are initialized? What security checks are performed? How does it allocate memory for the process's context and address space if it handles such allocation? Does it register the new process with any global data structures, such as a process table or a scheduler queue? I'll probably need to understand the flow control to ensure it's thread-safe. I'm wondering if this is a low-level operation that builds up the necessary data structures or if this is the high-level API call for user-facing applications. Understanding the semantics of `__proc_create` is absolutely crucial for tracing through the rest of the execution path. And I know I will need to look up documentation to ensure I understand every aspect of this function.
31/4	2026/05/23 11:35	tool	codesearch-definition-source	0m Args: map[ContextFile:fs/proc/generic.c IncludeLines:true Name:__proc_create] Results: map[SourceCode: 418: static struct proc_dir_entry __proc_create(struct proc_dir_entry parent, 419: const char name, 420: umode_t mode, 421: nlink_t nlink) 422: { 423: struct proc_dir_entry ent = NULL; 424: const char fn; 425: struct qstr qstr; 426: 427: if (xlate_proc_name(name, parent, &fn) != 0) 428: goto out; 429: qstr.name = fn; 430: qstr.len = strlen(fn); 431: if (qstr.len == 0 \|\| qstr.len >= 256) { 432: WARN(1, "name len %u\n", qstr.len); 433: return NULL; 434: } 435: if (qstr.len == 1 && fn[0] == '.') { 436: WARN(1, "name '.'\n"); 437: return NULL; 438: } 439: if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') { 440: WARN(1, "name '..'\n"); 441: return NULL; 442: } 443: if (parent == &proc_root && name_to_int(&qstr) != ~0U) { 444: WARN(1, "create '/proc/%s' by hand\n", qstr.name); 445: return NULL; 446: } 447: if (is_empty_pde(parent)) { 448: WARN(1, "attempt to add to permanently empty directory"); 449: return NULL; 450: } 451: 452: ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); 453: if (!ent) 454: goto out; 455: 456: if (qstr.len + 1 <= SIZEOF_PDE_INLINE_NAME) { 457: ent->name = ent->inline_name; 458: } else { 459: ent->name = kmalloc(qstr.len + 1, GFP_KERNEL); 460: if (!ent->name) { 461: pde_free(ent); 462: return NULL; 463: } 464: } 465: 466: memcpy(ent->name, fn, qstr.len + 1); 467: ent->namelen = qstr.len; 468: ent->mode = mode; 469: ent->nlink = nlink; 470: ent->subdir = RB_ROOT; 471: refcount_set(&ent->refcnt, 1); 472: spin_lock_init(&ent->pde_unload_lock); 473: INIT_LIST_HEAD(&ent->pde_openers); 474: proc_set_user(ent, (parent)->uid, (parent)->gid); 475: 476: /* Revalidate everything under /proc/${pid}/net / 477: if ((parent)->flags & PROC_ENTRY_FORCE_LOOKUP) 478: pde_force_lookup(ent); 479: 480: out: 481: return ent; 482: } SourceFile:fs/proc/generic.c]
32/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 10929 output: 42 thoughts: 377 Thoughts: Analyzing the /proc/timer_list Entry Creation Okay, so I'm digging into how the `/proc/timer_list` entry is created. My initial thought was to look at how the user and group are set for this new process entry. The code snippet in `__proc_create` shows that `proc_set_user` sets the new entry's UID and GID to those of its parent. That's straightforward enough. The tricky part is that, for `/proc/timer_list`, the parent seems to be `NULL` in the `proc_create_seq_private` function. My initial assumption was this would default the UID/GID to that of `proc_root`, but that's not what the code appears to do. Now I'm looking at `proc_create_reg`. This function is pivotal; it takes a `struct proc_dir_entry *parent`. The double pointer is unusual and now I see that `proc_create_seq_private` passes the address* of its `parent` variable to `proc_create_reg`. This is a crucial distinction. If `parent` is initially `NULL`, it's now a pointer to `NULL`, which changes how it's handled. Okay, let's step through. `proc_create_reg` calls `__proc_create`, passing the potentially-`NULL` parent. In `__proc_create`, the `xlate_proc_name` function seems like the logical place to check. That function probably has to handle this potential `NULL` parent and correctly process the entry's parent. I need to investigate `xlate_proc_name` to see what it's doing with that `NULL` pointer. That's the key to understanding the UID/GID assignment.
33/4	2026/05/23 11:35	tool	codesearch-definition-source	0m Args: map[ContextFile:fs/proc/generic.c IncludeLines:true Name:xlate_proc_name] Results: map[SourceCode: 182: static int xlate_proc_name(const char name, struct proc_dir_entry ret, 183: const char *residual) 184: { 185: int rv; 186: 187: read_lock(&proc_subdir_lock); 188: rv = __xlate_proc_name(name, ret, residual); 189: read_unlock(&proc_subdir_lock); 190: return rv; 191: } SourceFile:fs/proc/generic.c]
34/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 11904 output: 43 thoughts: 10 Thoughts: Okay, here's my attempt at summarizing the thought process, tailored for an expert audience, and written in the first person: Analyzing `__xlate_proc_name` and Its Implications Alright, let's break this down. When I see `__xlate_proc_name`, my mind immediately goes into overdrive, considering its potential role in translation or conversion processes. The double underscore prefix is a classic indicator, isn't it? It suggests an internal, implementation-specific function or symbol, very likely hidden from direct public use. That sparks a few questions right off the bat: * What's the context? Am I dealing with a compiler, an interpreter, a library, or a specific system call? The application domain is crucial to interpreting this. Is it a language runtime, OS kernel component, or something else entirely? The environment will significantly color my understanding. * What's being translated? Is it code (e.g., intermediate representation to machine code, or even source code translation), data, or addresses? The data type or structure undergoing translation provides a lot of context here. Is this an internal data representation being translated into a more user-friendly form? * What's the process? Based on the name, it's clear there's some sort of name translation happening. Are we talking about symbol resolution, stringification, or macro expansion? Is it related to dynamic linking, name mangling, or something more specialized? The algorithm employed here is what I want to understand. * How robust is it? Error handling is key. This could be where the magic, or the bugs, reside. What are the failure modes? What happens if the name can't be translated? Are there graceful fallbacks or will it throw a cryptic error? And what about security? Does this process introduce any vulnerabilities, such as format string vulnerabilities? * Performance implications: Any kind of name translation, especially if done dynamically, can introduce performance bottlenecks. I need to think about how often this function gets called, the complexity of its logic, and any caching or optimization strategies that might be in place. If it's a critical path, every cycle matters. So, while I'm looking at `__xlate_proc_name`, I'm simultaneously probing for clues about these areas. It could be a simple utility function, or a highly sophisticated piece of the puzzle. I need more information to really pin it down, but the initial impressions give me a good framework to start with. Let's see how much more context I can gather.
35/4	2026/05/23 11:35	tool	codesearch-definition-source	0m Args: map[ContextFile:fs/proc/generic.c IncludeLines:true Name:__xlate_proc_name] Results: map[SourceCode: 157: /* 158: * This function parses a name such as "tty/driver/serial", and 159: * returns the struct proc_dir_entry for "/proc/tty/driver", and 160: * returns "serial" in residual. 161: / 162: static int __xlate_proc_name(const char name, struct proc_dir_entry ret, 163: const char residual) 164: { 165: const char cp = name, next; 166: struct proc_dir_entry de; 167: 168: de = ret ?: &proc_root; 169: while ((next = strchr(cp, '/')) != NULL) { 170: de = pde_subdir_find(de, cp, next - cp); 171: if (!de) { 172: WARN(1, "name '%s'\n", name); 173: return -ENOENT; 174: } 175: cp = next + 1; 176: } 177: residual = cp; 178: ret = de; 179: return 0; 180: } SourceFile:fs/proc/generic.c]
36/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 12888 output: 39 thoughts: 130 Thoughts: Analyzing the User ID and Group ID Assignment in `procfs` Okay, so I'm tracing the user and group ID assignments within the `procfs` implementation, specifically when creating a new entry. It looks like if `ret` is `NULL`, the code defaults to using `&proc_root`. This means `parent` gets set to `&proc_root` in that scenario. Makes sense, that's the default root directory. Then, back in `__proc_create`, on line 474, `proc_set_user(ent, (parent)->uid, (*parent)->gid)` is executed. Aha, so `ent->uid` and `ent->gid` are assigned values from the parent – which, in this `NULL` `ret` case, is `proc_root.uid` and `proc_root.gid`. This is the crux of how the permissions are propagated from the root. Now, to be absolutely certain of the default initial values I need to check where `proc_root` is initialized. Let me go over to `fs/proc/root.c` and take a look.
37/4	2026/05/23 11:35	tool	codesearch-definition-source	0m Args: map[ContextFile:fs/proc/root.c IncludeLines:true Name:proc_root] Results: map[SourceCode: 442: /* 443: * This is the root "inode" in the /proc tree.. 444: */ 445: struct proc_dir_entry proc_root = { 446: .low_ino = PROCFS_ROOT_INO, 447: .namelen = 5, 448: .mode = S_IFDIR \| S_IRUGO \| S_IXUGO, 449: .nlink = 2, 450: .refcnt = REFCOUNT_INIT(1), 451: .proc_iops = &proc_root_inode_operations, 452: .proc_dir_ops = &proc_root_operations, 453: .parent = &proc_root, 454: .subdir = RB_ROOT, 455: .name = "/proc", 456: }; SourceFile:fs/proc/root.c]
38/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 13580 output: 41 thoughts: 362 Thoughts: Analyzing `/proc/timer_list` Permissions in User Namespaces Okay, so I'm looking at this code and trying to figure out the security implications, specifically around `/proc/timer_list`. My initial thought was that since the code doesn't explicitly assign a user ID (`.uid`) or group ID (`.gid`), it should default to 0, which would be the global root, `GLOBAL_ROOT_UID/GID`. But then I saw the `proc_set_user` function, and that clarifies things: it does set `de->uid` and `de->gid`, just not directly in this snippet. So that means `/proc/timer_list` is owned by the global root user and group, and its mode is `0400`. That's important. It basically means only the global root can read it. Now, the interesting question is: what happens when a process in a user namespace tries to access it? That's where things get tricky. A process inside a user namespace has a specific UID within that namespace. If it's the "root" of the namespace, its UID inside that namespace is 0. But, crucially, its UID in the initial, or "parent", namespace (where `/proc/timer_list` was created) is whatever UID was used to create that namespace. Then I paused and considered `/proc` itself. I had to remind myself about how it works with user namespaces. I know `/proc` is usually shared, but some parts are namespace-specific. However, `/proc/timer_list` is a global file, created at boot. That makes the whole thing much more interesting. Okay, so if a process within a user namespace tries to open `/proc/timer_list`, the kernel will perform a permission check. The inode for `/proc/timer_list` will have `i_uid` and `i_gid` which will be derived from the `proc_dir_entry`. That's the key. Now, I need to see exactly how `proc_get_inode` sets the inode's UID and GID to be absolutely certain. It would be helpful to trace the code to understand how it deals with UID/GID translation in the context of user namespaces. Understanding that link is the most important piece of the puzzle.
39/4	2026/05/23 11:35	tool	codesearch-definition-source	0m Args: map[ContextFile:fs/proc/inode.c IncludeLines:true Name:proc_get_inode] Results: map[SourceCode: 628: struct inode proc_get_inode(struct super_block sb, struct proc_dir_entry de) 629: { 630: struct inode inode = new_inode(sb); 631: 632: if (!inode) { 633: pde_put(de); 634: return NULL; 635: } 636: 637: inode->i_private = de->data; 638: inode->i_ino = de->low_ino; 639: simple_inode_init_ts(inode); 640: PROC_I(inode)->pde = de; 641: if (is_empty_pde(de)) { 642: make_empty_dir_inode(inode); 643: return inode; 644: } 645: 646: if (de->mode) { 647: inode->i_mode = de->mode; 648: inode->i_uid = de->uid; 649: inode->i_gid = de->gid; 650: } 651: if (de->size) 652: inode->i_size = de->size; 653: if (de->nlink) 654: set_nlink(inode, de->nlink); 655: 656: if (S_ISREG(inode->i_mode)) { 657: inode->i_op = de->proc_iops; 658: if (pde_has_proc_read_iter(de)) 659: inode->i_fop = &proc_iter_file_ops; 660: else 661: inode->i_fop = &proc_reg_file_ops; 662: #ifdef CONFIG_COMPAT 663: if (pde_has_proc_compat_ioctl(de)) { 664: if (pde_has_proc_read_iter(de)) 665: inode->i_fop = &proc_iter_file_ops_compat; 666: else 667: inode->i_fop = &proc_reg_file_ops_compat; 668: } 669: #endif 670: } else if (S_ISDIR(inode->i_mode)) { 671: inode->i_op = de->proc_iops; 672: inode->i_fop = de->proc_dir_ops; 673: } else if (S_ISLNK(inode->i_mode)) { 674: inode->i_op = de->proc_iops; 675: inode->i_fop = NULL; 676: } else { 677: BUG(); 678: } 679: return inode; 680: } SourceFile:fs/proc/inode.c]
40/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 15324 output: 43 thoughts: 650 Thoughts: Analyzing `/proc/timer_list` Access in User Namespaces Okay, so I'm diving into how `/proc/timer_list` works with user namespaces. It looks like the inode's UID and GID are set from the `proc_dir_entry`, and that's initially global root (UID 0). Makes sense. Now, the standard VFS permission check, probably using something like `generic_permission`, kicks in when a process in a user namespace tries to access it. Right, the key here is how the kernel handles credentials in user namespaces. It's comparing the process's `fsuid` with the inode's `i_uid`. And, oh yeah, I need to remember that `inode->i_uid` is a `kuid_t`, that's an internal kernel representation, meaning it's using the global UID. Got it. Permission checks usually boil down to something like `inode_owner_or_capable`, so either the `fsuid` matches `i_uid` or the process has `CAP_DAC_OVERRIDE`. Now, the tricky part... capabilities are namespaced. So, a process's `CAP_DAC_OVERRIDE` in a user namespace only works for files where the global UID is mapped into the namespace. If `/proc/timer_list` is owned by global root, which it is, and the user namespace doesn't map global root (UID 0) – which is typical for unprivileged namespaces – then even `CAP_DAC_OVERRIDE` within the namespace won't help. The file's still owned by global root, and the process's `fsuid` (likely some non-zero global UID) won't match. Hold on, I see the catch. Unprivileged user namespaces usually map the creating user's UID to 0 in the new namespace, but not usually global UID 0. If global UID 0 isn't mapped, the file's UID will appear to be something else, usually `overflowuid` (65534) from within the namespace, or some other unmapped UID. So the process's UID would definitely not match the apparent owner. And `CAP_DAC_OVERRIDE` won't apply to global root. So, for a `0400` file owned by global root, it should be inaccessible to an unprivileged user within a user namespace unless, and this is important, the namespace has global root mapped or the user is actually global root. Makes sense. But wait a minute, I have to remember that `/proc` isn't always standard. Some `/proc` files can have custom permission handlers. However, `timer_list` uses `proc_file_inode_operations`, so it's probably using the standard VFS checks. Time to go check `proc_file_inode_operations` to be absolutely certain...
41/4	2026/05/23 11:35	tool	codesearch-definition-source	0m Args: map[ContextFile:fs/proc/generic.c IncludeLines:true Name:proc_file_inode_operations] Results: map[SourceCode: 153: static const struct inode_operations proc_file_inode_operations = { 154: .setattr = proc_setattr, 155: }; SourceFile:fs/proc/generic.c]
42/4	2026/05/23 11:35	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 16731 output: 30 thoughts: 1335 Thoughts: Analyzing `/proc/timer_list` Accessibility in User Namespaces Okay, so the initial question revolves around whether an unprivileged user can read `/proc/timer_list`. My first thought is that since there's no explicit `.permission` method, it relies on the default file permissions. Then, I need to verify that `proc_create_seq_private` is consistently used with `0400` for this file, which the user confirmed. I've double-checked in the kernel code (`kernel/time/timer_list.c`) and that's indeed the case. The key then becomes how the `proc` filesystem behaves within user namespaces, specifically around mount options. When mounting `/proc` in a user namespace, it usually creates a new mount instance linked to the associated PID namespace. Given that user namespaces and PID namespaces are frequently created together, I need to understand what happens to file UIDs in this scenario. I've looked at `proc_fill_super` in `fs/proc/root.c` and remember that `proc_get_inode` will use the `de->uid` and `de->gid`. `proc_root`'s `uid` and `gid` are initialized to 0. The crucial part here is how this interacts with user namespace mapping. If the global UID 0 isn't mapped within the user namespace, the inode's `i_uid` remains global UID 0, and `stat` will likely report an `overflowuid`. With a `0400` permission, only the owner (global UID 0) can read it. However, if my UID within the namespace is, say, 1000 (mapped to 0), I am not the owner. Therefore, I can't read it. I'm wondering if there's any mechanism to change ownership of `/proc` entries based on the namespace. While some entries under `/proc/[pid]/` get the PID's owner, `/proc/timer_list` is a top-level entry. Let's quickly check whether `timer_list` has some namespace specific treatment or some security check to see if it is considered safe. I don't see any special handling in `kernel/time/timer_list.c`. The `proc_set_user` function isn't called after the creation of the entry, so there is no way to change the user's permissions once the file is made. A key concern is that this `/proc` file might leak kernel addresses, as it displays addresses. I know `%p` might be hashed unless `%pK` is used, and `kptr_restrict` is set. Even with those measures, timing information might still be exposed. I confirmed from the code that `timer_list_show` prints addresses. I've verified that `proc_create_seq_private` is the only method of creating the file. Now, if the user namespace does map global UID 0 (which is unlikely), a process could be UID 0 and access it. But, this is ruled out by the premise of an unprivileged user. I've also verified that the file creation mode is indeed `0400`. There's no after-the-fact change to permissions. Finally, I checked for other `timer_list` proc files with a `git grep`, but this appears to be the only one. Just to be completely thorough, I confirmed that `proc_root`'s UID/GID are always initialized to 0, and that no code changes them later. I verified this with a search of the code. Given the `0400` permissions, the default ownership of UID 0, the lack of any namespace-specific permission changes, and that the unprivileged user likely cannot map UID 0, the answer should be no; the user cannot read `/proc/timer_list`.
43/4	2026/05/23 11:35	tool	grepper	0m Error: no matches Args: map[Expression:proc_root.uid\|proc_set_user\(&proc_root] Results: map[Output:]
44/4	2026/05/23 11:36	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 18947 output: 22 thoughts: 1111 Thoughts: Analyzing the Accessibility of `/proc/timer_list` Okay, let's break this down. My initial understanding is that `/proc/timer_list` inherits its ownership from `proc_root`, which, in turn, is owned by global root. Its mode is set to `0400`, meaning it's intended to be readable only by root. I should double-check that `proc_create_seq_private` always sets this mode. Right, it's hardcoded, so that's consistent. I also made sure that the `subset=pid` mount option does not change this behavior, it doesn't. Now, I can't directly verify if an unprivileged user can read it on a live system, but I can trace the code. I need to figure out how the permission check actually happens. My next step is to examine the read path. I'm looking for special permission checks in `seq_read` or `proc_reg_read`. I know `proc_reg_open` is called when the file is opened, and if the associated `proc_ops` structure has a `.proc_open` method, that's called. For `timer_list`, this uses `proc_seq_ops` which means `proc_seq_open` is called, which then uses `seq_open`. Nothing obvious there. The permission check should be happening in the VFS layer, specifically with `may_open`. `may_open` then calls `inode_permission`. `inode_permission` calls `do_inode_permission`. If the inode has an `.i_op->permission` method defined, that's called; otherwise, it calls `generic_permission`. The `proc_file_inode_operations` doesn't have a `.permission` method, so it uses `generic_permission`. `generic_permission` first checks ACLs, but it's the `acl_permission_check` that matters here. If there are no ACLs, it checks the mode bits directly. With `0400`, it checks: if the caller's UID matches the inode's UID, then the read permission (the `4`) is checked. If the caller's UID does not match, it checks group and other permissions. Those are 0, so access is denied unless the user has `CAP_DAC_OVERRIDE`. `capable_wrt_inode_uidgid` will be called, which in turn checks if the caller has the capability in the namespace that owns the inode. Now, who owns the inode? The inode's UID/GID are global root. I know that the procfs superblock has `s_user_ns`. If procfs is mounted in a user namespace, then `s_user_ns` is that user namespace. I should re-examine how the `proc_mount` function sets `s_user_ns`. Let me look at `fs/proc/root.c`... Ah, yes. It uses `mount_ns`. So, if a user namespace is involved, this is the key. It's likely `mount_nodev`, but I need to confirm this.
45/4	2026/05/23 11:36	tool	read-file	0m Args: map[File:fs/proc/root.c] Results: map[Contents:// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/root.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc root directory handling functions / #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/stat.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/pid_namespace.h> #include <linux/fs_parser.h> #include <linux/cred.h> #include <linux/magic.h> #include <linux/slab.h> #include "internal.h" struct proc_fs_context { struct pid_namespace pid_ns; unsigned int mask; enum proc_hidepid hidepid; int gid; enum proc_pidonly pidonly; }; enum proc_param { Opt_gid, Opt_hidepid, Opt_subset, Opt_pidns, }; static const struct fs_parameter_spec proc_fs_parameters[] = { fsparam_u32("gid", Opt_gid), fsparam_string("hidepid", Opt_hidepid), fsparam_string("subset", Opt_subset), fsparam_file_or_string("pidns", Opt_pidns), {} }; static inline int valid_hidepid(unsigned int value) { return (value == HIDEPID_OFF \|\| value == HIDEPID_NO_ACCESS \|\| value == HIDEPID_INVISIBLE \|\| value == HIDEPID_NOT_PTRACEABLE); } static int proc_parse_hidepid_param(struct fs_context fc, struct fs_parameter param) { struct proc_fs_context ctx = fc->fs_private; struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid); struct fs_parse_result result; int base = (unsigned long)hidepid_u32_spec.data; if (param->type != fs_value_is_string) return invalf(fc, "proc: unexpected type of hidepid value\n"); if (!kstrtouint(param->string, base, &result.uint_32)) { if (!valid_hidepid(result.uint_32)) return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); ctx->hidepid = result.uint_32; return 0; } if (!strcmp(param->string, "off")) ctx->hidepid = HIDEPID_OFF; else if (!strcmp(param->string, "noaccess")) ctx->hidepid = HIDEPID_NO_ACCESS; else if (!strcmp(param->string, "invisible")) ctx->hidepid = HIDEPID_INVISIBLE; else if (!strcmp(param->string, "ptraceable")) ctx->hidepid = HIDEPID_NOT_PTRACEABLE; else return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); return 0; } static int proc_parse_subset_param(struct fs_context fc, char value) { struct proc_fs_context ctx = fc->fs_private; while (value) { char ptr = strchr(value, ','); if (ptr != NULL) ptr++ = '\0'; if (value != '\0') { if (!strcmp(value, "pid")) { ctx->pidonly = PROC_PIDONLY_ON; } else { return invalf(fc, "proc: unsupported subset option - %s\n", value); } } value = ptr; } return 0; } #ifdef CONFIG_PID_NS static int proc_parse_pidns_param(struct fs_context fc, struct fs_parameter param, struct fs_parse_result result) { struct proc_fs_context ctx = fc->fs_private; struct pid_namespace target, active = task_active_pid_ns(current); struct ns_common ns; struct file ns_filp __free(fput) = NULL; switch (param->type) { case fs_value_is_file: / came through fsconfig, steal the file reference / ns_filp = no_free_ptr(param->file); break; case fs_value_is_string: ns_filp = filp_open(param->string, O_RDONLY, 0); break; default: WARN_ON_ONCE(true); break; } if (!ns_filp) ns_filp = ERR_PTR(-EBADF); if (IS_ERR(ns_filp)) { errorfc(fc, "could not get file from pidns argument"); return PTR_ERR(ns_filp); } if (!proc_ns_file(ns_filp)) return invalfc(fc, "pidns argument is not an nsfs file"); ns = get_proc_ns(file_inode(ns_filp)); if (ns->ns_type != CLONE_NEWPID) return invalfc(fc, "pidns argument is not a pidns file"); target = container_of(ns, struct pid_namespace, ns); / * pidns= is shorthand for joining the pidns to get a fsopen fd, so the * permission model should be the same as pidns_install(). / if (!ns_capable(target->user_ns, CAP_SYS_ADMIN)) { errorfc(fc, "insufficient permissions to set pidns"); return -EPERM; } if (!pidns_is_ancestor(target, active)) return invalfc(fc, "cannot set pidns to non-descendant pidns"); put_pid_ns(ctx->pid_ns); ctx->pid_ns = get_pid_ns(target); put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->pid_ns->user_ns); return 0; } #endif / CONFIG_PID_NS / static int proc_parse_param(struct fs_context fc, struct fs_parameter param) { struct proc_fs_context ctx = fc->fs_private; struct fs_parse_result result; int opt, err; opt = fs_parse(fc, proc_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_gid: ctx->gid = result.uint_32; break; case Opt_hidepid: err = proc_parse_hidepid_param(fc, param); if (err) return err; break; case Opt_subset: err = proc_parse_subset_param(fc, param->string); if (err) return err; break; case Opt_pidns: #ifdef CONFIG_PID_NS /* * We would have to RCU-protect every proc_pid_ns() or * proc_sb_info() access if we allowed this to be reconfigured * for an existing procfs instance. Luckily, procfs instances * are cheap to create, and mount-beneath would let you * atomically replace an instance even with overmounts. / if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { errorfc(fc, "cannot reconfigure pidns for existing procfs"); return -EBUSY; } err = proc_parse_pidns_param(fc, param, &result); if (err) return err; break; #else errorfc(fc, "pidns mount flag not supported on this system"); return -EOPNOTSUPP; #endif default: return -EINVAL; } ctx->mask \|= 1 << opt; return 0; } static void proc_apply_options(struct proc_fs_info fs_info, struct fs_context fc, struct user_namespace user_ns) { struct proc_fs_context ctx = fc->fs_private; if (ctx->mask & (1 << Opt_gid)) fs_info->pid_gid = make_kgid(user_ns, ctx->gid); if (ctx->mask & (1 << Opt_hidepid)) fs_info->hide_pid = ctx->hidepid; if (ctx->mask & (1 << Opt_subset)) fs_info->pidonly = ctx->pidonly; if (ctx->mask & (1 << Opt_pidns) && !WARN_ON_ONCE(fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)) { put_pid_ns(fs_info->pid_ns); fs_info->pid_ns = get_pid_ns(ctx->pid_ns); } } static int proc_fill_super(struct super_block s, struct fs_context fc) { struct proc_fs_context ctx = fc->fs_private; struct inode root_inode; struct proc_fs_info fs_info; int ret; fs_info = kzalloc_obj(fs_info); if (!fs_info) return -ENOMEM; fs_info->pid_ns = get_pid_ns(ctx->pid_ns); proc_apply_options(fs_info, fc, current_user_ns()); / User space would break if executables or devices appear on proc / s->s_iflags \|= SB_I_USERNS_VISIBLE \| SB_I_NOEXEC \| SB_I_NODEV; s->s_flags \|= SB_NODIRATIME \| SB_NOSUID \| SB_NOEXEC; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = PROC_SUPER_MAGIC; s->s_op = &proc_sops; s->s_time_gran = 1; s->s_fs_info = fs_info; / * procfs isn't actually a stacking filesystem; however, there is * too much magic going on inside it to permit stacking things on * top of it / s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; / procfs dentries and inodes don't require IO to create / s->s_shrink->seeks = 0; pde_get(&proc_root); root_inode = proc_get_inode(s, &proc_root); if (!root_inode) { pr_err("proc_fill_super: get root inode failed\n"); return -ENOMEM; } s->s_root = d_make_root(root_inode); if (!s->s_root) { pr_err("proc_fill_super: allocate dentry failed\n"); return -ENOMEM; } ret = proc_setup_self(s); if (ret) { return ret; } return proc_setup_thread_self(s); } static int proc_reconfigure(struct fs_context fc) { struct super_block sb = fc->root->d_sb; struct proc_fs_info fs_info = proc_sb_info(sb); sync_filesystem(sb); proc_apply_options(fs_info, fc, current_user_ns()); return 0; } static int proc_get_tree(struct fs_context fc) { return get_tree_nodev(fc, proc_fill_super); } static void proc_fs_context_free(struct fs_context fc) { struct proc_fs_context ctx = fc->fs_private; put_pid_ns(ctx->pid_ns); kfree(ctx); } static const struct fs_context_operations proc_fs_context_ops = { .free = proc_fs_context_free, .parse_param = proc_parse_param, .get_tree = proc_get_tree, .reconfigure = proc_reconfigure, }; static int proc_init_fs_context(struct fs_context fc) { struct proc_fs_context ctx; ctx = kzalloc_obj(struct proc_fs_context); if (!ctx) return -ENOMEM; ctx->pid_ns = get_pid_ns(task_active_pid_ns(current)); put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->pid_ns->user_ns); fc->fs_private = ctx; fc->ops = &proc_fs_context_ops; return 0; } static void proc_kill_sb(struct super_block sb) { struct proc_fs_info fs_info = proc_sb_info(sb); kill_anon_super(sb); if (fs_info) { put_pid_ns(fs_info->pid_ns); kfree_rcu(fs_info, rcu); } } static struct file_system_type proc_fs_type = { .name = "proc", .init_fs_context = proc_init_fs_context, .parameters = proc_fs_parameters, .kill_sb = proc_kill_sb, .fs_flags = FS_USERNS_MOUNT \| FS_DISALLOW_NOTIFY_PERM, }; void __init proc_root_init(void) { proc_init_kmemcache(); set_proc_pid_nlink(); proc_self_init(); proc_thread_self_init(); proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); proc_mkdir("fs", NULL); proc_mkdir("driver", NULL); proc_create_mount_point("fs/nfsd"); / somewhere for the nfsd filesystem to be mounted / #if defined(CONFIG_SUN_OPENPROMFS) \|\| defined(CONFIG_SUN_OPENPROMFS_MODULE) / just give it a mountpoint / proc_create_mount_point("openprom"); #endif proc_tty_init(); proc_mkdir("bus", NULL); proc_sys_init(); / * Last things last. It is not like userspace processes eager * to open /proc files exist at this point but register last * anyway. / register_filesystem(&proc_fs_type); } static int proc_root_getattr(struct mnt_idmap idmap, const struct path path, struct kstat stat, u32 request_mask, unsigned int query_flags) { generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(path->dentry), stat); stat->nlink = proc_root.nlink + nr_processes(); return 0; } static struct dentry proc_root_lookup(struct inode dir, struct dentry * dentry, unsigned int flags) { if (!proc_pid_lookup(dentry, flags)) return NULL; return proc_lookup(dir, dentry, flags); } static int proc_root_readdir(struct file file, struct dir_context ctx) { if (ctx->pos < FIRST_PROCESS_ENTRY) { int error = proc_readdir(file, ctx); if (unlikely(error <= 0)) return error; ctx->pos = FIRST_PROCESS_ENTRY; } return proc_pid_readdir(file, ctx); } /* * The root /proc directory is special, as it has the * <pid> directories. Thus we don't use the generic * directory handling functions for that.. / static const struct file_operations proc_root_operations = { .read = generic_read_dir, .iterate_shared = proc_root_readdir, .llseek = generic_file_llseek, }; / * proc root can do almost nothing.. / static const struct inode_operations proc_root_inode_operations = { .lookup = proc_root_lookup, .getattr = proc_root_getattr, }; / * This is the root "inode" in the /proc tree.. */ struct proc_dir_entry proc_root = { .low_ino = PROCFS_ROOT_INO, .namelen = 5, .mode = S_IFDIR \| S_IRUGO \| S_IXUGO, .nlink = 2, .refcnt = REFCOUNT_INIT(1), .proc_iops = &proc_root_inode_operations, .proc_dir_ops = &proc_root_operations, .parent = &proc_root, .subdir = RB_ROOT, .name = "/proc", }; ]
46/4	2026/05/23 11:36	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 25182 output: 35 thoughts: 1778 Thoughts: Analyzing `/proc/timer_list` Accessibility in User Namespaces Okay, so the user's question brings up an interesting access control scenario within user namespaces, specifically regarding `/proc/timer_list`. Let me think this through step by step. Initially, in the context of `proc_init_fs_context`, the `fc->user_ns` is set to the user namespace of the PID namespace. This implies that if a user creates a new user namespace and then a new PID namespace, the `s->s_user_ns` within the `proc` filesystem will be that new user namespace. Now, considering the `generic_permission` check, which utilizes `capable_wrt_inode_uidgid`, we need to understand how permissions are determined. `privileged_wrt_inode_uidgid` is key here: it checks if the inode's UID and GID have mappings within the current user namespace. If there's no mapping for the inode's UID (global 0, in the case of `timer_list`) or GID, access is denied. Since `timer_list`'s UID is global 0, and our unprivileged user's UID is something else, this means `CAP_DAC_OVERRIDE` isn't going to help. Moreover, because the file's mode is `0400`, the access is denied outright unless the effective UID matches the file's owner. My immediate thought was whether there might be exceptions for `/proc` files, given their system-level nature, but in this case, `/proc/timer_list` is definitely `0400`. We know it is a global PDE and is created for every proc instance. Also, I must ensure that `timer_list` is not hidden, for example, if `subset=pid` is used (it is not). It might return `ENOENT` if the filesystem is subsetted to PIDs. The core question, then, is about an unprivileged user within their own namespace. They can mount `proc`, if they also have their own PID namespace. However, the files within that mount will have the same global UIDs as the regular `/proc` (mostly). So, I checked to ensure whether the user, even if "root" within their namespace (by mapping their UID to 0), can access it. Because the inode's UID is global 0, their "local" root wouldn't be the owner, and thus wouldn't be able to access it. Now, I revisited the code to confirm if there are any other instances where `timer_list` is created, but it's only created once, during boot. I also considered whether `proc_set_user` might be called with the namespace's root UID, but `init_timer_list_procfs` runs early, in the initial namespace, so no luck there. I questioned if the file was created with a different mode, perhaps `0444`, in the past. Checking the current code, however, confirms the `0400` mode. I even checked `git log` about the permissions of `timer_list` but that's a shot in the dark. I briefly considered the `sysrq` path, knowing SysRq-Q calls `sysrq_timer_list_show`, but that prints to dmesg, which isn't the same as accessing `/proc/timer_list`. I need to stay focused on the user's original question. Furthermore, I explored if `proc_create_seq_private` might use the current namespace when creating the PDE but PDEs are global and not per-namespace, so the file's UID and GID are set at creation. `proc_get_inode` uses those fixed values. The code makes it clear `/proc/timer_list` always has `i_uid = 0` (global). I re-checked `proc_get_inode` to ensure there isn't any overriding code. I also looked at `proc_set_user`, where `de->uid` and `de->gid` are set but the parent's UID for `timer_list` is 0, so that doesn't help the unprivileged user either. Thus, the logical conclusion is: 1. `/proc/timer_list` is owned by global UID 0. 2. Its mode is `0400` (readable only by the owner). 3. An unprivileged user in a user namespace has a different global UID. 4. Even if they are "root" (UID 0) inside their namespace, their global UID remains their original UID (e.g., 1000). 5. The
47/4	2026/05/23 11:36	tool	git-log	0m Args: map[CodeRegexp:timer_list PathPrefix:kernel/time/timer_list.c] Results: map[Output:a9314773a91a timer_list: Guard procfs specific code 58c5fc2b96e4 time: Remove useless filenames in top level comments 44414d82cfe0 proc: introduce proc_create_seq_private 8e7df2b5b7f2 timer/debug: Change /proc/timer_list from 0444 to 0400 84a78a6504f5 timer_list: correct the iterator for timer_list b3956a896ea5 timer_list: Convert timer list to be a proper seq_file 60cf7ea849e7 timer_list: Split timer_list_show_tickdevices 828c09509b96 const: constify remaining file_operations de809347aeef timers: Drop write permission on /proc/timer_list c33fff0afbef kernel: use non-racy method for proc entries creation ]
48/4	2026/05/23 11:36	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 28269 output: 26 thoughts: 46 Thoughts: Okay, here's my interpretation of that commit message, expressed as my internal thought process: Diving into that Kernel Timer Change Right, that caught my eye: `8e7df2b5b7f2 timer/debug: Change /proc/timer_list from 0444 to 0400`. Always interesting to see low-level changes like this affecting `/proc`. Okay, time to dissect that commit. I'm immediately thinking about the implications of modifying the permissions on `/proc/timer_list`. Why the shift from 0444 (read-only for all) to 0400 (read-only for root)? My expert spidey senses are tingling - it suggests a security or information disclosure concern has been identified. I'm going to want to understand the rationale behind this tightening. Was there a vulnerability related to unprivileged processes accessing the timer list that needed patching? Or perhaps it was deemed an inadvertent leak of sensitive timing information that could be used for side-channel attacks? The details are crucial. Let's see if the commit message sheds any more light on the motivations, or if there's a related CVE or security advisory I need to dig into. This is definitely a change that warrants a deeper look.
49/4	2026/05/23 11:36	tool	git-show	0m Args: map[Commit:8e7df2b5b7f2] Results: map[Output:commit 8e7df2b5b7f245c9bd11064712db5cb69044a362 Author: Ingo Molnar <mingo@kernel.org> Date: Mon Nov 13 07:15:41 2017 +0100 timer/debug: Change /proc/timer_list from 0444 to 0400 While it uses %pK, there's still few reasons to read this file as non-root. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org> diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 0e7f5428a148..0ed768b56c60 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -389,7 +389,7 @@ static int __init init_timer_list_procfs(void) { struct proc_dir_entry *pe; - pe = proc_create("timer_list", 0444, NULL, &timer_list_fops); + pe = proc_create("timer_list", 0400, NULL, &timer_list_fops); if (!pe) return -ENOMEM; return 0; ]
50/4	2026/05/23 11:36	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 29069 output: 22 thoughts: 920 Thoughts: Analyzing File Permissions and User Namespaces Okay, so the commit message mentions `%pK`, but my immediate scan of the code shows `%p`, specifically in the `print_timer` function. It seems `%p` is used for the address and `%ps` for the symbol name. I need to make sure I am not missing a recent change that has not updated the documentation. Then it dawns on me: `%p` is hashed in modern kernels, which is generally preferred over `%pK` due to `kptr_restrict`. The key here is the `0400` permission. That restricts access to the file's owner, which is global root. An unprivileged user inside a user namespace is not global root. They might think they are root within their namespace, but the kernel knows they aren't the file's owner. The question then becomes, can an unprivileged user ever read it? Even in the initial user namespace, the `0400` permission prevents access. What if they're in a user namespace and have a UID mapping for what they think is root? Let me think. The check is handled by `proc_create_seq_private` with `0400`, which relies on `generic_permission`. As I recall, that uses `capable_wrt_inode_uidgid`. I remember that the `capable_wrt_inode_uidgid` will return false if the inode's UID isn't mapped. An unprivileged user cannot map global UID 0 to a local UID within their namespace. They'll typically map their own UID (e.g., 1000) to 0. So, inside the namespace, the local UID 0 is the global UID 1000, not global UID 0. The file is owned by global UID 0. The user (global 1000, local 0) is not the owner, and they don't have capabilities over global UID 0. So, no, they cannot read it. Are there any other `/proc` files with `0400` permissions that are readable within a user namespace? Some in `/proc/net` are namespace-aware, but `timer_list` isn't. Let me verify. I'll search `kernel/time/timer_list.c` for any mention of `struct net`, `user_namespace`, or `pid_namespace`. Nope, nothing there. Actually, let me check the use of `proc_create_seq_private`. Many `/proc` files are `0444`, but `timer_list` is specifically `0400`. There was a previous commit using the `proc_create_seq_private` API but that's just a change in the API, nothing more. I need to check if there are other files created with `0400` permissions in `/proc`.
51/4	2026/05/23 11:36	tool	grepper	0m Args: map[Expression:proc_create.0400] Results:* map[Output:arch/arm/kernel/atags_proc.c=33=static int __init init_atags_procfs(void) -- arch/arm/kernel/atags_proc.c-63- arch/arm/kernel/atags_proc.c:64: tags_entry = proc_create_data("atags", 0400, NULL, &atags_proc_ops, b); arch/arm/kernel/atags_proc.c-65- if (!tags_entry) -- arch/m68k/kernel/bootinfo_proc.c=55=static int __init init_bootinfo_procfs(void) -- arch/m68k/kernel/bootinfo_proc.c-69- arch/m68k/kernel/bootinfo_proc.c:70: pde = proc_create_data("bootinfo", 0400, NULL, &bootinfo_proc_ops, NULL); arch/m68k/kernel/bootinfo_proc.c-71- if (!pde) { -- arch/parisc/kernel/pdc_chassis.c=269=static int __init pdc_chassis_create_procfs(void) -- arch/parisc/kernel/pdc_chassis.c-282- PDC_CHASSIS_VER); arch/parisc/kernel/pdc_chassis.c:283: proc_create_single("chassis", 0400, NULL, pdc_chassis_warn_show); arch/parisc/kernel/pdc_chassis.c-284- return 0; -- arch/powerpc/kernel/rtas-proc.c=231=static int __init proc_rtas_init(void) -- arch/powerpc/kernel/rtas-proc.c-251- &ppc_rtas_tone_volume_proc_ops); arch/powerpc/kernel/rtas-proc.c:252: proc_create_single("powerpc/rtas/rmo_buffer", 0400, NULL, arch/powerpc/kernel/rtas-proc.c-253- ppc_rtas_rmo_buf_show); -- arch/powerpc/kernel/rtasd.c=546=static int __init rtas_init(void) -- arch/powerpc/kernel/rtasd.c-555- arch/powerpc/kernel/rtasd.c:556: entry = proc_create("powerpc/rtas/error_log", 0400, NULL, arch/powerpc/kernel/rtasd.c-557- &rtas_log_proc_ops); -- fs/smb/client/cifs_debug.c=924=cifs_proc_init(void) -- fs/smb/client/cifs_debug.c-932- fs/smb/client/cifs_debug.c:933: proc_create_single("open_files", 0400, proc_fs_cifs, fs/smb/client/cifs_debug.c-934- cifs_debug_files_proc_show); -- fs/smb/client/cifs_debug.c-938-#else /* CONFIG_CIFS_DEBUG / fs/smb/client/cifs_debug.c:939: proc_create_single("open_dirs", 0400, proc_fs_cifs, cifs_debug_dirs_proc_show); fs/smb/client/cifs_debug.c-940-#endif / !CONFIG_CIFS_DEBUG / -- fs/smb/server/proc.c=22=struct proc_dir_entry ksmbd_proc_create(const char name, -- fs/smb/server/proc.c-25-{ fs/smb/server/proc.c:26: return proc_create_single_data(name, 0400, ksmbd_proc_fs, fs/smb/server/proc.c-27- show, v); -- kernel/time/timer_list.c=349=static int __init init_timer_list_procfs(void) -- kernel/time/timer_list.c-352- kernel/time/timer_list.c:353: pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops, kernel/time/timer_list.c-354- sizeof(struct timer_list_iter), NULL); -- lib/alloc_tag.c=927=static int __init alloc_tag_init(void) -- lib/alloc_tag.c-948- lib/alloc_tag.c:949: if (!proc_create_seq_private(ALLOCINFO_FILE_NAME, 0400, NULL, &allocinfo_seq_op, lib/alloc_tag.c-950- sizeof(struct allocinfo_private), NULL)) { -- mm/vmalloc.c=5295=static int __init proc_vmalloc_init(void) mm/vmalloc.c-5296-{ mm/vmalloc.c:5297: proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); mm/vmalloc.c-5298- return 0; -- mm/vmstat.c=2268=void __init init_mm_internals(void) -- mm/vmstat.c-2294- proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); mm/vmstat.c:2295: proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); mm/vmstat.c-2296- proc_create_seq("vmstat", 0444, NULL, &vmstat_op); -- net/sunrpc/cache.c=1664=static int create_cache_proc_entries(struct cache_detail cd, struct net *net) -- net/sunrpc/cache.c-1688- if (cd->cache_show) { net/sunrpc/cache.c:1689: p = proc_create_data("content", S_IFREG \| 0400, cd->procfs, net/sunrpc/cache.c-1690- &content_proc_ops, cd); ]
52/4	2026/05/23 11:36	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 32285 output: 23 thoughts: 1401 Thoughts: Security Analysis of /proc/timer_list in User Namespaces Okay, so I'm looking at these files with `0400` permissions: `vmallocinfo`, `pagetypeinfo`, and especially `timer_list`. If an unprivileged user in a user namespace could read these, it's a huge security hole – leaking sensitive kernel info. The `0400` is there specifically to prevent this. Right, so, the key is whether the `proc` filesystem's `FS_USERNS_MOUNT` flag changes anything. Let me look at the code... Yep, `proc_fs_type` has `FS_USERNS_MOUNT`, meaning it's mountable inside a user namespace. When it's mounted, the superblock's `s_user_ns` is set to the namespace of the caller. But how does that affect permissions? The `generic_permission` function is where permissions are checked. It uses `capable_wrt_inode_uidgid`. If the inode UID is 0 (root, globally), and that UID isn't mapped in the user namespace, the check should fail, right? I need to confirm that `proc_get_inode` doesn't mess with UIDs. Ah, `proc_get_inode` just sets `inode->i_uid = de->uid`. And `de->uid` is a `kuid_t`, a global UID. So the inode always has a global UID of 0, and in a user namespace where global 0 isn't mapped, that's not "privileged". There are some exceptions for `proc` files, "namespace-safe" files. But `timer_list` isn't one of them. And `proc_create_seq_private` is called with a `NULL` parent, putting `timer_list` right at the root of `/proc`. If I'm in a user namespace and mount `proc`, the files are the same PDEs. The inodes might be new, but they're initialized from the same PDEs. So `/proc/timer_list` will always have `i_uid = 0`. Can an unprivileged user somehow map global UID 0? Not unless they have `CAP_SETUID` in the parent namespace, which they won't if they're actually unprivileged. So, the answer is "no," it shouldn't be possible. But let's verify. Let me check `proc_setattr`. Okay, `proc_setattr` lets you change UID/GID, but NOT mode. But even to change UID/GID, you need to be the owner or have `CAP_CHOWN`. An unprivileged user is neither. And all `proc` mounts share the same PDE tree, so trying a different mount won't work. But let's think this through. Can an unprivileged user read `/proc/timer_list` even in the initial namespace? No. It's `0400`, owned by root. If they can't read it there, they definitely can't read it in a more restricted user namespace. Unless the user namespace somehow makes them the owner. As we saw, that only happens if global UID 0 is mapped to them. Which, as we know, can't happen. What if they map their own UID (e.g., 1000) to 0 inside the namespace? They become UID 0 inside the namespace. But the file's `i_uid` is still global 0. Their global UID is still 1000. So, they're not the owner. What if the `i_uid` was also mapped, though? Remember, `proc_get_inode` sets `inode->i_uid` to the global UID from the PDE. So, no. Definitely "No." Wait, let's check the code specifically in `kernel/time/timer_list.c`. Anything special for `timer_list_show`? Nope. It doesn't check permissions. Permissions are checked at `open()`. Is there any other way to access it? Maybe through another file? No. Is `timer_list` available in `/proc/self/`? No. What about in a network namespace? No, it's not in `/proc/net`. Okay, finally, some documentation. Anything in `Documentation/admin-guide/kernel-parameters.txt`? Nope. Let's check `Documentation/filesystems/proc.rst`.
53/4	2026/05/23 11:36	tool	read-file	0m Args: map[File:Documentation/filesystems/proc.rst] Results: map[Contents:.. SPDX-License-Identifier: GPL-2.0 ==================== The /proc Filesystem ==================== ===================== ======================================= ================ /proc/sys Terrehon Bowden <terrehon@pacbell.net>, October 7 1999 Bodo Bauer <bb@ricochet.net> 2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000 move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009 fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009 ===================== ======================================= ================ .. Table of Contents 0 Preface 0.1 Introduction/Credits 0.2 Legal Stuff 1 Collecting System Information 1.1 Process-Specific Subdirectories 1.2 Kernel data 1.3 IDE devices in /proc/ide 1.4 Networking info in /proc/net 1.5 SCSI info 1.6 Parallel port info in /proc/parport 1.7 TTY info in /proc/tty 1.8 Miscellaneous kernel statistics in /proc/stat 1.9 Ext4 file system parameters 2 Modifying System Parameters 3 Per-Process Parameters 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer score 3.2 /proc/<pid>/oom_score - Display current oom-killer score 3.3 /proc/<pid>/io - Display the IO accounting fields 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings 3.5 /proc/<pid>/mountinfo - Information about mounts 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 3.7 /proc/<pid>/task/<tid>/children - Information about task children 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 3.9 /proc/<pid>/map_files - Information about memory mapped files 3.10 /proc/<pid>/timerslack_ns - Task timerslack value 3.11 /proc/<pid>/patch_state - Livepatch patch operation state 3.12 /proc/<pid>/arch_status - Task architecture specific information 3.13 /proc/<pid>/fd - List of symlinks to open files 3.14 /proc/<pid>/ksm_stat - Information about the process's ksm status. 4 Configuring procfs 4.1 Mount options 5 Filesystem behavior Preface ======= 0.1 Introduction/Credits ------------------------ We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of other people for help compiling this documentation. We'd also like to extend a special thank you to Andi Kleen for documentation, which we relied on heavily to create this document, as well as the additional information he provided. Thanks to everybody else who contributed source or docs to the Linux kernel and helped create a great piece of software... :) The latest version of this document is available online at https://www.kernel.org/doc/html/latest/filesystems/proc.html 0.2 Legal Stuff --------------- We don't guarantee the correctness of this document, and if you come to us complaining about how you screwed up your system because of incorrect documentation, we won't feel responsible... Chapter 1: Collecting System Information ======================================== In This Chapter --------------- * Investigating the properties of the pseudo file system /proc and its ability to provide information on the running Linux system * Examining /proc's structure * Uncovering various information about the kernel and the processes running on the system ------------------------------------------------------------------------------ The proc file system acts as an interface to internal data structures in the kernel. It can be used to obtain information about the system and to change certain kernel parameters at runtime (sysctl). First, we'll take a look at the read-only parts of /proc. In Chapter 2, we show you how you can use /proc/sys to change settings. 1.1 Process-Specific Subdirectories ----------------------------------- The directory /proc contains (among other things) one subdirectory for each process running on the system, which is named after the process ID (PID). The link 'self' points to the process reading the file system. Each process subdirectory has the entries listed in Table 1-1. A process can read its own information from /proc/PID/* with no extra permissions. When reading /proc/PID/* information for other processes, reading process is required to have either CAP_SYS_PTRACE capability with PTRACE_MODE_READ access permissions, or, alternatively, CAP_PERFMON capability. This applies to all read-only information like `maps`, `environ`, `pagemap`, etc. The only exception is `mem` file due to its read-write nature, which requires CAP_SYS_PTRACE capabilities with more elevated PTRACE_MODE_ATTACH permissions; CAP_PERFMON capability does not grant access to /proc/PID/mem for other processes. Note that an open file descriptor to /proc/<pid> or to any of its contained files or subdirectories does not prevent <pid> being reused for some other process in the event that <pid> exits. Operations on open /proc/<pid> file descriptors corresponding to dead processes never act on any new process that the kernel may, through chance, have also assigned the process ID <pid>. Instead, operations on these FDs usually fail with ESRCH. .. table:: Table 1-1: Process specific entries in /proc ============= =============================================================== File Content ============= =============================================================== clear_refs Clears page referenced bits shown in smaps output cmdline Command line arguments cpu Current and last cpu in which it was executed (2.4)(smp) cwd Link to the current working directory environ Values of environment variables exe Link to the executable of this process fd Directory, which contains all file descriptors maps Memory maps to executables and library files (2.4) mem Memory held by this process root Link to the root directory of this process stat Process status statm Process memory status information status Process status in human readable form wchan Present with CONFIG_KALLSYMS=y: it shows the kernel function symbol the task is blocked in - or "0" if not blocked. pagemap Page table stack Report full stack trace, enable via CONFIG_STACKTRACE smaps An extension based on maps, showing the memory consumption of each mapping and flags associated with it smaps_rollup Accumulated smaps stats for all mappings of the process. This can be derived from smaps, but is faster and more convenient numa_maps An extension based on maps, showing the memory locality and binding policy as well as mem usage (in pages) of each mapping. ============= =============================================================== For example, to get the status information of a process, all you have to do is read the file /proc/PID/status:: >cat /proc/self/status Name: cat State: R (running) Tgid: 5452 Pid: 5452 PPid: 743 TracerPid: 0 (2.4) Uid: 501 501 501 501 Gid: 100 100 100 100 FDSize: 256 Groups: 100 14 16 Kthread: 0 VmPeak: 5004 kB VmSize: 5004 kB VmLck: 0 kB VmHWM: 476 kB VmRSS: 476 kB RssAnon: 352 kB RssFile: 120 kB RssShmem: 4 kB VmData: 156 kB VmStk: 88 kB VmExe: 68 kB VmLib: 1412 kB VmPTE: 20 kb VmSwap: 0 kB HugetlbPages: 0 kB CoreDumping: 0 THP_enabled: 1 Threads: 1 SigQ: 0/28578 SigPnd: 0000000000000000 ShdPnd: 0000000000000000 SigBlk: 0000000000000000 SigIgn: 0000000000000000 SigCgt: 0000000000000000 CapInh: 00000000fffffeff CapPrm: 0000000000000000 CapEff: 0000000000000000 CapBnd: ffffffffffffffff CapAmb: 0000000000000000 NoNewPrivs: 0 Seccomp: 0 Speculation_Store_Bypass: thread vulnerable SpeculationIndirectBranch: conditional enabled voluntary_ctxt_switches: 0 nonvoluntary_ctxt_switches: 1 This shows you nearly the same information you would get if you viewed it with the ps command. In fact, ps uses the proc file system to obtain its information. But you get a more detailed view of the process by reading the file /proc/PID/status. It fields are described in table 1-2. The statm file contains more detailed information about the process memory usage. Its seven fields are explained in Table 1-3. The stat file contains detailed information about the process itself. Its fields are explained in Table 1-4. (for SMP CONFIG users) For making accounting scalable, RSS related information are handled in an asynchronous manner and the value may not be very precise. To see a precise snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table. It's slow but very precise. .. table:: Table 1-2: Contents of the status fields (as of 4.19) ========================== =================================================== Field Content ========================== =================================================== Name filename of the executable Umask file mode creation mask State state (R is running, S is sleeping, D is sleeping in an uninterruptible wait, Z is zombie, T is traced or stopped) Tgid thread group ID Ngid NUMA group ID (0 if none) Pid process id PPid process id of the parent process TracerPid PID of process tracing this process (0 if not, or the tracer is outside of the current pid namespace) Uid Real, effective, saved set, and file system UIDs Gid Real, effective, saved set, and file system GIDs FDSize number of file descriptor slots currently allocated Groups supplementary group list NStgid descendant namespace thread group ID hierarchy NSpid descendant namespace process ID hierarchy NSpgid descendant namespace process group ID hierarchy NSsid descendant namespace session ID hierarchy Kthread kernel thread flag, 1 is yes, 0 is no VmPeak peak virtual memory size VmSize total program size VmLck locked memory size VmPin pinned memory size VmHWM peak resident set size ("high water mark") VmRSS size of memory portions. It contains the three following parts (VmRSS = RssAnon + RssFile + RssShmem) RssAnon size of resident anonymous memory RssFile size of resident file mappings RssShmem size of resident shmem memory (includes SysV shm, mapping of tmpfs and shared anonymous mappings) VmData size of private data segments VmStk size of stack segments VmExe size of text segment VmLib size of shared library code VmPTE size of page table entries VmSwap amount of swap used by anonymous private data (shmem swap usage is not included) HugetlbPages size of hugetlb memory portions CoreDumping process's memory is currently being dumped (killing the process may lead to a corrupted core) THP_enabled process is allowed to use THP (returns 0 when PR_SET_THP_DISABLE is set on the process to disable THP completely, not just partially) Threads number of threads SigQ number of signals queued/max. number for queue SigPnd bitmap of pending signals for the thread ShdPnd bitmap of shared pending signals for the process SigBlk bitmap of blocked signals SigIgn bitmap of ignored signals SigCgt bitmap of caught signals CapInh bitmap of inheritable capabilities CapPrm bitmap of permitted capabilities CapEff bitmap of effective capabilities CapBnd bitmap of capabilities bounding set CapAmb bitmap of ambient capabilities NoNewPrivs no_new_privs, like prctl(PR_GET_NO_NEW_PRIV, ...) Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...) Speculation_Store_Bypass speculative store bypass mitigation status SpeculationIndirectBranch indirect branch speculation mode Cpus_allowed mask of CPUs on which this process may run Cpus_allowed_list Same as previous, but in "list format" Mems_allowed mask of memory nodes allowed to this process Mems_allowed_list Same as previous, but in "list format" voluntary_ctxt_switches number of voluntary context switches nonvoluntary_ctxt_switches number of non voluntary context switches ========================== =================================================== .. table:: Table 1-3: Contents of the statm fields (as of 2.6.8-rc3) ======== =============================== ============================== Field Content ======== =============================== ============================== size total program size (pages) (same as VmSize in status) resident size of memory portions (pages) (same as VmRSS in status) shared number of pages that are shared (i.e. backed by a file, same as RssFile+RssShmem in status) trs number of pages that are 'code' (not including libs; broken, includes data segment) lrs number of pages of library (always 0 on 2.6) drs number of pages of data/stack (including libs; broken, includes library text) dt number of dirty pages (always 0 on 2.6) ======== =============================== ============================== .. table:: Table 1-4: Contents of the stat fields (as of 2.6.30-rc7) ============= =============================================================== Field Content ============= =============================================================== pid process id tcomm filename of the executable state state (R is running, S is sleeping, D is sleeping in an uninterruptible wait, Z is zombie, T is traced or stopped) ppid process id of the parent process pgrp pgrp of the process sid session id tty_nr tty the process uses tty_pgrp pgrp of the tty flags task flags min_flt number of minor faults cmin_flt number of minor faults with child's maj_flt number of major faults cmaj_flt number of major faults with child's utime user mode jiffies stime kernel mode jiffies cutime user mode jiffies with child's cstime kernel mode jiffies with child's priority priority level nice nice level num_threads number of threads it_real_value (obsolete, always 0) start_time time the process started after system boot vsize virtual memory size rss resident set memory size rsslim current limit in bytes on the rss start_code address above which program text can run end_code address below which program text can run start_stack address of the start of the main process stack esp current value of ESP eip current value of EIP pending bitmap of pending signals blocked bitmap of blocked signals sigign bitmap of ignored signals sigcatch bitmap of caught signals 0 (place holder, used to be the wchan address, use /proc/PID/wchan instead) 0 (place holder) 0 (place holder) exit_signal signal to send to parent thread on exit task_cpu which CPU the task is scheduled on rt_priority realtime priority policy scheduling policy (man sched_setscheduler) blkio_ticks time spent waiting for block IO gtime guest time of the task in jiffies cgtime guest time of the task children in jiffies start_data address above which program data+bss is placed end_data address below which program data+bss is placed start_brk address above which program heap can be expanded with brk() arg_start address above which program command line is placed arg_end address below which program command line is placed env_start address above which program environment is placed env_end address below which program environment is placed exit_code the thread's exit_code in the form reported by the waitpid system call ============= =============================================================== The /proc/PID/maps file contains the currently mapped memory regions and their access permissions. The format is:: address perms offset dev inode pathname 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] a7cb1000-a7cb2000 ---p 00000000 00:00 0 a7cb2000-a7eb2000 rw-p 00000000 00:00 0 a7eb2000-a7eb3000 ---p 00000000 00:00 0 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 a800b000-a800e000 rw-p 00000000 00:00 0 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 a8024000-a8027000 rw-p 00000000 00:00 0 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack] ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] where "address" is the address space in the process that it occupies, "perms" is a set of permissions:: r = read w = write x = execute s = shared p = private (copy on write) "offset" is the offset into the mapping, "dev" is the device (major:minor), and "inode" is the inode on that device. 0 indicates that no inode is associated with the memory region, as the case would be with BSS (uninitialized data). The "pathname" shows the name associated file for this mapping. If the mapping is not associated with a file: =================== =========================================== [heap] the heap of the program [stack] the stack of the main process [vdso] the "virtual dynamic shared object", the kernel system call handler [anon:<name>] a private anonymous mapping that has been named by userspace [anon_shmem:<name>] an anonymous shared memory mapping that has been named by userspace =================== =========================================== or if empty, the mapping is anonymous. Starting with 6.11 kernel, /proc/PID/maps provides an alternative ioctl()-based API that gives ability to flexibly and efficiently query and filter individual VMAs. This interface is binary and is meant for more efficient and easy programmatic use. `struct procmap_query`, defined in linux/fs.h UAPI header, serves as an input/output argument to the `PROCMAP_QUERY` ioctl() command. See comments in linus/fs.h UAPI header for details on query semantics, supported flags, data returned, and general API usage information. The /proc/PID/smaps is an extension based on maps, showing the memory consumption for each of the process's mappings. For each mapping (aka Virtual Memory Area, or VMA) there is a series of lines such as the following:: 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash Size: 1084 kB KernelPageSize: 4 kB MMUPageSize: 4 kB Rss: 892 kB Pss: 374 kB Pss_Dirty: 0 kB Shared_Clean: 892 kB Shared_Dirty: 0 kB Private_Clean: 0 kB Private_Dirty: 0 kB Referenced: 892 kB Anonymous: 0 kB KSM: 0 kB LazyFree: 0 kB AnonHugePages: 0 kB FilePmdMapped: 0 kB ShmemPmdMapped: 0 kB Shared_Hugetlb: 0 kB Private_Hugetlb: 0 kB Swap: 0 kB SwapPss: 0 kB Locked: 0 kB THPeligible: 0 VmFlags: rd ex mr mw me dw The first of these lines shows the same information as is displayed for the mapping in /proc/PID/maps. Following lines show the size of the mapping (size); the smallest possible page size allocated when backing a VMA (KernelPageSize), which is the granularity in which VMA modifications can be performed; the smallest possible page size that could be used by the MMU (MMUPageSize) when backing a VMA; the amount of the mapping that is currently resident in RAM (RSS); the process's proportional share of this mapping (PSS); and the number of clean and dirty shared and private pages in the mapping. "KernelPageSize" always corresponds to "MMUPageSize", except when a larger kernel page size is emulated on a system with a smaller page size used by the MMU, which is the case for some PPC64 setups with hugetlb. Furthermore, "KernelPageSize" and "MMUPageSize" always correspond to the smallest possible granularity (fallback) that can be encountered in a VMA throughout its lifetime. These values are not affected by Transparent Huge Pages being in effect, or any usage of larger MMU page sizes (either through architectural huge-page mappings or other explicit/implicit coalescing of virtual ranges performed by the MMU). "AnonHugePages", "ShmemPmdMapped" and "FilePmdMapped" provide insight into the usage of PMD-level architectural huge-page mappings. The "proportional set size" (PSS) of a process is the count of pages it has in memory, where each page is divided by the number of processes sharing it. So if a process has 1000 pages all to itself, and 1000 shared with one other process, its PSS will be 1500. "Pss_Dirty" is the portion of PSS which consists of dirty pages. ("Pss_Clean" is not included, but it can be calculated by subtracting "Pss_Dirty" from "Pss".) Traditionally, a page is accounted as "private" if it is mapped exactly once, and a page is accounted as "shared" when mapped multiple times, even when mapped in the same process multiple times. Note that this accounting is independent of MAP_SHARED. In some kernel configurations, the semantics of pages part of a larger allocation (e.g., THP) can differ: a page is accounted as "private" if all pages part of the corresponding large allocation are certainly mapped in the same process, even if the page is mapped multiple times in that process. A page is accounted as "shared" if any page page of the larger allocation is maybe mapped in a different process. In some cases, a large allocation might be treated as "maybe mapped by multiple processes" even though this is no longer the case. Some kernel configurations do not track the precise number of times a page part of a larger allocation is mapped. In this case, when calculating the PSS, the average number of mappings per page in this larger allocation might be used as an approximation for the number of mappings of a page. The PSS calculation will be imprecise in this case. "Referenced" indicates the amount of memory currently marked as referenced or accessed. "Anonymous" shows the amount of memory that does not belong to any file. Even a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE and a page is modified, the file page is replaced by a private anonymous copy. "KSM" reports how many of the pages are KSM pages. Note that KSM-placed zeropages are not included, only actual KSM pages. "LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE). The memory isn't freed immediately with madvise(). It's freed in memory pressure if the memory is clean. Please note that the printed value might be lower than the real value due to optimizations used in the current implementation. If this is not desirable please file a bug report. "AnonHugePages", "ShmemPmdMapped" and "FilePmdMapped" show the amount of memory backed by Transparent Huge Pages that are currently mapped by architectural huge-page mappings at the PMD level. "AnonHugePages" corresponds to memory that does not belong to a file, "ShmemPmdMapped" to shared memory (shmem/tmpfs) and "FilePmdMapped" to file-backed memory (excluding shmem/tmpfs). There are no dedicated entries for Transparent Huge Pages (or similar concepts) that are not mapped by architectural huge-page mappings at the PMD level. "Shared_Hugetlb" and "Private_Hugetlb" show the amounts of memory backed by hugetlbfs page which is not counted in "RSS" or "PSS" field for historical reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field. "Swap" shows how much would-be-anonymous memory is also used, but out on swap. For shmem mappings, "Swap" includes also the size of the mapped (and not replaced by copy-on-write) part of the underlying shmem object out on swap. "SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this does not take into account swapped out page of underlying shmem objects. "Locked" indicates whether the mapping is locked in memory or not. "THPeligible" indicates whether the mapping is eligible for allocating naturally aligned THP pages of any currently enabled size. 1 if true, 0 otherwise. If both the kernel and the CPU support protection keys (pkeys), "ProtectionKey" indicates the memory protection key associated with the virtual memory area. "VmFlags" field deserves a separate description. This member represents the kernel flags associated with the particular virtual memory area in two letter encoded manner. The codes are the following: == ============================================================= rd readable wr writeable ex executable sh shared mr may read mw may write me may execute ms may share gd stack segment growns down pf pure PFN range lo pages are locked in memory io memory mapped I/O area sr sequential read advise provided rr random read advise provided dc do not copy area on fork de do not expand area on remapping ac area is accountable nr swap space is not reserved for the area ht area uses huge tlb pages sf synchronous page fault ar architecture specific flag wf wipe on fork dd do not include area into core dump sd soft dirty flag mm mixed map area hg huge page advise flag nh no huge page advise flag mg mergeable advise flag bt arm64 BTI guarded page mt arm64 MTE allocation tags are enabled um userfaultfd missing tracking uw userfaultfd wr-protect tracking ui userfaultfd minor fault ss shadow/guarded control stack page sl sealed lf lock on fault pages dp always lazily freeable mapping gu maybe contains guard regions (if not set, definitely doesn't) == ============================================================= Note that there is no guarantee that every flag and associated mnemonic will be present in all further kernel releases. Things get changed, the flags may be vanished or the reverse -- new added. Interpretation of their meaning might change in future as well. So each consumer of these flags has to follow each specific kernel version for the exact semantic. This file is only present if the CONFIG_MMU kernel configuration option is enabled. Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent output can be achieved only in the single read call). This typically manifests when doing partial reads of these files while the memory map is being modified. Despite the races, we do provide the following guarantees: 1) The mapped addresses never go backwards, which implies no two regions will ever overlap. 2) If there is something at a given vaddr during the entirety of the life of the smaps/maps walk, there will be some output for it. The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps, but their values are the sums of the corresponding values for all mappings of the process. Additionally, it contains these fields: - Pss_Anon - Pss_File - Pss_Shmem They represent the proportional shares of anonymous, file, and shmem pages, as described for smaps above. These fields are omitted in smaps since each mapping identifies the type (anon, file, or shmem) of all pages it contains. Thus all information in smaps_rollup can be derived from smaps, but at a significantly higher cost. The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG bits on both physical and virtual pages associated with a process, and the soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst for details). To clear the bits for all the pages associated with the process:: > echo 1 > /proc/PID/clear_refs To clear the bits for the anonymous pages associated with the process:: > echo 2 > /proc/PID/clear_refs To clear the bits for the file mapped pages associated with the process:: > echo 3 > /proc/PID/clear_refs To clear the soft-dirty bit:: > echo 4 > /proc/PID/clear_refs To reset the peak resident set size ("high water mark") to the process's current value:: > echo 5 > /proc/PID/clear_refs Any other value written to /proc/PID/clear_refs will have no effect. The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags using /proc/kpageflags and number of times a page is mapped using /proc/kpagecount. For detailed explanation, see Documentation/admin-guide/mm/pagemap.rst. The /proc/pid/numa_maps is an extension based on maps, showing the memory locality and binding policy, as well as the memory usage (in pages) of each mapping. The output follows a general format where mapping details get summarized separated by blank spaces, one mapping per each file line:: address policy mapping details 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4 320698b000 default file=/lib64/libc-2.12.so 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4 Where: "address" is the starting address for the mapping; "policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst); "mapping details" summarizes mapping data such as mapping type, page usage counters, node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page size, in KB, that is backing the mapping up. Note that some kernel configurations do not track the precise number of times a page part of a larger allocation (e.g., THP) is mapped. In these configurations, "mapmax" might corresponds to the average number of mappings per page in such a larger allocation instead. 1.2 Kernel data --------------- Similar to the process entries, the kernel data files give information about the running kernel. The files used to obtain this information are contained in /proc and are listed in Table 1-5. Not all of these will be present in your system. It depends on the kernel configuration and the loaded modules, which files are there, and which are missing. .. table:: Table 1-5: Kernel info in /proc ============ =============================================================== File Content ============ =============================================================== allocinfo Memory allocations profiling information apm Advanced power management info bootconfig Kernel command line obtained from boot config, and, if there were kernel parameters from the boot loader, a "# Parameters from bootloader:" line followed by a line containing those parameters prefixed by "# ". (5.5) buddyinfo Kernel memory allocator information (see text) (2.5) bus Directory containing bus specific information cmdline Kernel command line, both from bootloader and embedded in the kernel image cpuinfo Info about the CPU devices Available devices (block and character) dma Used DMA channels filesystems Supported filesystems driver Various drivers grouped here, currently rtc (2.4) execdomains Execdomains, related to security (2.4) fb Frame Buffer devices (2.4) fs File system parameters, currently nfs/exports (2.4) ide Directory containing info about the IDE subsystem interrupts Interrupt usage iomem Memory map (2.4) ioports I/O port usage irq Masks for irq to cpu affinity (2.4)(smp?) isapnp ISA PnP (Plug&Play) Info (2.4) kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) kmsg Kernel messages ksyms Kernel symbol table loadavg Load average of last 1, 5 & 15 minutes; number of processes currently runnable (running or on ready queue); total number of processes in system; last pid created. All fields are separated by one space except "number of processes currently runnable" and "total number of processes in system", which are separated by a slash ('/'). Example: 0.61 0.61 0.55 3/828 22084 locks Kernel locks meminfo Memory info misc Miscellaneous modules List of loaded modules mounts Mounted filesystems net Networking info (see text) pagetypeinfo Additional page allocator information (see text) (2.5) partitions Table of partitions known to the system pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, decoupled by lspci (2.4) rtc Real time clock scsi SCSI info (see text) slabinfo Slab pool info softirqs softirq usage stat Overall statistics swaps Swap space utilization sys See chapter 2 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) tty Info of tty drivers uptime Wall clock since boot, combined idle time of all cpus version Kernel version video bttv info of video resources (2.4) vmallocinfo Show vmalloced areas ============ =============================================================== You can, for example, check which interrupts are currently in use and what they are used for by looking in the file /proc/interrupts:: > cat /proc/interrupts CPU0 0: 8728810 XT-PIC timer 1: 895 XT-PIC keyboard 2: 0 XT-PIC cascade 3: 531695 XT-PIC aha152x 4: 2014133 XT-PIC serial 5: 44401 XT-PIC pcnet_cs 8: 2 XT-PIC rtc 11: 8 XT-PIC i82365 12: 182918 XT-PIC PS/2 Mouse 13: 1 XT-PIC fpu 14: 1232265 XT-PIC ide0 15: 7 XT-PIC ide1 NMI: 0 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the output of a SMP machine):: > cat /proc/interrupts CPU0 CPU1 0: 1243498 1214548 IO-APIC-edge timer 1: 8949 8958 IO-APIC-edge keyboard 2: 0 0 XT-PIC cascade 5: 11286 10161 IO-APIC-edge soundblaster 8: 1 0 IO-APIC-edge rtc 9: 27422 27407 IO-APIC-edge 3c503 12: 113645 113873 IO-APIC-edge PS/2 Mouse 13: 0 0 XT-PIC fpu 14: 22491 24012 IO-APIC-edge ide0 15: 2183 2415 IO-APIC-edge ide1 17: 30564 30414 IO-APIC-level eth0 18: 177 164 IO-APIC-level bttv NMI: 2457961 2457959 LOC: 2457882 2457881 ERR: 2155 NMI is incremented in this case because every timer interrupt generates a NMI (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups. LOC is the local interrupt counter of the internal APIC of every CPU. ERR is incremented in the case of errors in the IO-APIC bus (the bus that connects the CPUs in a SMP system. This means that an error has been detected, the IO-APIC automatically retry the transmission, so it should not be a big problem, but you should read the SMP-FAQ. In 2.6.2* /proc/interrupts was expanded again. This time the goal was for /proc/interrupts to display every IRQ vector in use by the system, not just those considered 'most important'. The new vectors are: THR interrupt raised when a machine check threshold counter (typically counting ECC corrected errors of memory or cache) exceeds a configurable threshold. Only available on some systems. TRM a thermal event interrupt occurs when a temperature threshold has been exceeded for the CPU. This interrupt may also be generated when the temperature drops back to normal. SPU a spurious interrupt is some interrupt that was raised then lowered by some IO device before it could be fully processed by the APIC. Hence the APIC sees the interrupt but does not know what device it came from. For this case the APIC will generate the interrupt with a IRQ vector of 0xff. This might also be generated by chipset bugs. RES, CAL, TLB rescheduling, call and TLB flush interrupts are sent from one CPU to another per the needs of the OS. Typically, their statistics are used by kernel developers and interested users to determine the occurrence of interrupts of the given type. The above IRQ vectors are displayed only when relevant. For example, the threshold vector does not exist on x86_64 platforms. Others are suppressed when the system is a uniprocessor. As of this writing, only i386 and x86_64 platforms support the new IRQ vector displays. Of some interest is the introduction of the /proc/irq directory to 2.4. It could be used to set IRQ to CPU affinity. This means that you can "hook" an IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the irq subdir is one subdir for each IRQ, and default_smp_affinity. For example:: > ls /proc/irq/ 0 10 12 14 16 18 2 4 6 8 default_smp_affinity 1 11 13 15 17 19 3 5 7 9 > ls /proc/irq/0/ smp_affinity smp_affinity is a bitmask, in which you can specify which CPUs can handle the IRQ. You can set it by doing:: > echo 1 > /proc/irq/10/smp_affinity This means that only the first CPU will handle the IRQ, but you can also echo 5 which means that only the first and third CPU can handle the IRQ. The contents of each smp_affinity file is the same by default:: > cat /proc/irq/0/smp_affinity ffffffff There is an alternate interface, smp_affinity_list which allows specifying a CPU range instead of a bitmask:: > cat /proc/irq/0/smp_affinity_list 1024-1031 The default_smp_affinity mask applies to all non-active IRQs, which are the IRQs which have not yet been allocated/activated, and hence which lack a /proc/irq/[0-9]* directory. The node file on an SMP system shows the node to which the device using the IRQ reports itself as being attached. This hardware locality information does not include information about any possible driver locality preference. The way IRQs are routed is handled by the IO-APIC, and it's Round Robin between all the CPUs which are allowed to handle it. As usual the kernel has more info than you and does a better job than you, so the defaults are the best choice for almost everyone. [Note this applies only to those IO-APIC's that support "Round Robin" interrupt distribution.] There are three more important subdirectories in /proc: net, scsi, and sys. The general rule is that the contents, or even the existence of these directories, depend on your kernel configuration. If SCSI is not enabled, the directory scsi may not exist. The same is true with the net, which is there only when networking support is present in the running kernel. The slabinfo file gives information about memory usage at the slab level. Linux uses slab pools for memory management above page level in version 2.2. Commonly used objects have their own slab pool (such as network buffers, directory cache, and so on). :: > cat /proc/buddyinfo Node 0, zone DMA 0 4 5 4 4 3 ... Node 0, zone Normal 1 0 0 1 101 8 ... Node 0, zone HighMem 2 0 0 1 1 0 ... External fragmentation is a problem under some workloads, and buddyinfo is a useful tool for helping diagnose these problems. Buddyinfo will give you a clue as to how big an area you can safely allocate, or why a previous allocation failed. Each column represents the number of pages of a certain order which are available. In this case, there are 0 chunks of 2^0PAGE_SIZE available in ZONE_DMA, 4 chunks of 2^1PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4PAGE_SIZE available in ZONE_NORMAL, etc... More information relevant to external fragmentation can be found in pagetypeinfo:: > cat /proc/pagetypeinfo Page block order: 9 Pages per block: 512 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate Node 0, zone DMA 2 0 5 1 0 Node 0, zone DMA32 41 6 967 2 0 Fragmentation avoidance in the kernel works by grouping pages of different migrate types into the same contiguous regions of memory called page blocks. A page block is typically the size of the default hugepage size, e.g. 2MB on X86-64. By keeping pages grouped based on their ability to move, the kernel can reclaim pages within a page block to satisfy a high-order allocation. The pagetypinfo begins with information on the size of a page block. It then gives the same type of information as buddyinfo except broken down by migrate-type and finishes with details on how many page blocks of each type exist. If min_free_kbytes has been tuned correctly (recommendations made by hugeadm from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can make an estimate of the likely number of huge pages that can be allocated at a given point in time. All the "Movable" blocks should be allocatable unless memory has been mlock()'d. Some of the Reclaimable blocks should also be allocatable although a lot of filesystem metadata may have to be reclaimed to achieve this. allocinfo ~~~~~~~~~ Provides information about memory allocations at all locations in the code base. Each allocation in the code is identified by its source file, line number, module (if originates from a loadable module) and the function calling the allocation. The number of bytes allocated and number of calls at each location are reported. The first line indicates the version of the file, the second line is the header listing fields in the file. If file version is 2.0 or higher then each line may contain additional <key>:<value> pairs representing extra information about the call site. For example if the counters are not accurate, the line will be appended with "accurate:no" pair. Supported markers in v2: accurate:no Absolute values of the counters in this line are not accurate because of the failure to allocate memory to track some of the allocations made at this location. Deltas in these counters are accurate, therefore counters can be used to track allocation size and count changes. Example output. :: > tail -n +3 /proc/allocinfo \| sort -rn 127664128 31168 mm/page_ext.c:270 func:alloc_page_ext 56373248 4737 mm/slub.c:2259 func:alloc_slab_page 14880768 3633 mm/readahead.c:247 func:page_cache_ra_unbounded 14417920 3520 mm/mm_init.c:2530 func:alloc_large_system_hash 13377536 234 block/blk-mq.c:3421 func:blk_mq_alloc_rqs 11718656 2861 mm/filemap.c:1919 func:__filemap_get_folio 9192960 2800 kernel/fork.c:307 func:alloc_thread_stack_node 4206592 4 net/netfilter/nf_conntrack_core.c:2567 func:nf_ct_alloc_hashtable 4136960 1010 drivers/staging/ctagmod/ctagmod.c:20 [ctagmod] func:ctagmod_start 3940352 962 mm/memory.c:4214 func:alloc_anon_folio 2894464 22613 fs/kernfs/dir.c:615 func:__kernfs_new_node ... meminfo ~~~~~~~ Provides information about distribution and utilization of memory. This varies by architecture and compile options. Some of the counters reported here overlap. The memory reported by the non overlapping counters may not add up to the overall memory usage and the difference for some workloads can be substantial. In many cases there are other means to find out additional memory using subsystem specific interfaces, for instance /proc/net/sockstat for TCP memory allocations. Example output. You may not have all of these fields. :: > cat /proc/meminfo MemTotal: 32858820 kB MemFree: 21001236 kB MemAvailable: 27214312 kB Buffers: 581092 kB Cached: 5587612 kB SwapCached: 0 kB Active: 3237152 kB Inactive: 7586256 kB Active(anon): 94064 kB Inactive(anon): 4570616 kB Active(file): 3143088 kB Inactive(file): 3015640 kB Unevictable: 0 kB Mlocked: 0 kB SwapTotal: 0 kB SwapFree: 0 kB Zswap: 1904 kB Zswapped: 7792 kB Dirty: 12 kB Writeback: 0 kB AnonPages: 4654780 kB Mapped: 266244 kB Shmem: 9976 kB KReclaimable: 517708 kB Slab: 660044 kB SReclaimable: 517708 kB SUnreclaim: 142336 kB KernelStack: 11168 kB PageTables: 20540 kB SecPageTables: 0 kB NFS_Unstable: 0 kB Bounce: 0 kB WritebackTmp: 0 kB CommitLimit: 16429408 kB Committed_AS: 7715148 kB VmallocTotal: 34359738367 kB VmallocUsed: 40444 kB VmallocChunk: 0 kB Percpu: 29312 kB EarlyMemtestBad: 0 kB HardwareCorrupted: 0 kB AnonHugePages: 4149248 kB ShmemHugePages: 0 kB ShmemPmdMapped: 0 kB FileHugePages: 0 kB FilePmdMapped: 0 kB CmaTotal: 0 kB CmaFree: 0 kB Unaccepted: 0 kB Balloon: 0 kB GPUActive: 0 kB GPUReclaim: 0 kB HugePages_Total: 0 HugePages_Free: 0 HugePages_Rsvd: 0 HugePages_Surp: 0 Hugepagesize: 2048 kB Hugetlb: 0 kB DirectMap4k: 401152 kB DirectMap2M: 10008576 kB DirectMap1G: 24117248 kB MemTotal Total usable RAM (i.e. physical RAM minus a few reserved bits and the kernel binary code) MemFree Total free RAM. On highmem systems, the sum of LowFree+HighFree MemAvailable An estimate of how much memory is available for starting new applications, without swapping. Calculated from MemFree, SReclaimable, the size of the file LRU lists, and the low watermarks in each zone. The estimate takes into account that the system needs some page cache to function well, and that not all reclaimable slab will be reclaimable, due to items being in use. The impact of those factors will vary from system to system. Buffers Relatively temporary storage for raw disk blocks shouldn't get tremendously large (20MB or so) Cached In-memory cache for files read from the disk (the pagecache) as well as tmpfs & shmem. Doesn't include SwapCached. SwapCached Memory that once was swapped out, is swapped back in but still also is in the swapfile (if memory is needed it doesn't need to be swapped out AGAIN because it is already in the swapfile. This saves I/O) Active Memory that has been used more recently and usually not reclaimed unless absolutely necessary. Inactive Memory which has been less recently used. It is more eligible to be reclaimed for other purposes Unevictable Memory allocated for userspace which cannot be reclaimed, such as mlocked pages, ramfs backing pages, secret memfd pages etc. Mlocked Memory locked with mlock(). HighTotal, HighFree Highmem is all memory above ~860MB of physical memory. Highmem areas are for use by userspace programs, or for the pagecache. The kernel must use tricks to access this memory, making it slower to access than lowmem. LowTotal, LowFree Lowmem is memory which can be used for everything that highmem can be used for, but it is also available for the kernel's use for its own data structures. Among many other things, it is where everything from the Slab is allocated. Bad things happen when you're out of lowmem. SwapTotal total amount of swap space available SwapFree Memory which has been evicted from RAM, and is temporarily on the disk Zswap Memory consumed by the zswap backend (compressed size) Zswapped Amount of anonymous memory stored in zswap (original size) Dirty Memory which is waiting to get written back to the disk Writeback Memory which is actively being written back to the disk AnonPages Non-file backed pages mapped into userspace page tables. Note that some kernel configurations might consider all pages part of a larger allocation (e.g., THP) as "mapped", as soon as a single page is mapped. Mapped files which have been mmapped, such as libraries. Note that some kernel configurations might consider all pages part of a larger allocation (e.g., THP) as "mapped", as soon as a single page is mapped. Shmem Total memory used by shared memory (shmem) and tmpfs KReclaimable Kernel allocations that the kernel will attempt to reclaim under memory pressure. Includes SReclaimable (below), and other direct allocations with a shrinker. Slab in-kernel data structures cache SReclaimable Part of Slab, that might be reclaimed, such as caches SUnreclaim Part of Slab, that cannot be reclaimed on memory pressure KernelStack Memory consumed by the kernel stacks of all tasks PageTables Memory consumed by userspace page tables SecPageTables Memory consumed by secondary page tables, this currently includes KVM mmu and IOMMU allocations on x86 and arm64. NFS_Unstable Always zero. Previously counted pages which had been written to the server, but has not been committed to stable storage. Bounce Always zero. Previously memory used for block device "bounce buffers". WritebackTmp Always zero. Previously memory used by FUSE for temporary writeback buffers. CommitLimit Based on the overcommit ratio ('vm.overcommit_ratio'), this is the total amount of memory currently available to be allocated on the system. This limit is only adhered to if strict overcommit accounting is enabled (mode 2 in 'vm.overcommit_memory'). The CommitLimit is calculated with the following formula:: CommitLimit = ([total RAM pages] - [total huge TLB pages]) overcommit_ratio / 100 + [total swap pages] For example, on a system with 1G of physical RAM and 7G of swap with a `vm.overcommit_ratio` of 30 it would yield a CommitLimit of 7.3G. For more details, see the memory overcommit documentation in mm/overcommit-accounting. Committed_AS The amount of memory presently allocated on the system. The committed memory is a sum of all of the memory which has been allocated by processes, even if it has not been "used" by them as of yet. A process which malloc()'s 1G of memory, but only touches 300M of it will show up as using 1G. This 1G is memory which has been "committed" to by the VM and can be used at any time by the allocating application. With strict overcommit enabled on the system (mode 2 in 'vm.overcommit_memory'), allocations which would exceed the CommitLimit (detailed above) will not be permitted. This is useful if one needs to guarantee that processes will not fail due to lack of memory once that memory has been successfully allocated. VmallocTotal total size of vmalloc virtual address space VmallocUsed amount of vmalloc area which is used VmallocChunk largest contiguous block of vmalloc area which is free Percpu Memory allocated to the percpu allocator used to back percpu allocations. This stat excludes the cost of metadata. EarlyMemtestBad The amount of RAM/memory in kB, that was identified as corrupted by early memtest. If memtest was not run, this field will not be displayed at all. Size is never rounded down to 0 kB. That means if 0 kB is reported, you can safely assume there was at least one pass of memtest and none of the passes found a single faulty byte of RAM. HardwareCorrupted The amount of RAM/memory in KB, the kernel identifies as corrupted. AnonHugePages Non-file backed huge pages mapped into userspace page tables ShmemHugePages Memory used by shared memory (shmem) and tmpfs allocated with huge pages ShmemPmdMapped Shared memory mapped into userspace with huge pages FileHugePages Memory used for filesystem data (page cache) allocated with huge pages FilePmdMapped Page cache mapped into userspace with huge pages CmaTotal Memory reserved for the Contiguous Memory Allocator (CMA) CmaFree Free remaining memory in the CMA reserves Unaccepted Memory that has not been accepted by the guest Balloon Memory returned to Host by VM Balloon Drivers GPUActive System memory allocated to active GPU objects GPUReclaim System memory stored in GPU pools for reuse. This memory is not counted in GPUActive. It is shrinker reclaimable memory kept in a reuse pool because it has non-standard page table attributes, like WC or UC. HugePages_Total, HugePages_Free, HugePages_Rsvd, HugePages_Surp, Hugepagesize, Hugetlb See Documentation/admin-guide/mm/hugetlbpage.rst. DirectMap4k, DirectMap2M, DirectMap1G Breakdown of page table sizes used in the kernel's identity mapping of RAM vmallocinfo ~~~~~~~~~~~ Provides information about vmalloced/vmaped areas. One line per area, containing the virtual address range of the area, size in bytes, caller information of the creator, and optional information depending on the kind of area: ========== =================================================== pages=nr number of pages phys=addr if a physical address was specified ioremap I/O mapping (ioremap() and friends) vmalloc vmalloc() area vmap vmap()ed pages user VM_USERMAP area vpages buffer for pages pointers was vmalloced (huge area) N<node>=nr (Only on NUMA kernels) Number of pages allocated on memory node <node> ========== =================================================== :: > cat /proc/vmallocinfo 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... phys=7fee8000 ioremap 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... phys=7fee7000 ioremap 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... pages=2 vmalloc N1=2 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... /0x130 [x_tables] pages=4 vmalloc N0=4 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... pages=14 vmalloc N2=14 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... pages=4 vmalloc N1=4 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... pages=2 vmalloc N1=2 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... pages=10 vmalloc N0=10 softirqs ~~~~~~~~ Provides counts of softirq handlers serviced since boot time, for each CPU. :: > cat /proc/softirqs CPU0 CPU1 CPU2 CPU3 HI: 0 0 0 0 TIMER: 27166 27120 27097 27034 NET_TX: 0 0 0 17 NET_RX: 42 0 0 39 BLOCK: 0 0 107 1121 TASKLET: 0 0 0 290 SCHED: 27035 26983 26971 26746 HRTIMER: 0 0 0 0 RCU: 1678 1769 2178 2250 1.3 Networking info in /proc/net -------------------------------- The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the additional values you get for IP version 6 if you configure the kernel to support this. Table 1-9 lists the files and their meaning. .. table:: Table 1-8: IPv6 info in /proc/net ========== ===================================================== File Content ========== ===================================================== udp6 UDP sockets (IPv6) tcp6 TCP sockets (IPv6) raw6 Raw device statistics (IPv6) igmp6 IP multicast addresses, which this host joined (IPv6) if_inet6 List of IPv6 interface addresses ipv6_route Kernel routing table for IPv6 rt6_stats Global IPv6 routing tables statistics sockstat6 Socket statistics (IPv6) snmp6 Snmp data (IPv6) ========== ===================================================== .. table:: Table 1-9: Network info in /proc/net ============= ================================================================ File Content ============= ================================================================ arp Kernel ARP table dev network devices with statistics dev_mcast the Layer2 multicast groups a device is listening too (interface index, label, number of references, number of bound addresses). dev_stat network device status ip_fwchains Firewall chain linkage ip_fwnames Firewall chain names ip_masq Directory containing the masquerading tables ip_masquerade Major masquerading table netstat Network statistics raw raw device statistics route Kernel routing table rpc Directory containing rpc info rt_cache Routing cache snmp SNMP data sockstat Socket statistics softnet_stat Per-CPU incoming packets queues statistics of online CPUs tcp TCP sockets udp UDP sockets unix UNIX domain sockets wireless Wireless interface data (Wavelan etc) igmp IP multicast addresses, which this host joined psched Global packet scheduler parameters. netlink List of PF_NETLINK sockets ip_mr_vifs List of multicast virtual interfaces ip_mr_cache List of multicast routing cache ============= ================================================================ You can use this information to see which network devices are available in your system and how much traffic was routed over those devices:: > cat /proc/net/dev Inter-\|Receive \|[... face \|bytes packets errs drop fifo frame compressed multicast\|[... lo: 908188 5596 0 0 0 0 0 0 [... ppp0:15475140 20721 410 0 0 410 0 0 [... eth0: 614530 7085 0 0 0 0 0 1 [... ...] Transmit ...] bytes packets errs drop fifo colls carrier compressed ...] 908188 5596 0 0 0 0 0 0 ...] 1375103 17405 0 0 0 0 0 0 ...] 1703981 5535 0 0 0 3 0 0 In addition, each Channel Bond interface has its own directory. For example, the bond0 device will have a directory called /proc/net/bond0/. It will contain information that is specific to that bond, such as the current slaves of the bond, the link status of the slaves, and how many times the slaves link has failed. 1.4 SCSI info ------------- If you have a SCSI or ATA host adapter in your system, you'll find a subdirectory named after the driver for this adapter in /proc/scsi. You'll also see a list of all recognized SCSI devices in /proc/scsi:: >cat /proc/scsi/scsi Attached devices: Host: scsi0 Channel: 00 Id: 00 Lun: 00 Vendor: IBM Model: DGHS09U Rev: 03E0 Type: Direct-Access ANSI SCSI revision: 03 Host: scsi0 Channel: 00 Id: 06 Lun: 00 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 Type: CD-ROM ANSI SCSI revision: 02 The directory named after the driver has one file for each adapter found in the system. These files contain information about the controller, including the used IRQ and the IO address range. The amount of information shown is dependent on the adapter you use. The example shows the output for an Adaptec AHA-2940 SCSI adapter:: > cat /proc/scsi/aic7xxx/0 Adaptec AIC7xxx driver version: 5.1.19/3.2.4 Compile Options: TCQ Enabled By Default : Disabled AIC7XXX_PROC_STATS : Disabled AIC7XXX_RESET_DELAY : 5 Adapter Configuration: SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter Ultra Wide Controller PCI MMAPed I/O Base: 0xeb001000 Adapter SEEPROM Config: SEEPROM found and used. Adaptec SCSI BIOS: Enabled IRQ: 10 SCBs: Active 0, Max Active 2, Allocated 15, HW 16, Page 255 Interrupts: 160328 BIOS Control Word: 0x18b6 Adapter Control Word: 0x005b Extended Translation: Enabled Disconnect Enable Flags: 0xffff Ultra Enable Flags: 0x0001 Tag Queue Enable Flags: 0x0000 Ordered Queue Tag Flags: 0x0000 Default Tag Queue Depth: 8 Tagged Queue By Device array for aic7xxx host instance 0: {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} Actual queue depth per device for aic7xxx host instance 0: {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} Statistics: (scsi0:0:0:0) Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) Total transfers 160151 (74577 reads and 85574 writes) (scsi0:0:6:0) Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) Total transfers 0 (0 reads and 0 writes) 1.5 Parallel port info in /proc/parport --------------------------------------- The directory /proc/parport contains information about the parallel ports of your system. It has one subdirectory for each port, named after the port number (0,1,2,...). These directories contain the four files shown in Table 1-10. .. table:: Table 1-10: Files in /proc/parport ========= ==================================================================== File Content ========= ==================================================================== autoprobe Any IEEE-1284 device ID information that has been acquired. devices list of the device drivers using that port. A + will appear by the name of the device currently using the port (it might not appear against any). hardware Parallel port's base address, IRQ line and DMA channel. irq IRQ that parport is using for that port. This is in a separate file to allow you to alter it by writing a new value in (IRQ number or none). ========= ==================================================================== 1.6 TTY info in /proc/tty ------------------------- Information about the available and actually used tty's can be found in the directory /proc/tty. You'll find entries for drivers and line disciplines in this directory, as shown in Table 1-11. .. table:: Table 1-11: Files in /proc/tty ============= ============================================== File Content ============= ============================================== drivers list of drivers and their usage ldiscs registered line disciplines driver/serial usage statistic and status of single tty lines ============= ============================================== To see which tty's are currently in use, you can simply look into the file /proc/tty/drivers:: > cat /proc/tty/drivers pty_slave /dev/pts 136 0-255 pty:slave pty_master /dev/ptm 128 0-255 pty:master pty_slave /dev/ttyp 3 0-255 pty:slave pty_master /dev/pty 2 0-255 pty:master serial /dev/cua 5 64-67 serial:callout serial /dev/ttyS 4 64-67 serial /dev/tty0 /dev/tty0 4 0 system:vtmaster /dev/ptmx /dev/ptmx 5 2 system /dev/console /dev/console 5 1 system:console /dev/tty /dev/tty 5 0 system:/dev/tty unknown /dev/tty 4 1-63 console 1.7 Miscellaneous kernel statistics in /proc/stat ------------------------------------------------- Various pieces of information about kernel activity are available in the /proc/stat file. All of the numbers reported in this file are aggregates since the system first booted. For a quick look, simply cat the file:: > cat /proc/stat cpu 237902850 368826709 106375398 1873517540 1135548 0 14507935 0 0 0 cpu0 60045249 91891769 26331539 468411416 495718 0 5739640 0 0 0 cpu1 59746288 91759249 26609887 468860630 312281 0 4384817 0 0 0 cpu2 59489247 92985423 26904446 467808813 171668 0 2268998 0 0 0 cpu3 58622065 92190267 26529524 468436680 155879 0 2114478 0 0 0 intr 8688370575 8 3373 0 0 0 0 0 0 1 40791 0 0 353317 0 0 0 0 224789828 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 190974333 41958554 123983334 43 0 224593 0 0 0 <more 0's deleted> ctxt 22848221062 btime 1605316999 processes 746787147 procs_running 2 procs_blocked 0 softirq 12121874454 100099120 3938138295 127375644 2795979 187870761 0 173808342 3072582055 52608 224184354 The very first "cpu" line aggregates the numbers in all of the other "cpuN" lines. These numbers identify the amount of time the CPU has spent performing different kinds of work. Time units are in USER_HZ (typically hundredths of a second). The meanings of the columns are as follows, from left to right: - user: normal processes executing in user mode - nice: niced processes executing in user mode - system: processes executing in kernel mode - idle: twiddling thumbs - iowait: In a word, iowait stands for waiting for I/O to complete. But there are several problems: 1. CPU will not wait for I/O to complete, iowait is the time that a task is waiting for I/O to complete. When CPU goes into idle state for outstanding task I/O, another task will be scheduled on this CPU. 2. In a multi-core CPU, the task waiting for I/O to complete is not running on any CPU, so the iowait of each CPU is difficult to calculate. 3. The value of iowait field in /proc/stat will decrease in certain conditions. So, the iowait is not reliable by reading from /proc/stat. - irq: servicing interrupts - softirq: servicing softirqs - steal: involuntary wait - guest: running a normal guest - guest_nice: running a niced guest The "intr" line gives counts of interrupts serviced since boot time, for each of the possible system interrupts. The first column is the total of all interrupts serviced including unnumbered architecture specific interrupts; each subsequent column is the total for that particular numbered interrupt. Unnumbered interrupts are not shown, only summed into the total. The "ctxt" line gives the total number of context switches across all CPUs. The "btime" line gives the time at which the system booted, in seconds since the Unix epoch. The "processes" line gives the number of processes and threads created, which includes (but is not limited to) those created by calls to the fork() and clone() system calls. The "procs_running" line gives the total number of threads that are running or ready to run (i.e., the total number of runnable threads). The "procs_blocked" line gives the number of processes currently blocked, waiting for I/O to complete. The "softirq" line gives counts of softirqs serviced since boot time, for each of the possible system softirqs. The first column is the total of all softirqs serviced; each subsequent column is the total for that particular softirq. 1.8 Ext4 file system parameters ------------------------------- Information about mounted ext4 file systems can be found in /proc/fs/ext4. Each mounted filesystem will have a directory in /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or /proc/fs/ext4/sda9 or /proc/fs/ext4/dm-0). The files in each per-device directory are shown in Table 1-12, below. .. table:: Table 1-12: Files in /proc/fs/ext4/<devname> ============== ========================================================== File Content mb_groups details of multiblock allocator buddy cache of free blocks ============== ========================================================== 1.9 /proc/consoles ------------------- Shows registered system console lines. To see which character device lines are currently used for the system console /dev/console, you may simply look into the file /proc/consoles:: > cat /proc/consoles tty0 -WU (ECp) 4:7 ttyS0 -W- (Ep) 4:64 The columns are: +--------------------+-------------------------------------------------------+ \| device \| name of the device \| +====================+=======================================================+ \| operations \| * R = can do read operations \| \| \| * W = can do write operations \| \| \| * U = can do unblank \| +--------------------+-------------------------------------------------------+ \| flags \| * E = it is enabled \| \| \| * C = it is preferred console \| \| \| * B = it is primary boot console \| \| \| * p = it is used for printk buffer \| \| \| * b = it is not a TTY but a Braille device \| \| \| * a = it is safe to use when cpu is offline \| +--------------------+-------------------------------------------------------+ \| major:minor \| major and minor number of the device separated by a \| \| \| colon \| +--------------------+-------------------------------------------------------+ Summary ------- The /proc file system serves information about the running system. It not only allows access to process data but also allows you to request the kernel status by reading files in the hierarchy. The directory structure of /proc reflects the types of information and makes it easy, if not obvious, where to look for specific data. Chapter 2: Modifying System Parameters ====================================== In This Chapter --------------- * Modifying kernel parameters by writing into files found in /proc/sys * Exploring the files which modify certain parameters * Review of the /proc/sys file tree ------------------------------------------------------------------------------ A very interesting part of /proc is the directory /proc/sys. This is not only a source of information, it also allows you to change parameters within the kernel. Be very careful when attempting this. You can optimize your system, but you can also cause it to crash. Never alter kernel parameters on a production system. Set up a development machine and test to make sure that everything works the way you want it to. You may have no alternative but to reboot the machine once an error has been made. To change a value, simply echo the new value into the file. You need to be root to do this. You can create your own boot script to perform this every time your system boots. The files in /proc/sys can be used to fine tune and monitor miscellaneous and general things in the operation of the Linux kernel. Since some of the files can inadvertently disrupt your system, it is advisable to read both documentation and source before actually making adjustments. In any case, be very careful when writing to any of these files. The entries in /proc may change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt review the kernel documentation in the directory linux/Documentation. This chapter is heavily based on the documentation included in the pre 2.2 kernels, and became part of it in version 2.2.1 of the Linux kernel. Please see: Documentation/admin-guide/sysctl/ directory for descriptions of these entries. Summary ------- Certain aspects of kernel behavior can be modified at runtime, without the need to recompile the kernel, or even to reboot the system. The files in the /proc/sys tree can not only be read, but also modified. You can use the echo command to write value into these files, thereby changing the default settings of the kernel. Chapter 3: Per-process Parameters ================================= 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score -------------------------------------------------------------------------------- These files can be used to adjust the badness heuristic used to select which process gets killed in out of memory (oom) conditions. The badness heuristic assigns a value to each candidate task ranging from 0 (never kill) to 1000 (always kill) to determine which process is targeted. The units are roughly a proportion along that range of allowed memory the process may allocate from based on an estimation of its current memory and swap use. For example, if a task is using all allowed memory, its badness score will be 1000. If it is using half of its allowed memory, its score will be 500. The amount of "allowed" memory depends on the context in which the oom killer was called. If it is due to the memory assigned to the allocating task's cpuset being exhausted, the allowed memory represents the set of mems assigned to that cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed memory represents the set of mempolicy nodes. If it is due to a memory limit (or swap limit) being reached, the allowed memory is that configured limit. Finally, if it is due to the entire system being out of memory, the allowed memory represents all allocatable resources. The value of /proc/<pid>/oom_score_adj is added to the badness score before it is used to determine which task to kill. Acceptable values range from -1000 (OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to polarize the preference for oom killing either by always preferring a certain task or completely disabling it. The lowest possible value, -1000, is equivalent to disabling oom killing entirely for that task since it will always report a badness score of 0. Consequently, it is very simple for userspace to define the amount of memory to consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for example, is roughly equivalent to allowing the remainder of tasks sharing the same system, cpuset, mempolicy, or memory controller resources to use at least 50% more memory. A value of -500, on the other hand, would be roughly equivalent to discounting 50% of the task's allowed memory from being considered as scoring against the task. For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also be used to tune the badness score. Its acceptable values range from -16 (OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17 (OOM_DISABLE) to disable oom killing entirely for that task. Its value is scaled linearly with /proc/<pid>/oom_score_adj. The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last value set by a CAP_SYS_RESOURCE process. To reduce the value any lower requires CAP_SYS_RESOURCE. 3.2 /proc/<pid>/oom_score - Display current oom-killer score ------------------------------------------------------------- This file can be used to check the current score used by the oom-killer for any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which process should be killed in an out-of-memory situation. Please note that the exported value includes oom_score_adj so it is effectively in range [0,2000]. 3.3 /proc/<pid>/io - Display the IO accounting fields ------------------------------------------------------- This file contains IO statistics for each running process. Example ~~~~~~~ :: test:/tmp # dd if=/dev/zero of=/tmp/test.dat & [1] 3828 test:/tmp # cat /proc/3828/io rchar: 323934931 wchar: 323929600 syscr: 632687 syscw: 632675 read_bytes: 0 write_bytes: 323932160 cancelled_write_bytes: 0 Description ~~~~~~~~~~~ rchar ^^^^^ I/O counter: chars read The number of bytes which this task has caused to be read from storage. This is simply the sum of bytes which this process passed to read() and pread(). It includes things like tty IO and it is unaffected by whether or not actual physical disk IO was required (the read might have been satisfied from pagecache). wchar ^^^^^ I/O counter: chars written The number of bytes which this task has caused, or shall cause to be written to disk. Similar caveats apply here as with rchar. syscr ^^^^^ I/O counter: read syscalls Attempt to count the number of read I/O operations, i.e. syscalls like read() and pread(). syscw ^^^^^ I/O counter: write syscalls Attempt to count the number of write I/O operations, i.e. syscalls like write() and pwrite(). read_bytes ^^^^^^^^^^ I/O counter: bytes read Attempt to count the number of bytes which this process really did cause to be fetched from the storage layer. Done at the submit_bio() level, so it is accurate for block-backed filesystems. <please add status regarding NFS and CIFS at a later time> write_bytes ^^^^^^^^^^^ I/O counter: bytes written Attempt to count the number of bytes which this process caused to be sent to the storage layer. This is done at page-dirtying time. cancelled_write_bytes ^^^^^^^^^^^^^^^^^^^^^ The big inaccuracy here is truncate. If a process writes 1MB to a file and then deletes the file, it will in fact perform no writeout. But it will have been accounted as having caused 1MB of write. In other words: The number of bytes which this process caused to not happen, by truncating pagecache. A task can cause "negative" IO too. If this task truncates some dirty pagecache, some IO which another task has been accounted for (in its write_bytes) will not be happening. We _could_ just subtract that from the truncating task's write_bytes, but there is information loss in doing that. .. Note:: At its current implementation state, this is a bit racy on 32-bit machines: if process A reads process B's /proc/pid/io while process B is updating one of those 64-bit counters, process A could see an intermediate result. More information about this can be found within the taskstats documentation in Documentation/accounting. 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings --------------------------------------------------------------- When a process is dumped, all anonymous memory is written to a core file as long as the size of the core file isn't limited. But sometimes we don't want to dump some memory segments, for example, huge shared memory or DAX. Conversely, sometimes we want to save file-backed memory segments into a core file, not only the individual files. /proc/<pid>/coredump_filter allows you to customize which memory segments will be dumped when the <pid> process is dumped. coredump_filter is a bitmask of memory types. If a bit of the bitmask is set, memory segments of the corresponding memory type are dumped, otherwise they are not dumped. The following 9 memory types are supported: - (bit 0) anonymous private memory - (bit 1) anonymous shared memory - (bit 2) file-backed private memory - (bit 3) file-backed shared memory - (bit 4) ELF header pages in file-backed private memory areas (it is effective only if the bit 2 is cleared) - (bit 5) hugetlb private memory - (bit 6) hugetlb shared memory - (bit 7) DAX private memory - (bit 8) DAX shared memory Note that MMIO pages such as frame buffer are never dumped and vDSO pages are always dumped regardless of the bitmask status. Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is only affected by bit 5-6, and DAX is only affected by bits 7-8. The default value of coredump_filter is 0x33; this means all anonymous memory segments, ELF header pages and hugetlb private memory are dumped. If you don't want to dump all shared memory segments attached to pid 1234, write 0x31 to the process's proc file:: $ echo 0x31 > /proc/1234/coredump_filter When a new process is created, the process inherits the bitmask status from its parent. It is useful to set up coredump_filter before the program runs. For example:: $ echo 0x7 > /proc/self/coredump_filter $ ./some_program 3.5 /proc/<pid>/mountinfo - Information about mounts -------------------------------------------------------- This file contains lines of the form:: 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue (1)(2)(3) (4) (5) (6) (n…m) (m+1)(m+2) (m+3) (m+4) (1) mount ID: unique identifier of the mount (may be reused after umount) (2) parent ID: ID of parent (or of self for the top of the mount tree) (3) major:minor: value of st_dev for files on filesystem (4) root: root of the mount within the filesystem (5) mount point: mount point relative to the process's root (6) mount options: per mount options (n…m) optional fields: zero or more fields of the form "tag[:value]" (m+1) separator: marks the end of the optional fields (m+2) filesystem type: name of filesystem of the form "type[.subtype]" (m+3) mount source: filesystem specific information or "none" (m+4) super options: per super block options Parsers should ignore all unrecognised optional fields. Currently the possible optional fields are: ================ ============================================================== shared:X mount is shared in peer group X master:X mount is slave to peer group X propagate_from:X mount is slave and receives propagation from peer group X [#]_ unbindable mount is unbindable ================ ============================================================== .. [#] X is the closest dominant peer group under the process's root. If X is the immediate master of the mount, or if there's no dominant peer group under the same root, then only the "master:X" field is present and not the "propagate_from:X" field. For more information on mount propagation see: Documentation/filesystems/sharedsubtree.rst 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm -------------------------------------------------------- These files provide a method to access a task's comm value. It also allows for a task to set its own or one of its thread siblings comm value. The comm value is limited in size compared to the cmdline value, so writing anything longer then the kernel's TASK_COMM_LEN (currently 16 chars, including the NUL terminator) will result in a truncated comm value. 3.7 /proc/<pid>/task/<tid>/children - Information about task children ------------------------------------------------------------------------- This file provides a fast way to retrieve first level children pids of a task pointed by <pid>/<tid> pair. The format is a space separated stream of pids. Note the "first level" here -- if a child has its own children they will not be listed here; one needs to read /proc/<children-pid>/task/<tid>/children to obtain the descendants. Since this interface is intended to be fast and cheap it doesn't guarantee to provide precise results and some children might be skipped, especially if they've exited right after we printed their pids, so one needs to either stop or freeze processes being inspected if precise results are needed. 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file --------------------------------------------------------------- This file provides information associated with an opened file. The regular files have at least four fields -- 'pos', 'flags', 'mnt_id' and 'ino'. The 'pos' represents the current offset of the opened file in decimal form [see lseek(2) for details], 'flags' denotes the octal O_xxx mask the file has been created with [see open(2) for details] and 'mnt_id' represents mount ID of the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo for details]. 'ino' represents the inode number of the file. A typical output is:: pos: 0 flags: 0100002 mnt_id: 19 ino: 63107 All locks associated with a file descriptor are shown in its fdinfo too:: lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags pair provide additional information particular to the objects they represent. Eventfd files ~~~~~~~~~~~~~ :: pos: 0 flags: 04002 mnt_id: 9 ino: 63107 eventfd-count: 5a where 'eventfd-count' is hex value of a counter. Signalfd files ~~~~~~~~~~~~~~ :: pos: 0 flags: 04002 mnt_id: 9 ino: 63107 sigmask: 0000000000000200 where 'sigmask' is hex value of the signal mask associated with a file. Epoll files ~~~~~~~~~~~ :: pos: 0 flags: 02 mnt_id: 9 ino: 63107 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 where 'tfd' is a target file descriptor number in decimal form, 'events' is events mask being watched and the 'data' is data associated with a target [see epoll(7) for more details]. The 'pos' is current offset of the target file in decimal form [see lseek(2)], 'ino' and 'sdev' are inode and device numbers where target file resides, all in hex format. Fsnotify files ~~~~~~~~~~~~~~ For inotify files the format is the following:: pos: 0 flags: 02000000 mnt_id: 9 ino: 63107 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d where 'wd' is a watch descriptor in decimal form, i.e. a target file descriptor number, 'ino' and 'sdev' are inode and device where the target file resides and the 'mask' is the mask of events, all in hex form [see inotify(7) for more details]. If the kernel was built with exportfs support, the path to the target file is encoded as a file handle. The file handle is provided by three fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex format. If the kernel is built without exportfs support the file handle won't be printed out. If there is no inotify mark attached yet the 'inotify' line will be omitted. For fanotify files the format is:: pos: 0 flags: 02 mnt_id: 9 ino: 63107 fanotify flags:10 event-flags:0 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4 where fanotify 'flags' and 'event-flags' are values used in fanotify_init call, 'mnt_id' is the mount point identifier, 'mflags' is the value of flags associated with mark which are tracked separately from events mask. 'ino' and 'sdev' are target inode and device, 'mask' is the events mask and 'ignored_mask' is the mask of events which are to be ignored. All are in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask' provide information about flags and mask used in fanotify_mark call [see fsnotify manpage for details]. While the first three lines are mandatory and always printed, the rest is optional and may be omitted if no marks created yet. Timerfd files ~~~~~~~~~~~~~ :: pos: 0 flags: 02 mnt_id: 9 ino: 63107 clockid: 0 ticks: 0 settime flags: 01 it_value: (0, 49406829) it_interval: (1, 0) where 'clockid' is the clock type and 'ticks' is the number of the timer expirations that have occurred [see timerfd_create(2) for details]. 'settime flags' are flags in octal form been used to setup the timer [see timerfd_settime(2) for details]. 'it_value' is remaining time until the timer expiration. 'it_interval' is the interval for the timer. Note the timer might be set up with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' still exhibits timer's remaining time. DMA Buffer files ~~~~~~~~~~~~~~~~ :: pos: 0 flags: 04002 mnt_id: 9 ino: 63107 size: 32768 count: 2 exp_name: system-heap where 'size' is the size of the DMA buffer in bytes. 'count' is the file count of the DMA buffer file. 'exp_name' is the name of the DMA buffer exporter. VFIO Device files ~~~~~~~~~~~~~~~~~ :: pos: 0 flags: 02000002 mnt_id: 17 ino: 5122 vfio-device-syspath: /sys/devices/pci0000:e0/0000:e0:01.1/0000:e1:00.0/0000:e2:05.0/0000:e8:00.0 where 'vfio-device-syspath' is the sysfs path corresponding to the VFIO device file. 3.9 /proc/<pid>/map_files - Information about memory mapped files --------------------------------------------------------------------- This directory contains symbolic links which represent memory mapped files the process is maintaining. Example output:: \| lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so \| lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so \| lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so \| ... \| lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1 \| lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls The name of a link represents the virtual memory bounds of a mapping, i.e. vm_area_struct::vm_start-vm_area_struct::vm_end. The main purpose of the map_files is to retrieve a set of memory mapped files in a fast way instead of parsing /proc/<pid>/maps or /proc/<pid>/smaps, both of which contain many more records. At the same time one can open(2) mappings from the listings of two processes and comparing their inode numbers to figure out which anonymous memory areas are actually shared. 3.10 /proc/<pid>/timerslack_ns - Task timerslack value --------------------------------------------------------- This file provides the value of the task's timerslack value in nanoseconds. This value specifies an amount of time that normal timers may be deferred in order to coalesce timers and avoid unnecessary wakeups. This allows a task's interactivity vs power consumption tradeoff to be adjusted. Writing 0 to the file will set the task's timerslack to the default value. Valid values are from 0 - ULLONG_MAX An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level permissions on the task specified to change its timerslack_ns value. 3.11 /proc/<pid>/patch_state - Livepatch patch operation state ----------------------------------------------------------------- When CONFIG_LIVEPATCH is enabled, this file displays the value of the patch state for the task. A value of '-1' indicates that no patch is in transition. A value of '0' indicates that a patch is in transition and the task is unpatched. If the patch is being enabled, then the task hasn't been patched yet. If the patch is being disabled, then the task has already been unpatched. A value of '1' indicates that a patch is in transition and the task is patched. If the patch is being enabled, then the task has already been patched. If the patch is being disabled, then the task hasn't been unpatched yet. 3.12 /proc/<pid>/arch_status - task architecture specific status ------------------------------------------------------------------- When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the architecture specific status of the task. Example ~~~~~~~ :: $ cat /proc/6753/arch_status AVX512_elapsed_ms: 8 Description ~~~~~~~~~~~ x86 specific entries ~~~~~~~~~~~~~~~~~~~~~ AVX512_elapsed_ms ^^^^^^^^^^^^^^^^^^ If AVX512 is supported on the machine, this entry shows the milliseconds elapsed since the last time AVX512 usage was recorded. The recording happens on a best effort basis when a task is scheduled out. This means that the value depends on two factors: 1) The time which the task spent on the CPU without being scheduled out. With CPU isolation and a single runnable task this can take several seconds. 2) The time since the task was scheduled out last. Depending on the reason for being scheduled out (time slice exhausted, syscall ...) this can be arbitrary long time. As a consequence the value cannot be considered precise and authoritative information. The application which uses this information has to be aware of the overall scenario on the system in order to determine whether a task is a real AVX512 user or not. Precise information can be obtained with performance counters. A special value of '-1' indicates that no AVX512 usage was recorded, thus the task is unlikely an AVX512 user, but depends on the workload and the scheduling scenario, it also could be a false negative mentioned above. 3.13 /proc/<pid>/fd - List of symlinks to open files ------------------------------------------------------- This directory contains symbolic links which represent open files the process is maintaining. Example output:: lr-x------ 1 root root 64 Sep 20 17:53 0 -> /dev/null l-wx------ 1 root root 64 Sep 20 17:53 1 -> /dev/null lrwx------ 1 root root 64 Sep 20 17:53 10 -> 'socket:[12539]' lrwx------ 1 root root 64 Sep 20 17:53 11 -> 'socket:[12540]' lrwx------ 1 root root 64 Sep 20 17:53 12 -> 'socket:[12542]' The number of open files for the process is stored in 'size' member of stat() output for /proc/<pid>/fd for fast access. ------------------------------------------------------- 3.14 /proc/<pid>/ksm_stat - Information about the process's ksm status ---------------------------------------------------------------------- When CONFIG_KSM is enabled, each process has this file which displays the information of ksm merging status. Example ~~~~~~~ :: / # cat /proc/self/ksm_stat ksm_rmap_items 0 ksm_zero_pages 0 ksm_merging_pages 0 ksm_process_profit 0 ksm_merge_any: no ksm_mergeable: no Description ~~~~~~~~~~~ ksm_rmap_items ^^^^^^^^^^^^^^ The number of ksm_rmap_item structures in use. The structure ksm_rmap_item stores the reverse mapping information for virtual addresses. KSM will generate a ksm_rmap_item for each ksm-scanned page of the process. ksm_zero_pages ^^^^^^^^^^^^^^ When /sys/kernel/mm/ksm/use_zero_pages is enabled, it represent how many empty pages are merged with kernel zero pages by KSM. ksm_merging_pages ^^^^^^^^^^^^^^^^^ It represents how many pages of this process are involved in KSM merging (not including ksm_zero_pages). It is the same with what /proc/<pid>/ksm_merging_pages shows. ksm_process_profit ^^^^^^^^^^^^^^^^^^ The profit that KSM brings (Saved bytes). KSM can save memory by merging identical pages, but also can consume additional memory, because it needs to generate a number of rmap_items to save each scanned page's brief rmap information. Some of these pages may be merged, but some may not be abled to be merged after being checked several times, which are unprofitable memory consumed. ksm_merge_any ^^^^^^^^^^^^^ It specifies whether the process's 'mm is added by prctl() into the candidate list of KSM or not, and if KSM scanning is fully enabled at process level. ksm_mergeable ^^^^^^^^^^^^^ It specifies whether any VMAs of the process''s mms are currently applicable to KSM. More information about KSM can be found in Documentation/admin-guide/mm/ksm.rst. Chapter 4: Configuring procfs ============================= 4.1 Mount options --------------------- The following mount options are supported: ========= ======================================================== hidepid= Set /proc/<pid>/ access mode. gid= Set the group authorized to learn processes information. subset= Show only the specified subset of procfs. pidns= Specify a the namespace used by this procfs. ========= ======================================================== hidepid=off or hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories (default). hidepid=noaccess or hidepid=1 means users may not access any /proc/<pid>/ directories but their own. Sensitive files like cmdline, sched*, status are now protected against other users. This makes it impossible to learn whether any user runs specific program (given the program doesn't reveal itself by its behaviour). As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users, poorly written programs passing sensitive information via program arguments are now protected against local eavesdroppers. hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other users. It doesn't mean that it hides a fact whether a process with a specific pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"), but it hides process's uid and gid, which may be learned by stat()'ing /proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering information about running processes, whether some daemon runs with elevated privileges, whether other user runs some sensitive program, whether other users run any program at all, etc. hidepid=ptraceable or hidepid=4 means that procfs should only contain /proc/<pid>/ directories that the caller can ptrace. gid= defines a group authorized to learn processes information otherwise prohibited by hidepid=. If you use some daemon like identd which needs to learn information about processes information, just add identd to this group. subset=pid hides all top level files and directories in the procfs that are not related to tasks. pidns= specifies a pid namespace (either as a string path to something like `/proc/$pid/ns/pid`, or a file descriptor when using `FSCONFIG_SET_FD`) that will be used by the procfs instance when translating pids. By default, procfs will use the calling process's active pid namespace. Note that the pid namespace of an existing procfs instance cannot be modified (attempting to do so will give an `-EBUSY` error). Chapter 5: Filesystem behavior ============================== Originally, before the advent of pid namespace, procfs was a global file system. It means that there was only one procfs instance in the system. When pid namespace was added, a separate procfs instance was mounted in each pid namespace. So, procfs mount options are global among all mountpoints within the same namespace:: # grep ^proc /proc/mounts proc /proc proc rw,relatime,hidepid=2 0 0 # strace -e mount mount -o hidepid=1 -t proc proc /tmp/proc mount("proc", "/tmp/proc", "proc", 0, "hidepid=1") = 0 +++ exited with 0 +++ # grep ^proc /proc/mounts proc /proc proc rw,relatime,hidepid=2 0 0 proc /tmp/proc proc rw,relatime,hidepid=2 0 0 and only after remounting procfs mount options will change at all mountpoints:: # mount -o remount,hidepid=1 -t proc proc /tmp/proc # grep ^proc /proc/mounts proc /proc proc rw,relatime,hidepid=1 0 0 proc /tmp/proc proc rw,relatime,hidepid=1 0 0 This behavior is different from the behavior of other filesystems. The new procfs behavior is more like other filesystems. Each procfs mount creates a new procfs instance. Mount options affect own procfs instance. It means that it became possible to have several procfs instances displaying tasks with different filtering options in one pid namespace:: # mount -o hidepid=invisible -t proc proc /proc # mount -o hidepid=noaccess -t proc proc /tmp/proc # grep ^proc /proc/mounts proc /proc proc rw,relatime,hidepid=invisible 0 0 proc /tmp/proc proc rw,relatime,hidepid=noaccess 0 0 ]
54/4	2026/05/23 11:37	llm	codeexpert	0m Model: gemini-3-flash-preview Tokens: input: 64945 output: 464 thoughts: 1576 Thoughts: Analysis of `/proc/timer_list` Accessibility Okay, let's break this down systematically. The documentation mentions `timer_list` as residing within `/proc`, though it's strangely absent from the expected table. I can confirm its existence, however. I recall that the `/proc/sys` entries require root privileges, and there are specific access rules for `/proc/<pid>/`. For top-level files like `/proc/timer_list`, we're dealing with standard VFS permissions. Given `timer_list`'s `0400` permissions and ownership by global root, the restriction to global root seems straightforward. So, my initial inclination is "No," it's not readable. To be absolutely certain, I considered edge cases: * User Namespace and Root: If an unprivileged user created a namespace as root, they could map UID 0, but the scenario specifies an unprivileged user. * `sudo`: Using `sudo` grants privilege, violating the unprivileged constraint. * `unshare -r`: With `unshare -r`, the current UID is mapped to 0 inside the new namespace. If the current UID is 1000, then inside the namespace, UID 0 is global UID 1000. The file `/proc/timer_list` is owned by global UID 0. Global UID 0 is NOT mapped in the namespace. So the user (global 1000) is NOT the owner of the file (global 0). I double-checked `proc_create_seq_private` to ensure it uses the parent's UID, which defaults to `proc_root` (UID 0), and I confirmed `proc_root.uid` is never modified. The `proc_set_user` function, in `__proc_create`, uses `(parent)->uid` if `parent` is `proc_root`. I needed to make sure that the `proc_root` isn't per-namespace. I searched for it, and confirmed that it is a global variable. `proc_net` is special; however, `timer_list` is a global file, not within the `net` subdirectory. The crucial point is that capabilities like `CAP_DAC_OVERRIDE` and `CAP_DAC_READ_SEARCH` in a user namespace only apply to files where the owner UID is mapped within that namespace. Global UID 0, being unmapped, means these capabilities are ineffective. I went back to the source code for the `timer_list` proc entry creation. There's no conditional mode setting. `proc_create_seq_private` is a function, not a macro, so no tricks there. I also checked if creating the namespace with `CLONE_NEWUSER` but NOT `CLONE_NEWPID` would change things. No, since it's the same mount, the permissions are the same. A new PID namespace and a new `proc` mount use the same PDE tree and inodes inherit the same UID/GID. Finally, does `kptr_restrict` matter? No, because the permission check happens before attempting to read the content. The commit `8e7df2b5b7f2` specifically sets the mode to `0400` to restrict access. Conclusion:* * `/proc/timer_list`'s mode is explicitly `0400`. * It's owned by global root (UID 0). * Standard VFS permission logic applies to `/proc` files. * An unprivileged user in a user namespace does not have global UID 0. * Even with namespace capabilities, global UID 0 is unmapped. * Thus, an unprivileged user cannot read `/proc/timer_list`. My answer remains: "No."
55/2	2026/05/23 11:37	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 14520 output: 66 thoughts: 484 Thoughts: My Assessment of the Timer List Vulnerability Alright, let's break this down. First, the crucial aspect is that this isn't exploitable by unprivileged processes or within user namespaces. That's good. Now, onto the core issue: the data race. It's a read and write conflict on an 8-byte value – specifically, the `cpu_base->expires_next` field. The read is part of printing to a `seq_file`, and the write updates the same field. From a security perspective, this looks benign. It's highly unlikely to cause memory corruption, a denial-of-service condition, or any other security concern. So, Exploitable is false, DenialOfService is false. Unprivileged and UserNamespace are also false. No VMGuestTrigger, VMHostTrigger, NetworkTrigger, RemoteTrigger, PeripheralTrigger, or FilesystemTrigger either. I need to confirm all the entry points to `timer_list_show`, just in case. It's called from `sysrq_timer_list_show`, which is itself triggered by `sysrq_handle_show_timers`. SysRq access is limited to either a physical keyboard or `/proc/sysrq-trigger`, which is root-only. So, definitely not unprivileged. I also need to make sure that `print_cpu` can only be called from `timer_list_show`. This confirms that access is limited to root-only. Let's revisit the data race itself. Could concurrently reading `cpu_base->expires_next` during a write cause a crash? No, it's an 8-byte read on a 64-bit architecture. On most architectures, it is atomic, but even if it's torn, the result is merely a garbage value being printed. The KCSAN report confirms this: the value changes from one read to the next, which is exactly what we expect from a data race on a primitive type like this. Okay, I've got a clear picture of what's going on here. Time to fill out the results.
56/2	2026/05/23 11:37	tool	set-results	0m Args: map[DenialOfService:false Exploitable:false FilesystemTrigger:false NetworkTrigger:false PeripheralTrigger:false RemoteTrigger:false Unprivileged:false UserNamespace:false VMGuestTrigger:false VMHostTrigger:false] Results: map[DenialOfService:false Exploitable:false FilesystemTrigger:false NetworkTrigger:false PeripheralTrigger:false RemoteTrigger:false Unprivileged:false UserNamespace:false VMGuestTrigger:false VMHostTrigger:false]
57/2	2026/05/23 11:37	llm	expert	0m Model: gemini-3.1-pro-preview Tokens: input: 15578 output: 383 thoughts: 179 Thoughts: Analyzing a Benign KCSAN Data-Race Report Okay, so I've got this KCSAN data-race report to look at. The core of it seems to be between the `hrtimer_interrupt` function, which is writing to `cpu_base->expires_next`, and `print_cpu`, which is reading it. `print_cpu` gets called when we look at `/proc/timer_list` or when SysRq-Q is triggered. The crucial thing here is that `/proc/timer_list` is created with mode 0400, meaning it's only readable by root. That immediately limits the scope; unprivileged users and user namespaces can't even get to this data. Given that restriction, this data race is basically harmless. `print_cpu` is just reading the value to then print it to a sequential file. Even if it gets a torn read or some intermediate value, the worst that happens is a bit of garbage gets printed. It's not exploitable, there's no way this turns into a denial-of-service, and it has no security ramifications. I'll document my analysis to be thorough and state this clearly.
58/1	2026/05/23 11:37	action	format-explanation	0m Results: map[Explanation:The reported bug is a KCSAN data-race between a write to `cpu_base->expires_next` in `hrtimer_interrupt` and a read of the same variable in `print_cpu`. Analysis: 1. Trigger mechanism: The read occurs in `print_cpu`, which is invoked by `timer_list_show`. This function is executed when reading the `/proc/timer_list` file or when triggering the SysRq-Q command. 2. Privilege level: The `/proc/timer_list` file is created with `0400` permissions (`proc_create_seq_private("timer_list", 0400, ...)`), meaning it is only readable by the global root user. Unprivileged users cannot read it. Furthermore, it is not accessible from within an unprivileged user namespace because the file is owned by the global root (UID 0), which is not mapped into the user namespace, preventing `CAP_DAC_OVERRIDE` from bypassing the permission check. SysRq triggers also require root privileges (writing to `/proc/sysrq-trigger`) or physical access. 3. Impact: The data race is completely benign. `print_cpu` reads the 8-byte `expires_next` value locklessly simply to print it for diagnostic purposes. If a concurrent write occurs, the read might fetch an intermediate or torn value, which would merely result in a garbage timestamp being printed to the seq_file. This cannot cause memory corruption, control-flow hijacking, kernel crashes, or any form of denial-of-service. Conclusion: This is a benign diagnostic data race restricted to the root user. It has no security impact, is not exploitable, and cannot be triggered by unprivileged users, network traffic, or other external vectors.]

map[DenialOfService:false Explanation:The reported bug is a KCSAN data-race between a write to
`cpu_base->expires_next` in `hrtimer_interrupt` and a read of the same variable
in `print_cpu`.

**Analysis:**
1. **Trigger mechanism:** The read occurs in `print_cpu`, which is invoked by
`timer_list_show`. This function is executed when reading the `/proc/timer_list`
file or when triggering the SysRq-Q command.
2. **Privilege level:** The `/proc/timer_list` file is created with `0400`
permissions (`proc_create_seq_private("timer_list", 0400, ...)`), meaning it is
only readable by the global root user. Unprivileged users cannot read it.
Furthermore, it is not accessible from within an unprivileged user namespace
because the file is owned by the global root (UID 0), which is not mapped into
the user namespace, preventing `CAP_DAC_OVERRIDE` from bypassing the permission
check. SysRq triggers also require root privileges (writing to
`/proc/sysrq-trigger`) or physical access.
3. **Impact:** The data race is completely benign. `print_cpu` reads the 8-byte
`expires_next` value locklessly simply to print it for diagnostic purposes. If a
concurrent write occurs, the read might fetch an intermediate or torn value,
which would merely result in a garbage timestamp being printed to the seq_file.
This cannot cause memory corruption, control-flow hijacking, kernel crashes, or
any form of denial-of-service.

**Conclusion:**
This is a benign diagnostic data race restricted to the root user. It has no
security impact, is not exploitable, and cannot be triggered by unprivileged
users, network traffic, or other external vectors. Exploitable:false FilesystemTrigger:false NetworkTrigger:false PeripheralTrigger:false RemoteTrigger:false Unprivileged:false UserNamespace:false VMGuestTrigger:false VMHostTrigger:false]

map[SimplifiedCRepro:]

map[KernelSrc:/app/workdir/cache/src/fdb7cb6bb7b27f7e6d7ef669765813dd83c15406]

map[KernelObj:/app/workdir/cache/build/8c4827c6c7734fe87e2fc497164821fb44622630]

map[Index:codesearch-index]

gemini-3.1-pro-preview

map[DenialOfService:false Exploitable:false FilesystemTrigger:false NetworkTrigger:false PeripheralTrigger:false RemoteTrigger:false Unprivileged:false UserNamespace:false VMGuestTrigger:false VMHostTrigger:false]

You are an experienced Linux kernel security engineer. Your task is to analyze given kernel bug report
and determine its security impact based on the following dimensions.

Use the provided tools to examine the source code, check for capability checks (e.g., capable(), ns_capable()),
and understand the nature of the bug. Analyze the given kernel build and configuration.
You can check the kernel config by grepping ".config" file; you can check kernel cmdline by greeping
".config" file for "CONFIG_CMDLINE=". Assume sysctl parameters have default values.
But analyze for the corresponding production build w/o debugging tools enabled (like KASAN, KMSAN, UBSAN).

Try different strategies when analyzing the bug:
- think of ways in which the vulnerable code is unreachable
- or the other way around: try to come up with different ideas of how an unprivileged user can reach the bug
If still unsure err on the side of the bug being non-exploitable/not-accessible.
In the final reply, provide a reasoning for your assessment.

Analysis dimensions:

* Exploitable:
Determine if the bug can result in memory corruption or elevated privileges.
Memory safety issues are almost always exploitable (KASAN or UBSAN reports for use-after-free, out-of-bounds;
refcounting issues, corrupted lists, etc). When kernel is crashing on a completly wild pointer access
(e.g. user-space address, or non-canonical address, but not on NULL or address corresponding to KASAN shadow
for NULL address), including both data accesses and control tranfers, that's also usually implies possibility
of exploitation. Such reports usually say "unable to handle kernel paging request".
Uses of uninitialized values detected by KMSAN may be exploitable b/c attacker frequently can affect uninit
values with spraying techniques. However, for these exploitabability depends on how exactly the uninit value
is used in the code, and what it affects.

Think of what happens after the bug is triggered. Some bugs cause kernel panic and halt execution,
they are harder to exploit. For example, BUG reports halts the kernel. However, WARNING reports don't halt
execution in production builds. Debug bug detection tools (like KASAN, KMSAN, KCSAN, UBSAN) are also not enabled
in production builds, so attacker can freely exploit these bugs w/o being detected by these tools.
If you see an integer overflow, think how the overflowed value used later (if it's used as allocation size,
or an array index). If you see an out-of-bounds read, think if it's followed by an out-of-bounds write as well.
Some KCSAN data-races may be exploitable by skilled attackers as well. Think what data structures got corrupted
as the result of data races and how. However, note that kernel has lots of "benign" data races that don't lead
to any runtime misbehavior at all.

* Denial Of Service:
Determine if the bug can result in denial-of-service. Most bugs can, since they cause system crash,
hangs, deadlocks, or resource leaks. This is mostly applicable to WARNING bugs that won't cause system crash
in production. For these think what will be consequences of the violation of the kernel assumptions flagged
by the WARNING. In some cases the unexpected condition is also properly handled by the normal control flow
(e.g. with "if (WARN_ON(...))"), these won't cause denial-of-service. If the condition is not handled,
then it may or may not cause denial-of-service.

* Accessible From Unprivileged Processes:
Determine if the bug can be reached from a typical (non-root) user process that does NOT have any special capabilities
(like CAP_SYS_ADMIN, CAP_NET_ADMIN, CAP_NET_RAW, CAP_PERFMON) or access to device nodes restricted to root.
Assume that unprivileged_bpf_disabled=1, that is eBPF loading is not accessible. However, cBPF (classical BPF)
is still accessible to non-root processes.
Assume that user namespaces are not accessible, that is, the process cannot get the mentioned capabilities even
within a new user namespace (checked by ns_capable() function in the kernel sources).

* Accessible From User Namespaces:
Determine if the bug can be reached within a user-namespace where the process has all capabilities
(including CAP_SYS_ADMIN, CAP_NET_ADMIN, CAP_NET_RAW, CAP_PERFMON). Such capabilities are checked with ns_capable()
function in the kernel sources.

* VM Guest Trigger:
Determine if the bug can be triggered from the context of a typical KVM guest (e.g., set up by a QEMU VMM).
Consider accesses to standard Linux host paravirtualized features (virtio-blk, virtio-net, etc.),
and handling of VM exits in the KVM code.

* VM Host Trigger in The Confidetial Computing Context:
Determine if the bug can be triggered in a confidential computing guest kernel from the context of a KVM host.
Consider access to standard Linux guest paravirtualized features (virtio-blk, virtio-net, etc.).

* Ethernet Network Trigger:
Determine if the bug can be triggered by processing ingress network Ethernet traffic, either directly (network stack)
or via drivers exposed to network data.

* Other Remote Trigger:
Determine if the bug can be triggered by processing remote traffic other than Ethernet (Wifi, Bluetooth, NFC, etc).

* Peripheral Trigger:
Determine if the bug can be triggered via an untrusted peripheral device that can be physically plugged
into a system, such as a USB device or a niche hardware driver handling external hardware inputs.
This is particularly important for mobile and desktop environments where users can plug in unknown devices.

* Malicious Filesystem Trigger:
Determine if the bug can be triggered by the kernel mounting and parsing a malicious filesystem image.
This is highly critical for Desktop and Mobile environments where external media or downloaded images
might be auto-mounted.

Don't make assumptions about the kernel source code (it may be different from what you assume it is).
Extensively use the provided code access tools (codesearch-*, git-*, grepper, etc)
to examine the actual source code, and confirm any assumptions.

Prefer calling several tools at the same time to save round-trips.

Use set-results tool to provide results of the analysis.
It must be called exactly once before the final reply.
Ignore results of this tool.

The kernel bug report is:

==================================================================
BUG: KCSAN: data-race in hrtimer_interrupt / print_cpu

write to 0xffff888237c1b8e8 of 8 bytes by interrupt on cpu 0:
 hrtimer_interrupt+0x1ea/0x850 kernel/time/hrtimer.c:2105
 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1050 [inline]
 __sysvec_apic_timer_interrupt+0x5f/0x1c0 arch/x86/kernel/apic/apic.c:1067
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1061 [inline]
 sysvec_apic_timer_interrupt+0x6f/0x80 arch/x86/kernel/apic/apic.c:1061
 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:697
 kcsan_setup_watchpoint+0x404/0x410 kernel/kcsan/core.c:705
 tlb_flush_pte_range include/asm-generic/tlb.h:622 [inline]
 tlb_remove_tlb_entries include/asm-generic/tlb.h:675 [inline]
 zap_present_folio_ptes mm/memory.c:1650 [inline]
 zap_present_ptes mm/memory.c:1714 [inline]
 do_zap_pte_range mm/memory.c:1816 [inline]
 zap_pte_range mm/memory.c:1918 [inline]
 zap_pmd_range mm/memory.c:2004 [inline]
 zap_pud_range mm/memory.c:2032 [inline]
 zap_p4d_range mm/memory.c:2053 [inline]
 __zap_vma_range+0x1404/0x2c10 mm/memory.c:2093
 unmap_vmas+0x22a/0x340 mm/memory.c:2162
 exit_mmap+0x1ab/0x5f0 mm/mmap.c:1300
 __mmput+0x28/0x1c0 kernel/fork.c:1178
 mmput+0x40/0x50 kernel/fork.c:1201
 exit_mm+0x113/0x1a0 kernel/exit.c:581
 do_exit+0x442/0x1530 kernel/exit.c:963
 __do_sys_exit kernel/exit.c:1085 [inline]
 __se_sys_exit kernel/exit.c:1083 [inline]
 __x64_sys_exit+0x1f/0x20 kernel/exit.c:1083
 x64_sys_call+0x301d/0x3020 arch/x86/include/generated/asm/syscalls_64.h:61
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x12c/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

read to 0xffff888237c1b8e8 of 8 bytes by task 24599 on cpu 1:
 print_cpu+0x2fb/0x670 kernel/time/timer_list.c:129
 timer_list_show+0x107/0x170 kernel/time/timer_list.c:291
 seq_read_iter+0x636/0x940 fs/seq_file.c:273
 proc_reg_read_iter+0x110/0x180 fs/proc/inode.c:299
 copy_splice_read+0x471/0x6c0 fs/splice.c:362
 do_splice_read fs/splice.c:980 [inline]
 splice_direct_to_actor+0x26e/0x670 fs/splice.c:1084
 do_splice_direct_actor fs/splice.c:1202 [inline]
 do_splice_direct+0x119/0x1a0 fs/splice.c:1228
 do_sendfile+0x382/0x650 fs/read_write.c:1372
 __do_sys_sendfile64 fs/read_write.c:1433 [inline]
 __se_sys_sendfile64 fs/read_write.c:1419 [inline]
 __x64_sys_sendfile64+0x105/0x150 fs/read_write.c:1419
 x64_sys_call+0x2dc4/0x3020 arch/x86/include/generated/asm/syscalls_64.h:41
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x12c/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

value changed: 0x000000cde75a636b -> 0x000000cde75e1b80

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 UID: 0 PID: 24599 Comm: syz.4.4498 Tainted: G        W           syzkaller #0 PREEMPT(full) 
Tainted: [W]=WARN
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/18/2026
==================================================================

The reported bug is a KCSAN data-race between a write to `cpu_base->expires_next` in `hrtimer_interrupt` and a read of the same variable in `print_cpu`.

**Analysis:**
1. **Trigger mechanism:** The read occurs in `print_cpu`, which is invoked by `timer_list_show`. This function is executed when reading the `/proc/timer_list` file or when triggering the SysRq-Q command. 
2. **Privilege level:** The `/proc/timer_list` file is created with `0400` permissions (`proc_create_seq_private("timer_list", 0400, ...)`), meaning it is only readable by the global root user. Unprivileged users cannot read it. Furthermore, it is not accessible from within an unprivileged user namespace because the file is owned by the global root (UID 0), which is not mapped into the user namespace, preventing `CAP_DAC_OVERRIDE` from bypassing the permission check. SysRq triggers also require root privileges (writing to `/proc/sysrq-trigger`) or physical access.
3. **Impact:** The data race is completely benign. `print_cpu` reads the 8-byte `expires_next` value locklessly simply to print it for diagnostic purposes. If a concurrent write occurs, the read might fetch an intermediate or torn value, which would merely result in a garbage timestamp being printed to the seq_file. This cannot cause memory corruption, control-flow hijacking, kernel crashes, or any form of denial-of-service.

**Conclusion:**
This is a benign diagnostic data race restricted to the root user. It has no security impact, is not exploitable, and cannot be triggered by unprivileged users, network traffic, or other external vectors.

gemini-3.1-pro-preview

							input: 6939
							output: 82
							thoughts: 141

**Analyzing a KCSAN Data-Race Report**

Okay, so I've got a KCSAN data-race report here. Looks like there's a race condition. The report indicates a conflict between a write and a read operation. Specifically, `hrtimer_interrupt` is writing 8 bytes, and `print_cpu` is reading those same 8 bytes. Interesting. The write operation originates from `kernel/time/hrtimer.c:2105`, occurring within the `hrtimer_interrupt` function. The read is at `kernel/time/timer_list.c:129`, and it's happening inside the `print_cpu` function.

Now, let's break this down. The read is triggered by accessing `/proc/timer_list` through `timer_list_show`, which is as expected. Reading `/proc/timer_list` is a common way to inspect the state of kernel timers. The write, however, is triggered by a timer interrupt, specifically `hrtimer_interrupt`.

Time to dive into the source code for these two locations and understand the data structures involved, and the potential for concurrent access. I need to figure out what data is being written and read, how the memory is shared, and if there's any synchronization (or lack thereof) that's causing this. This is a classic concurrency problem, I'll bet it's something simple that was overlooked, so lets get to it.

map[ContextFile:kernel/time/hrtimer.c IncludeLines:true Name:hrtimer_interrupt]

map[SourceCode:2079:	/*
2080:	 * High resolution timer interrupt
2081:	 * Called with interrupts disabled
2082:	 */
2083:	void hrtimer_interrupt(struct clock_event_device *dev)
2084:	{
2085:		struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
2086:		ktime_t expires_next, now, entry_time, delta;
2087:		unsigned long flags;
2088:		int retries = 0;
2089:	
2090:		BUG_ON(!cpu_base->hres_active);
2091:		cpu_base->nr_events++;
2092:		dev->next_event = KTIME_MAX;
2093:		dev->next_event_forced = 0;
2094:	
2095:		raw_spin_lock_irqsave(&cpu_base->lock, flags);
2096:		entry_time = now = hrtimer_update_base(cpu_base);
2097:	retry:
2098:		cpu_base->deferred_rearm = true;
2099:		/*
2100:		 * Set expires_next to KTIME_MAX, which prevents that remote CPUs queue
2101:		 * timers while __hrtimer_run_queues() is expiring the clock bases.
2102:		 * Timers which are re/enqueued on the local CPU are not affected by
2103:		 * this.
2104:		 */
2105:		cpu_base->expires_next = KTIME_MAX;
2106:	
2107:		if (!ktime_before(now, cpu_base->softirq_expires_next)) {
2108:			cpu_base->softirq_expires_next = KTIME_MAX;
2109:			cpu_base->softirq_activated = true;
2110:			raise_timer_softirq(HRTIMER_SOFTIRQ);
2111:		}
2112:	
2113:		__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
2114:	
2115:		/*
2116:		 * The next timer was already expired due to:
2117:		 * - tracing
2118:		 * - long lasting callbacks
2119:		 * - being scheduled away when running in a VM
2120:		 *
2121:		 * We need to prevent that we loop forever in the hrtiner interrupt
2122:		 * routine. We give it 3 attempts to avoid overreacting on some
2123:		 * spurious event.
2124:		 */
2125:		now = hrtimer_update_base(cpu_base);
2126:		expires_next = hrtimer_update_next_event(cpu_base);
2127:		cpu_base->hang_detected = false;
2128:		if (expires_next < now) {
2129:			if (++retries < 3)
2130:				goto retry;
2131:	
2132:			delta = ktime_sub(now, entry_time);
2133:			cpu_base->max_hang_time = max_t(unsigned int, cpu_base->max_hang_time, delta);
2134:			cpu_base->nr_hangs++;
2135:			cpu_base->hang_detected = true;
2136:		}
2137:	
2138:		hrtimer_interrupt_rearm(cpu_base, expires_next);
2139:		raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
2140:	}
 SourceFile:kernel/time/hrtimer.c]

map[ContextFile:kernel/time/timer_list.c IncludeLines:true Name:print_cpu]

map[SourceCode: 111:	static void print_cpu(struct seq_file *m, int cpu, u64 now)
 112:	{
 113:		struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
 114:		int i;
 115:	
 116:		SEQ_printf(m, "cpu: %d\n", cpu);
 117:		for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 118:			SEQ_printf(m, " clock %d:\n", i);
 119:			print_base(m, cpu_base->clock_base + i, now);
 120:		}
 121:	#define P(x) \
 122:		SEQ_printf(m, "  .%-15s: %Lu\n", #x, \
 123:			   (unsigned long long)(cpu_base->x))
 124:	#define P_ns(x) \
 125:		SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
 126:			   (unsigned long long)(ktime_to_ns(cpu_base->x)))
 127:	
 128:	#ifdef CONFIG_HIGH_RES_TIMERS
 129:		P_ns(expires_next);
 130:		P(hres_active);
 131:		P(nr_events);
 132:		P(nr_retries);
 133:		P(nr_hangs);
 134:		P(max_hang_time);
 135:	#endif
 136:	#undef P
 137:	#undef P_ns
 138:	
 139:	#ifdef CONFIG_TICK_ONESHOT
 140:	# define P(x) \
 141:		SEQ_printf(m, "  .%-15s: %Lu\n", #x, \
 142:			   (unsigned long long)(ts->x))
 143:	# define P_ns(x) \
 144:		SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
 145:			   (unsigned long long)(ktime_to_ns(ts->x)))
 146:	# define P_flag(x, f)			    \
 147:		SEQ_printf(m, "  .%-15s: %d\n", #x, !!(ts->flags & (f)))
 148:	
 149:		{
 150:			struct tick_sched *ts = tick_get_tick_sched(cpu);
 151:			P_flag(nohz, TS_FLAG_NOHZ);
 152:			P_flag(highres, TS_FLAG_HIGHRES);
 153:			P_ns(last_tick);
 154:			P_flag(tick_stopped, TS_FLAG_STOPPED);
 155:			P(idle_jiffies);
 156:			P(idle_calls);
 157:			P(idle_sleeps);
 158:			P_ns(idle_entrytime);
 159:			P_ns(idle_waketime);
 160:			P_ns(idle_exittime);
 161:			P_ns(idle_sleeptime);
 162:			P_ns(iowait_sleeptime);
 163:			P(last_jiffies);
 164:			P(next_timer);
 165:			P_ns(idle_expires);
 166:			SEQ_printf(m, "jiffies: %Lu\n",
 167:				   (unsigned long long)jiffies);
 168:		}
 169:	#endif
 170:	
 171:	#undef P
 172:	#undef P_ns
 173:		SEQ_printf(m, "\n");
 174:	}
 SourceFile:kernel/time/timer_list.c]

gemini-3.1-pro-preview

							input: 9605
							output: 44
							thoughts: 393

**Analyzing a Benign Data Race in HRTimers**

Okay, so I'm looking at this code and immediately see a potential data race. It looks like the issue revolves around `cpu_base->expires_next` in the high-resolution timers (HRTimers) code. Specifically, the race is between the `hrtimer_interrupt` function and the `print_cpu` function.

In `hrtimer_interrupt`, there's a critical section protected by `cpu_base->lock`.  Inside this critical section, `cpu_base->expires_next` is being manipulated.  It's first set to `KTIME_MAX` as part of a mechanism to prevent race conditions during timer queue processing, and I can see the intention behind this, it's about controlling timer re-queuing during a critical expiry process.

However, in `print_cpu`, there's a read of `cpu_base->expires_next`. And I can see that this read happens *without* holding that same lock. My gut reaction is: data race! But it's likely a benign one.

The `print_cpu` function is using a `seq_file` for output, so this read is likely for diagnostic purposes.  The value read is simply printed to the output. The fact that the code uses `ktime_to_ns` suggests that it's dealing with nanoseconds, but the important point is this: if `print_cpu` reads a torn or intermediate value for `expires_next`, which could easily happen with a lockless read, it'll just print whatever it reads. No harm, no foul.  `ktime_to_ns` looks to be a simple cast or some minor arithmetic operation, so there's no complex or volatile manipulation happening here.  So, at worst, the output will be slightly misleading.  I'll just double-check the implementation of `ktime_to_ns` to be certain.

This is a classic example of a benign data race: a lockless read of a diagnostic value where the consequences of a race are minor or acceptable. This is a very familiar pattern in `/proc` or `/sys` files, where real-time accuracy isn't critical.

map[ContextFile:kernel/time/timer_list.c IncludeLines:true Name:ktime_to_ns]

map[SourceCode:  77:	/* Convert ktime_t to nanoseconds */
  78:	static inline s64 ktime_to_ns(const ktime_t kt)
  79:	{
  80:		return kt;
  81:	}
 SourceFile:include/linux/ktime.h]

gemini-3.1-pro-preview

							input: 10611
							output: 51
							thoughts: 87

**Analyzing the Benign Nature of this Data Race**

Okay, so looking at this, `ktime_to_ns` just passes along that `s64` value, essentially returning it directly.  And from what I'm seeing, `print_cpu` is simply reading that 8-byte integer and printing it out. There's really nothing sophisticated happening here.  

Given this, I am quite confident that this can't possibly result in any serious issues. There's no possibility of memory corruption, no chance of control flow hijacking, and no real vector for a denial of service. The underlying integer itself cannot be changed by another process while it is in a read process of another since it's an integer. This is just a completely benign data race. The worst-case scenario is an incorrect value, which won't cause any security implications.

Now, let me just quickly verify if `/proc/timer_list` is accessible to unprivileged users, just to be thorough.

map[ContextFile:kernel/time/timer_list.c IncludeSnippetLines:5 Name:timer_list_show SourceTreePrefix:]

map[References:<nil> TruncatedOutput:false]

gemini-3.1-pro-preview

							input: 10976
							output: 43
							thoughts: 31

Here's a summary of my thought process, as requested:

**Navigating Kernel Timers**

Okay, so I'm looking at this code and I see `timer_list_show` – that function name rings a bell.  Ah, yes, it seems to be involved with the timer functionality. The obvious next step is to pinpoint its definition.  The cross-referencing is pointing me towards `kernel/time/timer_list.c`. Let's open that file and dive into the implementation. I need to understand what `timer_list_show` is doing within the broader context of the timer management system. I need to determine its purpose and how it fits into the kernel's overall timing mechanism. Let's see what we can find.

map[ContextFile:kernel/time/timer_list.c IncludeLines:true Name:timer_list_show]

map[SourceCode: 284:	static int timer_list_show(struct seq_file *m, void *v)
 285:	{
 286:		struct timer_list_iter *iter = v;
 287:	
 288:		if (iter->cpu == -1 && !iter->second_pass)
 289:			timer_list_header(m, iter->now);
 290:		else if (!iter->second_pass)
 291:			print_cpu(m, iter->cpu, iter->now);
 292:	#ifdef CONFIG_GENERIC_CLOCKEVENTS
 293:		else if (iter->cpu == -1 && iter->second_pass)
 294:			timer_list_show_tickdevices_header(m);
 295:		else
 296:			print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
 297:	#endif
 298:		return 0;
 299:	}
 SourceFile:kernel/time/timer_list.c]

gemini-3.1-pro-preview

							input: 11507
							output: 19
							thoughts: 15

Here's my thought process, as if I were considering this myself:

**Tracing `timer_list_show` Usage**

Okay, I need to understand the impact of `timer_list_show`. My immediate approach is to figure out where it's actually *used* in the codebase. I don't want to get lost in the weeds right away. Knowing the call sites will give me a critical context. I can use my tools to locate all the instances where this function is called. From there, I'll examine the surrounding code to determine how `timer_list_show` fits into the broader picture. I need to understand its arguments and return values and how they are handled. With that information, I'll be in a much better position to assess its purpose and potential consequences.

map[Expression:timer_list_show]

map[Output:drivers/tty/sysrq.c=189=static void sysrq_handle_show_timers(u8 key)
drivers/tty/sysrq.c-190-{
drivers/tty/sysrq.c:191:	sysrq_timer_list_show();
drivers/tty/sysrq.c-192-}
--
include/linux/hrtimer.h=344=extern void __init hrtimers_init(void);
--
include/linux/hrtimer.h-346-/* Show pending timers: */
include/linux/hrtimer.h:347:extern void sysrq_timer_list_show(void);
include/linux/hrtimer.h-348-
--
kernel/time/timer_list.c=178=print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
--
kernel/time/timer_list.c-241-
kernel/time/timer_list.c:242:static void timer_list_show_tickdevices_header(struct seq_file *m)
kernel/time/timer_list.c-243-{
--
kernel/time/timer_list.c=257=static inline void timer_list_header(struct seq_file *m, u64 now)
--
kernel/time/timer_list.c-264-
kernel/time/timer_list.c:265:void sysrq_timer_list_show(void)
kernel/time/timer_list.c-266-{
--
kernel/time/timer_list.c-275-#ifdef CONFIG_GENERIC_CLOCKEVENTS
kernel/time/timer_list.c:276:	timer_list_show_tickdevices_header(NULL);
kernel/time/timer_list.c-277-	for_each_online_cpu(cpu)
--
kernel/time/timer_list.c-283-#ifdef CONFIG_PROC_FS
kernel/time/timer_list.c:284:static int timer_list_show(struct seq_file *m, void *v)
kernel/time/timer_list.c-285-{
--
kernel/time/timer_list.c-293-	else if (iter->cpu == -1 && iter->second_pass)
kernel/time/timer_list.c:294:		timer_list_show_tickdevices_header(m);
kernel/time/timer_list.c-295-	else
--
kernel/time/timer_list.c=342=static const struct seq_operations timer_list_sops = {
--
kernel/time/timer_list.c-345-	.stop = timer_list_stop,
kernel/time/timer_list.c:346:	.show = timer_list_show,
kernel/time/timer_list.c-347-};
--
lib/sys_info.c=139=static void __sys_info(unsigned long si_mask)
--
lib/sys_info.c-147-	if (si_mask & SYS_INFO_TIMERS)
lib/sys_info.c:148:		sysrq_timer_list_show();
lib/sys_info.c-149-
]

gemini-3.1-pro-preview

							input: 12522
							output: 20
							thoughts: 29

Here's my summary, as if I were thinking these thoughts:

**Tracing the Usage of `timer_list_sops`**

Okay, so I see `timer_list_sops` is in play. My first thought is to understand its scope and impact. Let's trace back where this is actually being *used*. Knowing where `timer_list_sops` is referenced will give me a better understanding of how the system is designed and function in the broader context. Time to start digging through the code...

map[Expression:timer_list_sops]

map[Output:kernel/time/timer_list.c=338=static void timer_list_stop(struct seq_file *seq, void *v)
--
kernel/time/timer_list.c-341-
kernel/time/timer_list.c:342:static const struct seq_operations timer_list_sops = {
kernel/time/timer_list.c-343-	.start = timer_list_start,
--
kernel/time/timer_list.c=349=static int __init init_timer_list_procfs(void)
--
kernel/time/timer_list.c-352-
kernel/time/timer_list.c:353:	pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
kernel/time/timer_list.c-354-			sizeof(struct timer_list_iter), NULL);
]

gemini-3.1-pro-preview

							input: 12921
							output: 63
							thoughts: 479

**Analyzing `/proc/timer_list` Accessibility in User Namespaces**

Okay, so I'm looking at this `proc_create_seq_private` call, specifically the permissions, `0400`. That's root-readable, right? Just the owner, which is root, can read it. So, that means unprivileged processes are locked out, that seems pretty standard. But hold on, what about user namespaces? I need to think this through carefully.

Since it's a `/proc` entry, it's a global procfs file, so generally, these aren't accessible from non-init user namespaces unless specifically mounted or exposed. But... `/proc` *is* mounted in user namespaces. Hmm. The owner is root in the init namespace.

Ah, right, if a user *does* create a user namespace and mounts `/proc`, files owned by root in the init namespace will be seen as `nobody` (or maybe `overflowuid`) within the new user namespace. And they *won't* have read access to it because they don't have `CAP_DAC_OVERRIDE` in the init namespace. This is important, it's about the owner of the inode. They only have the override within their *own* namespace.

So, let's test the hypothesis: Is `/proc/timer_list` actually accessible? If an unprivileged user creates a user namespace, they become root *in that namespace* and can mount `/proc`, sure. However, the inode for `/proc/timer_list` will still be owned by the init namespace's root (uid 0).

Since the user namespace root doesn't map to the init namespace root, that file is going to appear as `nobody` (like, 65534) in the user namespace.

And the permissions? They're still `0400`. The user namespace root doesn't have `CAP_DAC_OVERRIDE` that *trumps* the init namespace's root. That's a crucial point.

Wait... `CAP_DAC_OVERRIDE` in a user namespace *only* applies to files whose UIDs are mapped *into* that user namespace! So, if the file's UID, which is zero in the init namespace, isn't mapped, it's treated as `overflowuid`. And even *then*, `CAP_DAC_OVERRIDE` in the user namespace doesn't give them access! This is the key.

Therefore, my conclusion is that `/proc/timer_list` *is NOT* accessible from user namespaces created by unprivileged users. I'm pretty confident in that analysis. Now, I should verify this by checking it out.

map[Question:Is `/proc/timer_list` readable by a process in a user namespace created by an unprivileged user? The file is created with `proc_create_seq_private("timer_list", 0400, ...)`.]

map[Answer:No, `/proc/timer_list` is **not readable** by a process in a user namespace created by an unprivileged user.

The file is created in `kernel/time/timer_list.c` with the following call:
```c
pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
                             sizeof(struct timer_list_iter), NULL);
```
The mode `0400` restricts read access to the owner of the file. In the case of `/proc/timer_list`, the owner is the global root user (UID 0 in the initial user namespace), as it is created as a top-level entry in the global `/proc` filesystem and inherits the UID/GID of the `proc_root` entry (which is 0).

When an unprivileged user creates a new user namespace, they typically map their own global UID (e.g., 1000) to UID 0 inside the new namespace. However, the global root user (UID 0) is generally not mapped into such a namespace. 

The kernel's permission check (specifically `generic_permission` and `capable_wrt_inode_uidgid`) works as follows:
1.  **UID Match**: The process's filesystem UID (global 1000) is compared with the file's UID (global 0). They do not match.
2.  **Capabilities**: The kernel checks if the process has the `CAP_DAC_OVERRIDE` or `CAP_DAC_READ_SEARCH` capability. While the process may have these capabilities *within its own user namespace*, these capabilities only allow overriding permissions for files owned by UIDs that are mapped into that namespace. Since global UID 0 is not mapped, the process's capabilities do not grant access to the file.

This restriction was intentionally introduced in commit `8e7df2b5b7f2` ("timer/debug: Change /proc/timer_list from 0444 to 0400") to prevent non-root users from accessing kernel timing and address information.]

gemini-3-flash-preview

You are a capable Linux kernel developer tasked with researching complex questions
about kernel source code. You will be given a concrete question, and need to provide
a concrete answer.
Use tools extensively while researching the question. Don't make assumptions,
or rely on your previous knowledge about the kernel source code, use available tools
to access the actual source code.
Use all available sources of information:
 - kernel source code
 - documentation in the Documentation dir in the source tree
 - git commits descriptions, git blame

Prefer calling several tools at the same time to save round-trips.

Is `/proc/timer_list` readable by a process in a user namespace created by an unprivileged user? The file is created with `proc_create_seq_private("timer_list", 0400, ...)`.

No, `/proc/timer_list` is **not readable** by a process in a user namespace created by an unprivileged user.

The file is created in `kernel/time/timer_list.c` with the following call:
```c
pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
                             sizeof(struct timer_list_iter), NULL);
```
The mode `0400` restricts read access to the owner of the file. In the case of `/proc/timer_list`, the owner is the global root user (UID 0 in the initial user namespace), as it is created as a top-level entry in the global `/proc` filesystem and inherits the UID/GID of the `proc_root` entry (which is 0).

When an unprivileged user creates a new user namespace, they typically map their own global UID (e.g., 1000) to UID 0 inside the new namespace. However, the global root user (UID 0) is generally not mapped into such a namespace. 

The kernel's permission check (specifically `generic_permission` and `capable_wrt_inode_uidgid`) works as follows:
1.  **UID Match**: The process's filesystem UID (global 1000) is compared with the file's UID (global 0). They do not match.
2.  **Capabilities**: The kernel checks if the process has the `CAP_DAC_OVERRIDE` or `CAP_DAC_READ_SEARCH` capability. While the process may have these capabilities *within its own user namespace*, these capabilities only allow overriding permissions for files owned by UIDs that are mapped into that namespace. Since global UID 0 is not mapped, the process's capabilities do not grant access to the file.

This restriction was intentionally introduced in commit `8e7df2b5b7f2` ("timer/debug: Change /proc/timer_list from 0444 to 0400") to prevent non-root users from accessing kernel timing and address information.

gemini-3-flash-preview

							input: 3245
							output: 19
							thoughts: 152

**Investigating the Readability of /proc/timer_list in User Namespaces**

Okay, so I'm being asked a pretty specific question: can an unprivileged user, operating within a user namespace they created, actually read `/proc/timer_list`? Seems straightforward, right? I've seen this kind of thing before. My initial thought is, based on the `proc_create_seq_private("timer_list", 0400, ...)` call, it's probably *not* going to be readable. The mode `0400` *should* mean "read-only for owner" – and the owner is almost certainly root in this context.

But, I know better than to jump to conclusions. I need to understand how `proc_create_seq_private` functions *specifically* with regard to permissions and namespaces. Does it perform the standard credential checks against the calling process? Most of the `proc_create*` family does, based on my past experience. But I need to be sure. I've encountered some quirks in the past.

So, first things first: I'm going to have to dive into the kernel source. My immediate goal is to locate the code that actually creates that `/proc/timer_list` entry. I need to see *precisely* how the permissions are handled and if any namespace-specific considerations are taken into account during the permission checks. That's my starting point.

map[Expression:"timer_list"]

map[Output:kernel/time/timer.c=776=static const struct debug_obj_descr timer_debug_descr = {
kernel/time/timer.c:777:	.name			= "timer_list",
kernel/time/timer.c-778-	.debug_hint		= timer_debug_hint,
--
kernel/time/timer_list.c=349=static int __init init_timer_list_procfs(void)
--
kernel/time/timer_list.c-352-
kernel/time/timer_list.c:353:	pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
kernel/time/timer_list.c-354-			sizeof(struct timer_list_iter), NULL);
]

gemini-3-flash-preview

							input: 3934
							output: 24
							thoughts: 361

**Analyzing the Timer List Procfs Entry**

Okay, so I'm looking at how the `/proc/timer_list` file is created. The code in `kernel/time/timer_list.c` shows it's being set up in `init_timer_list_procfs` using `proc_create_seq_private`. The interesting part is the mode: `0400`. This is important, as it restricts access to the owner of the file. In a standard setup, that owner would likely be global root for files under `/proc`. However, things get a bit more nuanced within user namespaces.

My immediate question now is, given that the file is created with `0400` permissions and, likely, owned by root (uid 0), how does the proc filesystem handle permission checks when a process *within* a user namespace attempts to read this file? Specifically, if global root is mapped differently (or not at all) inside the namespace. The crucial point hinges on whether the accessing process has `CAP_DAC_OVERRIDE`, or if it's considered the owner in a user namespace. Since the permission is only read by the owner, that's what's vital.

I need to confirm who actually *is* the owner of `/proc/timer_list`. My experience tells me it's either the user who mounted the procfs or it defaults to global root. This ownership is key to how permissions will ultimately be resolved. Let me double-check the code in `kernel/time/timer_list.c` for any namespace-specific handling or modifications to the ownership or permission setting.

map[File:kernel/time/timer_list.c]

map[Contents:// SPDX-License-Identifier: GPL-2.0
/*
 * List pending timers
 *
 * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
 */

#include <linux/proc_fs.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/kallsyms.h>
#include <linux/nmi.h>

#include <linux/uaccess.h>

#include "tick-internal.h"

struct timer_list_iter {
	int cpu;
	bool second_pass;
	u64 now;
};

/*
 * This allows printing both to /proc/timer_list and
 * to the console (on SysRq-Q):
 */
__printf(2, 3)
static void SEQ_printf(struct seq_file *m, const char *fmt, ...)
{
	va_list args;

	va_start(args, fmt);

	if (m)
		seq_vprintf(m, fmt, args);
	else
		vprintk(fmt, args);

	va_end(args);
}

static void
print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
	    int idx, u64 now)
{
	SEQ_printf(m, " #%d: <%p>, %ps", idx, taddr, ACCESS_PRIVATE(timer, function));
	SEQ_printf(m, ", S:%02x", timer->is_queued);
	SEQ_printf(m, "\n");
	SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n",
		(unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)),
		(unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)),
		(long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now),
		(long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now));
}

static void print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
{
	struct timerqueue_linked_node *curr;
	struct hrtimer *timer, tmp;
	unsigned long next = 0, i;
	unsigned long flags;

next_one:
	i = 0;

	touch_nmi_watchdog();

	raw_spin_lock_irqsave(&base->cpu_base->lock, flags);

	curr = timerqueue_linked_first(&base->active);
	/*
	 * Crude but we have to do this O(N*N) thing, because
	 * we have to unlock the base when printing:
	 */
	while (curr && i < next) {
		curr = timerqueue_linked_next(curr);
		i++;
	}

	if (curr) {

		timer = container_of(curr, struct hrtimer, node);
		tmp = *timer;
		raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);

		print_timer(m, timer, &tmp, i, now);
		next++;
		goto next_one;
	}
	raw_spin_unlock_irqrestore(&base->cpu_base->lock, flags);
}

static void
print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
{
	SEQ_printf(m, "  .base:       %p\n", base);
	SEQ_printf(m, "  .index:      %d\n", base->index);

	SEQ_printf(m, "  .resolution: %u nsecs\n", hrtimer_resolution);
#ifdef CONFIG_HIGH_RES_TIMERS
	SEQ_printf(m, "  .offset:     %Ld nsecs\n",
		   (long long) base->offset);
#endif
	SEQ_printf(m,   "active timers:\n");
	print_active_timers(m, base, now + ktime_to_ns(base->offset));
}

static void print_cpu(struct seq_file *m, int cpu, u64 now)
{
	struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
	int i;

	SEQ_printf(m, "cpu: %d\n", cpu);
	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
		SEQ_printf(m, " clock %d:\n", i);
		print_base(m, cpu_base->clock_base + i, now);
	}
#define P(x) \
	SEQ_printf(m, "  .%-15s: %Lu\n", #x, \
		   (unsigned long long)(cpu_base->x))
#define P_ns(x) \
	SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
		   (unsigned long long)(ktime_to_ns(cpu_base->x)))

#ifdef CONFIG_HIGH_RES_TIMERS
	P_ns(expires_next);
	P(hres_active);
	P(nr_events);
	P(nr_retries);
	P(nr_hangs);
	P(max_hang_time);
#endif
#undef P
#undef P_ns

#ifdef CONFIG_TICK_ONESHOT
# define P(x) \
	SEQ_printf(m, "  .%-15s: %Lu\n", #x, \
		   (unsigned long long)(ts->x))
# define P_ns(x) \
	SEQ_printf(m, "  .%-15s: %Lu nsecs\n", #x, \
		   (unsigned long long)(ktime_to_ns(ts->x)))
# define P_flag(x, f)			    \
	SEQ_printf(m, "  .%-15s: %d\n", #x, !!(ts->flags & (f)))

	{
		struct tick_sched *ts = tick_get_tick_sched(cpu);
		P_flag(nohz, TS_FLAG_NOHZ);
		P_flag(highres, TS_FLAG_HIGHRES);
		P_ns(last_tick);
		P_flag(tick_stopped, TS_FLAG_STOPPED);
		P(idle_jiffies);
		P(idle_calls);
		P(idle_sleeps);
		P_ns(idle_entrytime);
		P_ns(idle_waketime);
		P_ns(idle_exittime);
		P_ns(idle_sleeptime);
		P_ns(iowait_sleeptime);
		P(last_jiffies);
		P(next_timer);
		P_ns(idle_expires);
		SEQ_printf(m, "jiffies: %Lu\n",
			   (unsigned long long)jiffies);
	}
#endif

#undef P
#undef P_ns
	SEQ_printf(m, "\n");
}

#ifdef CONFIG_GENERIC_CLOCKEVENTS
static void
print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
{
	struct clock_event_device *dev = td->evtdev;

	touch_nmi_watchdog();

	SEQ_printf(m, "Tick Device: mode:     %d\n", td->mode);
	if (cpu < 0)
		SEQ_printf(m, "Broadcast device\n");
	else
		SEQ_printf(m, "Per CPU device: %d\n", cpu);

	SEQ_printf(m, "Clock Event Device: ");
	if (!dev) {
		SEQ_printf(m, "<NULL>\n");
		return;
	}
	SEQ_printf(m, "%s\n", dev->name);
	SEQ_printf(m, " max_delta_ns:   %llu\n",
		   (unsigned long long) dev->max_delta_ns);
	SEQ_printf(m, " min_delta_ns:   %llu\n",
		   (unsigned long long) dev->min_delta_ns);
	SEQ_printf(m, " mult:           %u\n", dev->mult);
	SEQ_printf(m, " shift:          %u\n", dev->shift);
	SEQ_printf(m, " mode:           %d\n", clockevent_get_state(dev));
	SEQ_printf(m, " next_event:     %Ld nsecs\n",
		   (unsigned long long) ktime_to_ns(dev->next_event));

	SEQ_printf(m, " set_next_event: %ps\n", dev->set_next_event);

	if (dev->set_state_shutdown)
		SEQ_printf(m, " shutdown:       %ps\n",
			dev->set_state_shutdown);

	if (dev->set_state_periodic)
		SEQ_printf(m, " periodic:       %ps\n",
			dev->set_state_periodic);

	if (dev->set_state_oneshot)
		SEQ_printf(m, " oneshot:        %ps\n",
			dev->set_state_oneshot);

	if (dev->set_state_oneshot_stopped)
		SEQ_printf(m, " oneshot stopped: %ps\n",
			dev->set_state_oneshot_stopped);

	if (dev->tick_resume)
		SEQ_printf(m, " resume:         %ps\n",
			dev->tick_resume);

	SEQ_printf(m, " event_handler:  %ps\n", dev->event_handler);
	SEQ_printf(m, "\n");
	SEQ_printf(m, " retries:        %lu\n", dev->retries);

#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
	if (cpu >= 0) {
		const struct clock_event_device *wd = tick_get_wakeup_device(cpu);

		SEQ_printf(m, "Wakeup Device: %s\n", wd ? wd->name : "<NULL>");
	}
#endif
	SEQ_printf(m, "\n");
}

static void timer_list_show_tickdevices_header(struct seq_file *m)
{
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
	print_tickdevice(m, tick_get_broadcast_device(), -1);
	SEQ_printf(m, "tick_broadcast_mask: %*pb\n",
		   cpumask_pr_args(tick_get_broadcast_mask()));
#ifdef CONFIG_TICK_ONESHOT
	SEQ_printf(m, "tick_broadcast_oneshot_mask: %*pb\n",
		   cpumask_pr_args(tick_get_broadcast_oneshot_mask()));
#endif
	SEQ_printf(m, "\n");
#endif
}
#endif

static inline void timer_list_header(struct seq_file *m, u64 now)
{
	SEQ_printf(m, "Timer List Version: v0.10\n");
	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
	SEQ_printf(m, "\n");
}

void sysrq_timer_list_show(void)
{
	u64 now = ktime_to_ns(ktime_get());
	int cpu;

	timer_list_header(NULL, now);

	for_each_online_cpu(cpu)
		print_cpu(NULL, cpu, now);

#ifdef CONFIG_GENERIC_CLOCKEVENTS
	timer_list_show_tickdevices_header(NULL);
	for_each_online_cpu(cpu)
		print_tickdevice(NULL, tick_get_device(cpu), cpu);
#endif
	return;
}

#ifdef CONFIG_PROC_FS
static int timer_list_show(struct seq_file *m, void *v)
{
	struct timer_list_iter *iter = v;

	if (iter->cpu == -1 && !iter->second_pass)
		timer_list_header(m, iter->now);
	else if (!iter->second_pass)
		print_cpu(m, iter->cpu, iter->now);
#ifdef CONFIG_GENERIC_CLOCKEVENTS
	else if (iter->cpu == -1 && iter->second_pass)
		timer_list_show_tickdevices_header(m);
	else
		print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
#endif
	return 0;
}

static void *move_iter(struct timer_list_iter *iter, loff_t offset)
{
	for (; offset; offset--) {
		iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
		if (iter->cpu >= nr_cpu_ids) {
#ifdef CONFIG_GENERIC_CLOCKEVENTS
			if (!iter->second_pass) {
				iter->cpu = -1;
				iter->second_pass = true;
			} else
				return NULL;
#else
			return NULL;
#endif
		}
	}
	return iter;
}

static void *timer_list_start(struct seq_file *file, loff_t *offset)
{
	struct timer_list_iter *iter = file->private;

	if (!*offset)
		iter->now = ktime_to_ns(ktime_get());
	iter->cpu = -1;
	iter->second_pass = false;
	return move_iter(iter, *offset);
}

static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset)
{
	struct timer_list_iter *iter = file->private;
	++*offset;
	return move_iter(iter, 1);
}

static void timer_list_stop(struct seq_file *seq, void *v)
{
}

static const struct seq_operations timer_list_sops = {
	.start = timer_list_start,
	.next = timer_list_next,
	.stop = timer_list_stop,
	.show = timer_list_show,
};

static int __init init_timer_list_procfs(void)
{
	struct proc_dir_entry *pe;

	pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
			sizeof(struct timer_list_iter), NULL);
	if (!pe)
		return -ENOMEM;
	return 0;
}
__initcall(init_timer_list_procfs);
#endif
]

gemini-3-flash-preview

							input: 8344
							output: 43
							thoughts: 99

Okay, here's my summary, tailored to an expert like myself:

**Investigating `proc_create_seq_private` and Permissions**

Right, so I've got a file created with `0400` permissions. Nothing too surprising there. The key, however, is that `proc_create_seq_private` function is employed in its creation. My immediate thought is, I need to understand how *that* specific function handles the user and group IDs (UID/GID) for the newly created proc entry. My gut says that if `proc_create_seq_private` doesn't explicitly set them, it'll default to root (0). That's the typical behavior, and I need to confirm this.

Time to dive into the source code to get the definitive answer. I'll need to locate the definition of `proc_create_seq_private` -- `fs/proc/generic.c` seems like the most likely place, or wherever the relevant procfs code resides for my kernel version. I'll focus on how the UID/GID are set or defaulted during the creation process. That should tell me if I need to explicitly set them to avoid running afoul of security constraints.

map[ContextFile:fs/proc/generic.c IncludeLines:true Name:proc_create_seq_private]

map[SourceCode: 634:	struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
 635:			struct proc_dir_entry *parent, const struct seq_operations *ops,
 636:			unsigned int state_size, void *data)
 637:	{
 638:		struct proc_dir_entry *p;
 639:	
 640:		p = proc_create_reg(name, mode, &parent, data);
 641:		if (!p)
 642:			return NULL;
 643:		p->proc_ops = &proc_seq_ops;
 644:		p->seq_ops = ops;
 645:		p->state_size = state_size;
 646:		return proc_register(parent, p);
 647:	}
 SourceFile:fs/proc/generic.c]

gemini-3-flash-preview

							input: 9000
							output: 41
							thoughts: 21

Here's my take on the thought process, as requested:

**Deconstructing the Process Creation**

Okay, so the code's jumping into `proc_create_reg`. That function name rings a bell, but let's not rely on memory alone. I need to understand what's happening at this core level. This feels like the pivotal point for the process creation, the function that's responsible for the registration aspects of the procedure, and that likely involves setting up the data structures and context needed for the new process within the kernel's process table or its equivalent. We need to dig into this `proc_create_reg` to figure out its inner workings. Let's see what that function does.

map[ContextFile:fs/proc/generic.c IncludeLines:true Name:proc_create_reg]

map[SourceCode: 566:	struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
 567:			struct proc_dir_entry **parent, void *data)
 568:	{
 569:		struct proc_dir_entry *p;
 570:	
 571:		if ((mode & S_IFMT) == 0)
 572:			mode |= S_IFREG;
 573:		if ((mode & S_IALLUGO) == 0)
 574:			mode |= S_IRUGO;
 575:		if (WARN_ON_ONCE(!S_ISREG(mode)))
 576:			return NULL;
 577:	
 578:		p = __proc_create(parent, name, mode, 1);
 579:		if (p) {
 580:			p->proc_iops = &proc_file_inode_operations;
 581:			p->data = data;
 582:		}
 583:		return p;
 584:	}
 SourceFile:fs/proc/generic.c]

gemini-3-flash-preview

							input: 9532
							output: 40
							thoughts: 8

Okay, here's my interpretation of that thought process, assuming I'm deep in the weeds of kernel development:

**Initial Assessment: Creation of a Process Entry**

Alright, so the core of this operation hinges on the `__proc_create` function. That immediately tells me we're dealing with the fundamental setup of a process or a related process-like entity within the kernel. I need to understand the context. Is this a new task, a thread, or perhaps a system-level process we're constructing? The name itself screams "create," so it's likely about instantiating a new process control block (PCB), or its equivalent in this architecture.

My mind immediately starts ticking through the implications. I’m thinking about the arguments passed to `__proc_create`. What data structures are initialized? What security checks are performed? How does it allocate memory for the process's context and address space if it handles such allocation? Does it register the new process with any global data structures, such as a process table or a scheduler queue? I'll probably need to understand the flow control to ensure it's thread-safe. I'm wondering if this is a low-level operation that builds up the necessary data structures or if this is the high-level API call for user-facing applications. Understanding the semantics of `__proc_create` is absolutely crucial for tracing through the rest of the execution path. And I know I will need to look up documentation to ensure I understand every aspect of this function.

map[ContextFile:fs/proc/generic.c IncludeLines:true Name:__proc_create]

map[SourceCode: 418:	static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 419:						  const char *name,
 420:						  umode_t mode,
 421:						  nlink_t nlink)
 422:	{
 423:		struct proc_dir_entry *ent = NULL;
 424:		const char *fn;
 425:		struct qstr qstr;
 426:	
 427:		if (xlate_proc_name(name, parent, &fn) != 0)
 428:			goto out;
 429:		qstr.name = fn;
 430:		qstr.len = strlen(fn);
 431:		if (qstr.len == 0 || qstr.len >= 256) {
 432:			WARN(1, "name len %u\n", qstr.len);
 433:			return NULL;
 434:		}
 435:		if (qstr.len == 1 && fn[0] == '.') {
 436:			WARN(1, "name '.'\n");
 437:			return NULL;
 438:		}
 439:		if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') {
 440:			WARN(1, "name '..'\n");
 441:			return NULL;
 442:		}
 443:		if (*parent == &proc_root && name_to_int(&qstr) != ~0U) {
 444:			WARN(1, "create '/proc/%s' by hand\n", qstr.name);
 445:			return NULL;
 446:		}
 447:		if (is_empty_pde(*parent)) {
 448:			WARN(1, "attempt to add to permanently empty directory");
 449:			return NULL;
 450:		}
 451:	
 452:		ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL);
 453:		if (!ent)
 454:			goto out;
 455:	
 456:		if (qstr.len + 1 <= SIZEOF_PDE_INLINE_NAME) {
 457:			ent->name = ent->inline_name;
 458:		} else {
 459:			ent->name = kmalloc(qstr.len + 1, GFP_KERNEL);
 460:			if (!ent->name) {
 461:				pde_free(ent);
 462:				return NULL;
 463:			}
 464:		}
 465:	
 466:		memcpy(ent->name, fn, qstr.len + 1);
 467:		ent->namelen = qstr.len;
 468:		ent->mode = mode;
 469:		ent->nlink = nlink;
 470:		ent->subdir = RB_ROOT;
 471:		refcount_set(&ent->refcnt, 1);
 472:		spin_lock_init(&ent->pde_unload_lock);
 473:		INIT_LIST_HEAD(&ent->pde_openers);
 474:		proc_set_user(ent, (*parent)->uid, (*parent)->gid);
 475:	
 476:		/* Revalidate everything under /proc/${pid}/net */
 477:		if ((*parent)->flags & PROC_ENTRY_FORCE_LOOKUP)
 478:			pde_force_lookup(ent);
 479:	
 480:	out:
 481:		return ent;
 482:	}
 SourceFile:fs/proc/generic.c]

gemini-3-flash-preview

							input: 10929
							output: 42
							thoughts: 377

**Analyzing the /proc/timer_list Entry Creation**

Okay, so I'm digging into how the `/proc/timer_list` entry is created. My initial thought was to look at how the user and group are set for this new process entry. The code snippet in `__proc_create` shows that `proc_set_user` sets the new entry's UID and GID to those of its parent. That's straightforward enough.

The tricky part is that, for `/proc/timer_list`, the parent seems to be `NULL` in the `proc_create_seq_private` function. My initial assumption was this would default the UID/GID to that of `proc_root`, but that's not what the code appears to do.

Now I'm looking at `proc_create_reg`. This function is pivotal; it takes a `struct proc_dir_entry **parent`. The double pointer is unusual and now I see that `proc_create_seq_private` *passes the address* of its `parent` variable to `proc_create_reg`. This is a crucial distinction. If `parent` is initially `NULL`, it's now a pointer to `NULL`, which changes how it's handled.

Okay, let's step through. `proc_create_reg` calls `__proc_create`, passing the potentially-`NULL` parent. In `__proc_create`, the `xlate_proc_name` function seems like the logical place to check. That function probably has to handle this potential `NULL` parent and correctly process the entry's parent. I need to investigate `xlate_proc_name` to see what it's doing with that `NULL` pointer. That's the key to understanding the UID/GID assignment.

map[ContextFile:fs/proc/generic.c IncludeLines:true Name:xlate_proc_name]

map[SourceCode: 182:	static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
 183:				   const char **residual)
 184:	{
 185:		int rv;
 186:	
 187:		read_lock(&proc_subdir_lock);
 188:		rv = __xlate_proc_name(name, ret, residual);
 189:		read_unlock(&proc_subdir_lock);
 190:		return rv;
 191:	}
 SourceFile:fs/proc/generic.c]

gemini-3-flash-preview

							input: 11904
							output: 43
							thoughts: 10

Okay, here's my attempt at summarizing the thought process, tailored for an expert audience, and written in the first person:

**Analyzing `__xlate_proc_name` and Its Implications**

Alright, let's break this down. When I see `__xlate_proc_name`, my mind immediately goes into overdrive, considering its potential role in translation or conversion processes. The double underscore prefix is a classic indicator, isn't it? It suggests an internal, implementation-specific function or symbol, very likely hidden from direct public use. That sparks a few questions right off the bat:

*   **What's the context?** Am I dealing with a compiler, an interpreter, a library, or a specific system call? The application domain is crucial to interpreting this. Is it a language runtime, OS kernel component, or something else entirely? The environment will significantly color my understanding.
*   **What's being translated?** Is it code (e.g., intermediate representation to machine code, or even source code translation), data, or addresses? The data type or structure undergoing translation provides a lot of context here. Is this an internal data representation being translated into a more user-friendly form?
*   **What's the process?** Based on the name, it's clear there's some sort of name translation happening. Are we talking about symbol resolution, stringification, or macro expansion? Is it related to dynamic linking, name mangling, or something more specialized? The algorithm employed here is what I want to understand.
*   **How robust is it?** Error handling is key. This could be where the magic, or the bugs, reside. What are the failure modes? What happens if the name can't be translated? Are there graceful fallbacks or will it throw a cryptic error? And what about security? Does this process introduce any vulnerabilities, such as format string vulnerabilities?
*   **Performance implications:** Any kind of name translation, especially if done dynamically, can introduce performance bottlenecks. I need to think about how often this function gets called, the complexity of its logic, and any caching or optimization strategies that might be in place. If it's a critical path, every cycle matters.

So, while I'm looking at `__xlate_proc_name`, I'm simultaneously probing for clues about these areas. It could be a simple utility function, or a highly sophisticated piece of the puzzle. I need more information to really pin it down, but the initial impressions give me a good framework to start with. Let's see how much more context I can gather.

map[ContextFile:fs/proc/generic.c IncludeLines:true Name:__xlate_proc_name]

map[SourceCode: 157:	/*
 158:	 * This function parses a name such as "tty/driver/serial", and
 159:	 * returns the struct proc_dir_entry for "/proc/tty/driver", and
 160:	 * returns "serial" in residual.
 161:	 */
 162:	static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
 163:				     const char **residual)
 164:	{
 165:		const char     		*cp = name, *next;
 166:		struct proc_dir_entry	*de;
 167:	
 168:		de = *ret ?: &proc_root;
 169:		while ((next = strchr(cp, '/')) != NULL) {
 170:			de = pde_subdir_find(de, cp, next - cp);
 171:			if (!de) {
 172:				WARN(1, "name '%s'\n", name);
 173:				return -ENOENT;
 174:			}
 175:			cp = next + 1;
 176:		}
 177:		*residual = cp;
 178:		*ret = de;
 179:		return 0;
 180:	}
 SourceFile:fs/proc/generic.c]

gemini-3-flash-preview

							input: 12888
							output: 39
							thoughts: 130

**Analyzing the User ID and Group ID Assignment in `procfs`**

Okay, so I'm tracing the user and group ID assignments within the `procfs` implementation, specifically when creating a new entry. It looks like if `*ret` is `NULL`, the code defaults to using `&proc_root`. This means `parent` gets set to `&proc_root` in that scenario. Makes sense, that's the default root directory. Then, back in `__proc_create`, on line 474, `proc_set_user(ent, (*parent)->uid, (*parent)->gid)` is executed. Aha, so `ent->uid` and `ent->gid` are assigned values from the parent – which, in this `NULL` `ret` case, is `proc_root.uid` and `proc_root.gid`. This is the crux of how the permissions are propagated from the root. Now, to be absolutely certain of the default initial values I need to check where `proc_root` is initialized. Let me go over to `fs/proc/root.c` and take a look.

map[ContextFile:fs/proc/root.c IncludeLines:true Name:proc_root]

map[SourceCode: 442:	/*
 443:	 * This is the root "inode" in the /proc tree..
 444:	 */
 445:	struct proc_dir_entry proc_root = {
 446:		.low_ino	= PROCFS_ROOT_INO,
 447:		.namelen	= 5,
 448:		.mode		= S_IFDIR | S_IRUGO | S_IXUGO,
 449:		.nlink		= 2,
 450:		.refcnt		= REFCOUNT_INIT(1),
 451:		.proc_iops	= &proc_root_inode_operations,
 452:		.proc_dir_ops	= &proc_root_operations,
 453:		.parent		= &proc_root,
 454:		.subdir		= RB_ROOT,
 455:		.name		= "/proc",
 456:	};
 SourceFile:fs/proc/root.c]

gemini-3-flash-preview

							input: 13580
							output: 41
							thoughts: 362

**Analyzing `/proc/timer_list` Permissions in User Namespaces**

Okay, so I'm looking at this code and trying to figure out the security implications, specifically around `/proc/timer_list`. My initial thought was that since the code doesn't explicitly assign a user ID (`.uid`) or group ID (`.gid`), it should default to 0, which would be the global root, `GLOBAL_ROOT_UID/GID`. But then I saw the `proc_set_user` function, and that clarifies things: it *does* set `de->uid` and `de->gid`, just not directly in this snippet.

So that means `/proc/timer_list` *is* owned by the global root user and group, and its mode is `0400`. That's important. It basically means only the global root can read it.

Now, the interesting question is: what happens when a process in a *user namespace* tries to access it? That's where things get tricky. A process inside a user namespace has a specific UID within *that* namespace. If it's the "root" of the namespace, its UID inside that namespace is 0. But, crucially, its UID in the initial, or "parent", namespace (where `/proc/timer_list` was created) is whatever UID was used to create that namespace.

Then I paused and considered `/proc` itself. I had to remind myself about how it works with user namespaces. I know `/proc` is usually shared, but some parts are namespace-specific. However, `/proc/timer_list` is a global file, created at boot. That makes the whole thing much more interesting.

Okay, so if a process within a user namespace tries to *open* `/proc/timer_list`, the kernel will perform a permission check. The inode for `/proc/timer_list` will have `i_uid` and `i_gid` which will be derived from the `proc_dir_entry`. That's the key.

Now, I need to see exactly how `proc_get_inode` sets the inode's UID and GID to be absolutely certain. It would be helpful to trace the code to understand how it deals with UID/GID translation in the context of user namespaces. Understanding that link is the most important piece of the puzzle.

map[ContextFile:fs/proc/inode.c IncludeLines:true Name:proc_get_inode]

map[SourceCode: 628:	struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 629:	{
 630:		struct inode *inode = new_inode(sb);
 631:	
 632:		if (!inode) {
 633:			pde_put(de);
 634:			return NULL;
 635:		}
 636:	
 637:		inode->i_private = de->data;
 638:		inode->i_ino = de->low_ino;
 639:		simple_inode_init_ts(inode);
 640:		PROC_I(inode)->pde = de;
 641:		if (is_empty_pde(de)) {
 642:			make_empty_dir_inode(inode);
 643:			return inode;
 644:		}
 645:	
 646:		if (de->mode) {
 647:			inode->i_mode = de->mode;
 648:			inode->i_uid = de->uid;
 649:			inode->i_gid = de->gid;
 650:		}
 651:		if (de->size)
 652:			inode->i_size = de->size;
 653:		if (de->nlink)
 654:			set_nlink(inode, de->nlink);
 655:	
 656:		if (S_ISREG(inode->i_mode)) {
 657:			inode->i_op = de->proc_iops;
 658:			if (pde_has_proc_read_iter(de))
 659:				inode->i_fop = &proc_iter_file_ops;
 660:			else
 661:				inode->i_fop = &proc_reg_file_ops;
 662:	#ifdef CONFIG_COMPAT
 663:			if (pde_has_proc_compat_ioctl(de)) {
 664:				if (pde_has_proc_read_iter(de))
 665:					inode->i_fop = &proc_iter_file_ops_compat;
 666:				else
 667:					inode->i_fop = &proc_reg_file_ops_compat;
 668:			}
 669:	#endif
 670:		} else if (S_ISDIR(inode->i_mode)) {
 671:			inode->i_op = de->proc_iops;
 672:			inode->i_fop = de->proc_dir_ops;
 673:		} else if (S_ISLNK(inode->i_mode)) {
 674:			inode->i_op = de->proc_iops;
 675:			inode->i_fop = NULL;
 676:		} else {
 677:			BUG();
 678:		}
 679:		return inode;
 680:	}
 SourceFile:fs/proc/inode.c]

gemini-3-flash-preview

							input: 15324
							output: 43
							thoughts: 650

**Analyzing `/proc/timer_list` Access in User Namespaces**

Okay, so I'm diving into how `/proc/timer_list` works with user namespaces. It looks like the inode's UID and GID are set from the `proc_dir_entry`, and that's initially global root (UID 0). Makes sense. Now, the standard VFS permission check, probably using something like `generic_permission`, kicks in when a process in a user namespace tries to access it.

Right, the key here is how the kernel handles credentials in user namespaces. It's comparing the process's `fsuid` with the inode's `i_uid`. And, oh yeah, I need to remember that `inode->i_uid` is a `kuid_t`, that's an *internal* kernel representation, meaning it's using the *global* UID. Got it.

Permission checks usually boil down to something like `inode_owner_or_capable`, so either the `fsuid` matches `i_uid` or the process has `CAP_DAC_OVERRIDE`. Now, the tricky part... capabilities are *namespaced*. So, a process's `CAP_DAC_OVERRIDE` in a user namespace only works for files where the global UID is mapped into the namespace.

If `/proc/timer_list` is owned by global root, which it is, and the user namespace *doesn't* map global root (UID 0) – which is typical for unprivileged namespaces – then even `CAP_DAC_OVERRIDE` within the namespace won't help. The file's still owned by global root, and the process's `fsuid` (likely some non-zero global UID) won't match.

Hold on, I see the catch. Unprivileged user namespaces usually map the creating user's UID to 0 in the new namespace, but not usually global UID 0. If global UID 0 *isn't* mapped, the file's UID will appear to be something else, usually `overflowuid` (65534) from within the namespace, or some other unmapped UID. So the process's UID would definitely not match the apparent owner. And `CAP_DAC_OVERRIDE` won't apply to global root.

So, for a `0400` file owned by global root, it *should* be inaccessible to an unprivileged user within a user namespace unless, and this is important, the namespace has global root mapped *or* the user is actually global root. Makes sense.

But wait a minute, I have to remember that `/proc` isn't always standard. Some `/proc` files can have custom permission handlers. However, `timer_list` uses `proc_file_inode_operations`, so it's probably using the standard VFS checks.

Time to go check `proc_file_inode_operations` to be absolutely certain...

map[ContextFile:fs/proc/generic.c IncludeLines:true Name:proc_file_inode_operations]

map[SourceCode: 153:	static const struct inode_operations proc_file_inode_operations = {
 154:		.setattr	= proc_setattr,
 155:	};
 SourceFile:fs/proc/generic.c]

gemini-3-flash-preview

							input: 16731
							output: 30
							thoughts: 1335

**Analyzing `/proc/timer_list` Accessibility in User Namespaces**

Okay, so the initial question revolves around whether an unprivileged user can read `/proc/timer_list`. My first thought is that since there's no explicit `.permission` method, it relies on the default file permissions. Then, I need to verify that `proc_create_seq_private` is consistently used with `0400` for this file, which the user confirmed. I've double-checked in the kernel code (`kernel/time/timer_list.c`) and that's indeed the case.

The key then becomes how the `proc` filesystem behaves within user namespaces, specifically around mount options. When mounting `/proc` in a user namespace, it usually creates a new mount instance linked to the associated PID namespace. Given that user namespaces and PID namespaces are frequently created together, I need to understand what happens to file UIDs in this scenario.

I've looked at `proc_fill_super` in `fs/proc/root.c` and remember that `proc_get_inode` will use the `de->uid` and `de->gid`. `proc_root`'s `uid` and `gid` are initialized to 0. The crucial part here is how this interacts with user namespace mapping. If the global UID 0 isn't mapped within the user namespace, the inode's `i_uid` remains global UID 0, and `stat` will likely report an `overflowuid`.

With a `0400` permission, only the owner (global UID 0) can read it. However, if my UID within the namespace is, say, 1000 (mapped to 0), I am *not* the owner. Therefore, I can't read it. I'm wondering if there's any mechanism to change ownership of `/proc` entries based on the namespace. While some entries under `/proc/[pid]/` get the PID's owner, `/proc/timer_list` is a top-level entry.

Let's quickly check whether `timer_list` has some namespace specific treatment or some security check to see if it is considered safe. I don't see any special handling in `kernel/time/timer_list.c`. The `proc_set_user` function isn't called after the creation of the entry, so there is no way to change the user's permissions once the file is made.

A key concern is that this `/proc` file might leak kernel addresses, as it displays addresses. I know `%p` might be hashed unless `%pK` is used, and `kptr_restrict` is set. Even with those measures, timing information might still be exposed. I confirmed from the code that `timer_list_show` prints addresses.

I've verified that `proc_create_seq_private` is the *only* method of creating the file.

Now, if the user namespace *does* map global UID 0 (which is unlikely), a process could be UID 0 and access it. But, this is ruled out by the premise of an unprivileged user.

I've also verified that the file creation mode is indeed `0400`. There's no after-the-fact change to permissions.

Finally, I checked for other `timer_list` proc files with a `git grep`, but this appears to be the only one. Just to be completely thorough, I confirmed that `proc_root`'s UID/GID are always initialized to 0, and that no code changes them later. I verified this with a search of the code.

Given the `0400` permissions, the default ownership of UID 0, the lack of any namespace-specific permission changes, and that the unprivileged user *likely* cannot map UID 0, the answer should be no; the user cannot read `/proc/timer_list`.

map[Expression:proc_root.uid|proc_set_user\(&proc_root]

gemini-3-flash-preview

							input: 18947
							output: 22
							thoughts: 1111

**Analyzing the Accessibility of `/proc/timer_list`**

Okay, let's break this down. My initial understanding is that `/proc/timer_list` inherits its ownership from `proc_root`, which, in turn, is owned by global root. Its mode is set to `0400`, meaning it's intended to be readable only by root.

I should double-check that `proc_create_seq_private` *always* sets this mode. Right, it's hardcoded, so that's consistent. I also made sure that the `subset=pid` mount option does not change this behavior, it doesn't.

Now, I can't directly verify if an unprivileged user can read it on a live system, but I can trace the code. I need to figure out *how* the permission check actually happens.

My next step is to examine the read path. I'm looking for special permission checks in `seq_read` or `proc_reg_read`. I know `proc_reg_open` is called when the file is opened, and if the associated `proc_ops` structure has a `.proc_open` method, that's called. For `timer_list`, this uses `proc_seq_ops` which means `proc_seq_open` is called, which then uses `seq_open`. Nothing obvious there.

The permission check should be happening in the VFS layer, specifically with `may_open`. `may_open` then calls `inode_permission`. `inode_permission` calls `do_inode_permission`. If the inode has an `.i_op->permission` method defined, that's called; otherwise, it calls `generic_permission`. The `proc_file_inode_operations` doesn't have a `.permission` method, so it uses `generic_permission`.

`generic_permission` first checks ACLs, but it's the `acl_permission_check` that matters here. If there are no ACLs, it checks the mode bits directly. With `0400`, it checks: if the caller's UID matches the inode's UID, then the read permission (the `4`) is checked. If the caller's UID does *not* match, it checks group and other permissions. Those are 0, so access is denied unless the user has `CAP_DAC_OVERRIDE`.

`capable_wrt_inode_uidgid` will be called, which in turn checks if the caller has the capability in the namespace that owns the inode.

Now, who owns the inode? The inode's UID/GID are global root. I know that the procfs superblock has `s_user_ns`. If procfs is mounted in a user namespace, then `s_user_ns` is that user namespace.

I should re-examine how the `proc_mount` function sets `s_user_ns`. Let me look at `fs/proc/root.c`... Ah, yes. It uses `mount_ns`. So, if a user namespace is involved, this is the key. It's likely `mount_nodev`, but I need to confirm this.

map[File:fs/proc/root.c]

map[Contents:// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/proc/root.c
 *
 *  Copyright (C) 1991, 1992 Linus Torvalds
 *
 *  proc root directory handling functions
 */
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/sched/stat.h>
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/user_namespace.h>
#include <linux/fs_context.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
#include <linux/fs_parser.h>
#include <linux/cred.h>
#include <linux/magic.h>
#include <linux/slab.h>

#include "internal.h"

struct proc_fs_context {
	struct pid_namespace	*pid_ns;
	unsigned int		mask;
	enum proc_hidepid	hidepid;
	int			gid;
	enum proc_pidonly	pidonly;
};

enum proc_param {
	Opt_gid,
	Opt_hidepid,
	Opt_subset,
	Opt_pidns,
};

static const struct fs_parameter_spec proc_fs_parameters[] = {
	fsparam_u32("gid",		Opt_gid),
	fsparam_string("hidepid",	Opt_hidepid),
	fsparam_string("subset",	Opt_subset),
	fsparam_file_or_string("pidns",	Opt_pidns),
	{}
};

static inline int valid_hidepid(unsigned int value)
{
	return (value == HIDEPID_OFF ||
		value == HIDEPID_NO_ACCESS ||
		value == HIDEPID_INVISIBLE ||
		value == HIDEPID_NOT_PTRACEABLE);
}

static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param)
{
	struct proc_fs_context *ctx = fc->fs_private;
	struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid);
	struct fs_parse_result result;
	int base = (unsigned long)hidepid_u32_spec.data;

	if (param->type != fs_value_is_string)
		return invalf(fc, "proc: unexpected type of hidepid value\n");

	if (!kstrtouint(param->string, base, &result.uint_32)) {
		if (!valid_hidepid(result.uint_32))
			return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
		ctx->hidepid = result.uint_32;
		return 0;
	}

	if (!strcmp(param->string, "off"))
		ctx->hidepid = HIDEPID_OFF;
	else if (!strcmp(param->string, "noaccess"))
		ctx->hidepid = HIDEPID_NO_ACCESS;
	else if (!strcmp(param->string, "invisible"))
		ctx->hidepid = HIDEPID_INVISIBLE;
	else if (!strcmp(param->string, "ptraceable"))
		ctx->hidepid = HIDEPID_NOT_PTRACEABLE;
	else
		return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);

	return 0;
}

static int proc_parse_subset_param(struct fs_context *fc, char *value)
{
	struct proc_fs_context *ctx = fc->fs_private;

	while (value) {
		char *ptr = strchr(value, ',');

		if (ptr != NULL)
			*ptr++ = '\0';

		if (*value != '\0') {
			if (!strcmp(value, "pid")) {
				ctx->pidonly = PROC_PIDONLY_ON;
			} else {
				return invalf(fc, "proc: unsupported subset option - %s\n", value);
			}
		}
		value = ptr;
	}

	return 0;
}

#ifdef CONFIG_PID_NS
static int proc_parse_pidns_param(struct fs_context *fc,
				  struct fs_parameter *param,
				  struct fs_parse_result *result)
{
	struct proc_fs_context *ctx = fc->fs_private;
	struct pid_namespace *target, *active = task_active_pid_ns(current);
	struct ns_common *ns;
	struct file *ns_filp __free(fput) = NULL;

	switch (param->type) {
	case fs_value_is_file:
		/* came through fsconfig, steal the file reference */
		ns_filp = no_free_ptr(param->file);
		break;
	case fs_value_is_string:
		ns_filp = filp_open(param->string, O_RDONLY, 0);
		break;
	default:
		WARN_ON_ONCE(true);
		break;
	}
	if (!ns_filp)
		ns_filp = ERR_PTR(-EBADF);
	if (IS_ERR(ns_filp)) {
		errorfc(fc, "could not get file from pidns argument");
		return PTR_ERR(ns_filp);
	}

	if (!proc_ns_file(ns_filp))
		return invalfc(fc, "pidns argument is not an nsfs file");
	ns = get_proc_ns(file_inode(ns_filp));
	if (ns->ns_type != CLONE_NEWPID)
		return invalfc(fc, "pidns argument is not a pidns file");
	target = container_of(ns, struct pid_namespace, ns);

	/*
	 * pidns= is shorthand for joining the pidns to get a fsopen fd, so the
	 * permission model should be the same as pidns_install().
	 */
	if (!ns_capable(target->user_ns, CAP_SYS_ADMIN)) {
		errorfc(fc, "insufficient permissions to set pidns");
		return -EPERM;
	}
	if (!pidns_is_ancestor(target, active))
		return invalfc(fc, "cannot set pidns to non-descendant pidns");

	put_pid_ns(ctx->pid_ns);
	ctx->pid_ns = get_pid_ns(target);
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
	return 0;
}
#endif /* CONFIG_PID_NS */

static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
	struct proc_fs_context *ctx = fc->fs_private;
	struct fs_parse_result result;
	int opt, err;

	opt = fs_parse(fc, proc_fs_parameters, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case Opt_gid:
		ctx->gid = result.uint_32;
		break;

	case Opt_hidepid:
		err = proc_parse_hidepid_param(fc, param);
		if (err)
			return err;
		break;

	case Opt_subset:
		err = proc_parse_subset_param(fc, param->string);
		if (err)
			return err;
		break;

	case Opt_pidns:
#ifdef CONFIG_PID_NS
		/*
		 * We would have to RCU-protect every proc_pid_ns() or
		 * proc_sb_info() access if we allowed this to be reconfigured
		 * for an existing procfs instance. Luckily, procfs instances
		 * are cheap to create, and mount-beneath would let you
		 * atomically replace an instance even with overmounts.
		 */
		if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
			errorfc(fc, "cannot reconfigure pidns for existing procfs");
			return -EBUSY;
		}
		err = proc_parse_pidns_param(fc, param, &result);
		if (err)
			return err;
		break;
#else
		errorfc(fc, "pidns mount flag not supported on this system");
		return -EOPNOTSUPP;
#endif

	default:
		return -EINVAL;
	}

	ctx->mask |= 1 << opt;
	return 0;
}

static void proc_apply_options(struct proc_fs_info *fs_info,
			       struct fs_context *fc,
			       struct user_namespace *user_ns)
{
	struct proc_fs_context *ctx = fc->fs_private;

	if (ctx->mask & (1 << Opt_gid))
		fs_info->pid_gid = make_kgid(user_ns, ctx->gid);
	if (ctx->mask & (1 << Opt_hidepid))
		fs_info->hide_pid = ctx->hidepid;
	if (ctx->mask & (1 << Opt_subset))
		fs_info->pidonly = ctx->pidonly;
	if (ctx->mask & (1 << Opt_pidns) &&
	    !WARN_ON_ONCE(fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)) {
		put_pid_ns(fs_info->pid_ns);
		fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
	}
}

static int proc_fill_super(struct super_block *s, struct fs_context *fc)
{
	struct proc_fs_context *ctx = fc->fs_private;
	struct inode *root_inode;
	struct proc_fs_info *fs_info;
	int ret;

	fs_info = kzalloc_obj(*fs_info);
	if (!fs_info)
		return -ENOMEM;

	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
	proc_apply_options(fs_info, fc, current_user_ns());

	/* User space would break if executables or devices appear on proc */
	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
	s->s_blocksize = 1024;
	s->s_blocksize_bits = 10;
	s->s_magic = PROC_SUPER_MAGIC;
	s->s_op = &proc_sops;
	s->s_time_gran = 1;
	s->s_fs_info = fs_info;

	/*
	 * procfs isn't actually a stacking filesystem; however, there is
	 * too much magic going on inside it to permit stacking things on
	 * top of it
	 */
	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;

	/* procfs dentries and inodes don't require IO to create */
	s->s_shrink->seeks = 0;

	pde_get(&proc_root);
	root_inode = proc_get_inode(s, &proc_root);
	if (!root_inode) {
		pr_err("proc_fill_super: get root inode failed\n");
		return -ENOMEM;
	}

	s->s_root = d_make_root(root_inode);
	if (!s->s_root) {
		pr_err("proc_fill_super: allocate dentry failed\n");
		return -ENOMEM;
	}

	ret = proc_setup_self(s);
	if (ret) {
		return ret;
	}
	return proc_setup_thread_self(s);
}

static int proc_reconfigure(struct fs_context *fc)
{
	struct super_block *sb = fc->root->d_sb;
	struct proc_fs_info *fs_info = proc_sb_info(sb);

	sync_filesystem(sb);

	proc_apply_options(fs_info, fc, current_user_ns());
	return 0;
}

static int proc_get_tree(struct fs_context *fc)
{
	return get_tree_nodev(fc, proc_fill_super);
}

static void proc_fs_context_free(struct fs_context *fc)
{
	struct proc_fs_context *ctx = fc->fs_private;

	put_pid_ns(ctx->pid_ns);
	kfree(ctx);
}

static const struct fs_context_operations proc_fs_context_ops = {
	.free		= proc_fs_context_free,
	.parse_param	= proc_parse_param,
	.get_tree	= proc_get_tree,
	.reconfigure	= proc_reconfigure,
};

static int proc_init_fs_context(struct fs_context *fc)
{
	struct proc_fs_context *ctx;

	ctx = kzalloc_obj(struct proc_fs_context);
	if (!ctx)
		return -ENOMEM;

	ctx->pid_ns = get_pid_ns(task_active_pid_ns(current));
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
	fc->fs_private = ctx;
	fc->ops = &proc_fs_context_ops;
	return 0;
}

static void proc_kill_sb(struct super_block *sb)
{
	struct proc_fs_info *fs_info = proc_sb_info(sb);

	kill_anon_super(sb);
	if (fs_info) {
		put_pid_ns(fs_info->pid_ns);
		kfree_rcu(fs_info, rcu);
	}
}

static struct file_system_type proc_fs_type = {
	.name			= "proc",
	.init_fs_context	= proc_init_fs_context,
	.parameters		= proc_fs_parameters,
	.kill_sb		= proc_kill_sb,
	.fs_flags		= FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM,
};

void __init proc_root_init(void)
{
	proc_init_kmemcache();
	set_proc_pid_nlink();
	proc_self_init();
	proc_thread_self_init();
	proc_symlink("mounts", NULL, "self/mounts");

	proc_net_init();
	proc_mkdir("fs", NULL);
	proc_mkdir("driver", NULL);
	proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
	/* just give it a mountpoint */
	proc_create_mount_point("openprom");
#endif
	proc_tty_init();
	proc_mkdir("bus", NULL);
	proc_sys_init();

	/*
	 * Last things last. It is not like userspace processes eager
	 * to open /proc files exist at this point but register last
	 * anyway.
	 */
	register_filesystem(&proc_fs_type);
}

static int proc_root_getattr(struct mnt_idmap *idmap,
			     const struct path *path, struct kstat *stat,
			     u32 request_mask, unsigned int query_flags)
{
	generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(path->dentry),
			 stat);
	stat->nlink = proc_root.nlink + nr_processes();
	return 0;
}

static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
	if (!proc_pid_lookup(dentry, flags))
		return NULL;

	return proc_lookup(dir, dentry, flags);
}

static int proc_root_readdir(struct file *file, struct dir_context *ctx)
{
	if (ctx->pos < FIRST_PROCESS_ENTRY) {
		int error = proc_readdir(file, ctx);
		if (unlikely(error <= 0))
			return error;
		ctx->pos = FIRST_PROCESS_ENTRY;
	}

	return proc_pid_readdir(file, ctx);
}

/*
 * The root /proc directory is special, as it has the
 * <pid> directories. Thus we don't use the generic
 * directory handling functions for that..
 */
static const struct file_operations proc_root_operations = {
	.read		 = generic_read_dir,
	.iterate_shared	 = proc_root_readdir,
	.llseek		= generic_file_llseek,
};

/*
 * proc root can do almost nothing..
 */
static const struct inode_operations proc_root_inode_operations = {
	.lookup		= proc_root_lookup,
	.getattr	= proc_root_getattr,
};

/*
 * This is the root "inode" in the /proc tree..
 */
struct proc_dir_entry proc_root = {
	.low_ino	= PROCFS_ROOT_INO,
	.namelen	= 5,
	.mode		= S_IFDIR | S_IRUGO | S_IXUGO,
	.nlink		= 2,
	.refcnt		= REFCOUNT_INIT(1),
	.proc_iops	= &proc_root_inode_operations,
	.proc_dir_ops	= &proc_root_operations,
	.parent		= &proc_root,
	.subdir		= RB_ROOT,
	.name		= "/proc",
};
]

gemini-3-flash-preview

							input: 25182
							output: 35
							thoughts: 1778

**Analyzing `/proc/timer_list` Accessibility in User Namespaces**

Okay, so the user's question brings up an interesting access control scenario within user namespaces, specifically regarding `/proc/timer_list`. Let me think this through step by step.

Initially, in the context of `proc_init_fs_context`, the `fc->user_ns` is set to the user namespace of the PID namespace. This implies that if a user creates a new user namespace and then a new PID namespace, the `s->s_user_ns` within the `proc` filesystem will be that new user namespace.

Now, considering the `generic_permission` check, which utilizes `capable_wrt_inode_uidgid`, we need to understand how permissions are determined.  `privileged_wrt_inode_uidgid` is key here: it checks if the inode's UID and GID have mappings within the current user namespace. If there's no mapping for the inode's UID (global 0, in the case of `timer_list`) or GID, access is denied. Since `timer_list`'s UID is global 0, and our unprivileged user's UID is something else, this means `CAP_DAC_OVERRIDE` isn't going to help. Moreover, because the file's mode is `0400`, the access is denied outright unless the effective UID matches the file's owner.

My immediate thought was whether there might be exceptions for `/proc` files, given their system-level nature, but in this case, `/proc/timer_list` is definitely `0400`. We know it is a global PDE and is created for every proc instance. Also, I must ensure that `timer_list` is not hidden, for example, if `subset=pid` is used (it is not). It might return `ENOENT` if the filesystem is subsetted to PIDs.

The core question, then, is about an unprivileged user within their own namespace. They can mount `proc`, if they also have their own PID namespace. However, the files *within* that mount will have the same global UIDs as the regular `/proc` (mostly).  So, I checked to ensure whether the user, even if "root" within their namespace (by mapping their UID to 0), can access it. Because the inode's UID is *global* 0, their "local" root wouldn't be the owner, and thus wouldn't be able to access it.

Now, I revisited the code to confirm if there are any other instances where `timer_list` is created, but it's only created once, during boot. I also considered whether `proc_set_user` might be called with the namespace's root UID, but `init_timer_list_procfs` runs early, in the initial namespace, so no luck there.

I questioned if the file was created with a different mode, perhaps `0444`, in the past. Checking the current code, however, confirms the `0400` mode. I even checked `git log` about the permissions of `timer_list` but that's a shot in the dark.

I briefly considered the `sysrq` path, knowing SysRq-Q calls `sysrq_timer_list_show`, but that prints to dmesg, which isn't the same as accessing `/proc/timer_list`. I need to stay focused on the user's original question.

Furthermore, I explored if `proc_create_seq_private` might use the current namespace when creating the PDE but PDEs are global and not per-namespace, so the file's UID and GID are set at creation. `proc_get_inode` uses those fixed values. The code makes it clear `/proc/timer_list` always has `i_uid = 0` (global). I re-checked `proc_get_inode` to ensure there isn't any overriding code.

I also looked at `proc_set_user`, where `de->uid` and `de->gid` are set but the parent's UID for `timer_list` is 0, so that doesn't help the unprivileged user either.

Thus, the logical conclusion is:

1.  `/proc/timer_list` is owned by global UID 0.
2.  Its mode is `0400` (readable only by the owner).
3.  An unprivileged user in a user namespace has a *different* global UID.
4.  Even if they are "root" (UID 0) inside *their* namespace, their *global* UID remains their original UID (e.g., 1000).
5.  The

map[CodeRegexp:timer_list PathPrefix:kernel/time/timer_list.c]

map[Output:a9314773a91a timer_list: Guard procfs specific code
58c5fc2b96e4 time: Remove useless filenames in top level comments
44414d82cfe0 proc: introduce proc_create_seq_private
8e7df2b5b7f2 timer/debug: Change /proc/timer_list from 0444 to 0400
84a78a6504f5 timer_list: correct the iterator for timer_list
b3956a896ea5 timer_list: Convert timer list to be a proper seq_file
60cf7ea849e7 timer_list: Split timer_list_show_tickdevices
828c09509b96 const: constify remaining file_operations
de809347aeef timers: Drop write permission on /proc/timer_list
c33fff0afbef kernel: use non-racy method for proc entries creation
]

gemini-3-flash-preview

							input: 28269
							output: 26
							thoughts: 46

Okay, here's my interpretation of that commit message, expressed as my internal thought process:

**Diving into that Kernel Timer Change**

Right, that caught my eye: `8e7df2b5b7f2 timer/debug: Change /proc/timer_list from 0444 to 0400`. Always interesting to see low-level changes like this affecting `/proc`. Okay, time to dissect that commit. I'm immediately thinking about the implications of modifying the permissions on `/proc/timer_list`. Why the shift from 0444 (read-only for all) to 0400 (read-only for root)? My expert spidey senses are tingling - it suggests a security or information disclosure concern has been identified. I'm going to want to understand the rationale behind this tightening. Was there a vulnerability related to unprivileged processes accessing the timer list that needed patching? Or perhaps it was deemed an inadvertent leak of sensitive timing information that could be used for side-channel attacks? The details are crucial. Let's see if the commit message sheds any more light on the motivations, or if there's a related CVE or security advisory I need to dig into. This is definitely a change that warrants a deeper look.

map[Commit:8e7df2b5b7f2]

map[Output:commit 8e7df2b5b7f245c9bd11064712db5cb69044a362
Author: Ingo Molnar <mingo@kernel.org>
Date:   Mon Nov 13 07:15:41 2017 +0100

    timer/debug: Change /proc/timer_list from 0444 to 0400
    
    While it uses %pK, there's still few reasons to read this file
    as non-root.
    
    Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
    Acked-by: Thomas Gleixner <tglx@linutronix.de>
    Cc: Peter Zijlstra <peterz@infradead.org>
    Cc: linux-kernel@vger.kernel.org
    Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 0e7f5428a148..0ed768b56c60 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -389,7 +389,7 @@ static int __init init_timer_list_procfs(void)
 {
 	struct proc_dir_entry *pe;
 
-	pe = proc_create("timer_list", 0444, NULL, &timer_list_fops);
+	pe = proc_create("timer_list", 0400, NULL, &timer_list_fops);
 	if (!pe)
 		return -ENOMEM;
 	return 0;
]

gemini-3-flash-preview

							input: 29069
							output: 22
							thoughts: 920

**Analyzing File Permissions and User Namespaces**

Okay, so the commit message mentions `%pK`, but my immediate scan of the code shows `%p`, specifically in the `print_timer` function. It seems `%p` is used for the address and `%ps` for the symbol name. I need to make sure I am not missing a recent change that has not updated the documentation. Then it dawns on me: `%p` is hashed in modern kernels, which is generally preferred over `%pK` due to `kptr_restrict`.

The key here is the `0400` permission. That restricts access to the file's owner, which is global root. An unprivileged user inside a user namespace is *not* global root. They might *think* they are root within their namespace, but the kernel knows they aren't the file's owner.

The question then becomes, can an unprivileged user ever read it? Even in the initial user namespace, the `0400` permission prevents access. What if they're in a user namespace and have a UID mapping for what they think is root?

Let me think. The check is handled by `proc_create_seq_private` with `0400`, which relies on `generic_permission`. As I recall, that uses `capable_wrt_inode_uidgid`. I remember that the `capable_wrt_inode_uidgid` will return false if the inode's UID isn't mapped. An unprivileged user cannot map global UID 0 to a local UID within their namespace. They'll typically map their own UID (e.g., 1000) to 0. So, inside the namespace, the local UID 0 is the global UID 1000, not global UID 0. The file is owned by global UID 0. The user (global 1000, local 0) is not the owner, and they don't have capabilities over global UID 0. So, no, they cannot read it.

Are there any other `/proc` files with `0400` permissions that *are* readable within a user namespace? Some in `/proc/net` are namespace-aware, but `timer_list` isn't. Let me verify. I'll search `kernel/time/timer_list.c` for any mention of `struct net`, `user_namespace`, or `pid_namespace`. Nope, nothing there.

Actually, let me check the use of `proc_create_seq_private`. Many `/proc` files are `0444`, but `timer_list` is specifically `0400`. There was a previous commit using the `proc_create_seq_private` API but that's just a change in the API, nothing more. I need to check if there are other files created with `0400` permissions in `/proc`.

map[Expression:proc_create.*0400]

map[Output:arch/arm/kernel/atags_proc.c=33=static int __init init_atags_procfs(void)
--
arch/arm/kernel/atags_proc.c-63-
arch/arm/kernel/atags_proc.c:64:	tags_entry = proc_create_data("atags", 0400, NULL, &atags_proc_ops, b);
arch/arm/kernel/atags_proc.c-65-	if (!tags_entry)
--
arch/m68k/kernel/bootinfo_proc.c=55=static int __init init_bootinfo_procfs(void)
--
arch/m68k/kernel/bootinfo_proc.c-69-
arch/m68k/kernel/bootinfo_proc.c:70:	pde = proc_create_data("bootinfo", 0400, NULL, &bootinfo_proc_ops, NULL);
arch/m68k/kernel/bootinfo_proc.c-71-	if (!pde) {
--
arch/parisc/kernel/pdc_chassis.c=269=static int __init pdc_chassis_create_procfs(void)
--
arch/parisc/kernel/pdc_chassis.c-282-			PDC_CHASSIS_VER);
arch/parisc/kernel/pdc_chassis.c:283:	proc_create_single("chassis", 0400, NULL, pdc_chassis_warn_show);
arch/parisc/kernel/pdc_chassis.c-284-	return 0;
--
arch/powerpc/kernel/rtas-proc.c=231=static int __init proc_rtas_init(void)
--
arch/powerpc/kernel/rtas-proc.c-251-		    &ppc_rtas_tone_volume_proc_ops);
arch/powerpc/kernel/rtas-proc.c:252:	proc_create_single("powerpc/rtas/rmo_buffer", 0400, NULL,
arch/powerpc/kernel/rtas-proc.c-253-			ppc_rtas_rmo_buf_show);
--
arch/powerpc/kernel/rtasd.c=546=static int __init rtas_init(void)
--
arch/powerpc/kernel/rtasd.c-555-
arch/powerpc/kernel/rtasd.c:556:	entry = proc_create("powerpc/rtas/error_log", 0400, NULL,
arch/powerpc/kernel/rtasd.c-557-			    &rtas_log_proc_ops);
--
fs/smb/client/cifs_debug.c=924=cifs_proc_init(void)
--
fs/smb/client/cifs_debug.c-932-
fs/smb/client/cifs_debug.c:933:	proc_create_single("open_files", 0400, proc_fs_cifs,
fs/smb/client/cifs_debug.c-934-			cifs_debug_files_proc_show);
--
fs/smb/client/cifs_debug.c-938-#else /* CONFIG_CIFS_DEBUG */
fs/smb/client/cifs_debug.c:939:	proc_create_single("open_dirs", 0400, proc_fs_cifs, cifs_debug_dirs_proc_show);
fs/smb/client/cifs_debug.c-940-#endif /* !CONFIG_CIFS_DEBUG */
--
fs/smb/server/proc.c=22=struct proc_dir_entry *ksmbd_proc_create(const char *name,
--
fs/smb/server/proc.c-25-{
fs/smb/server/proc.c:26:	return proc_create_single_data(name, 0400, ksmbd_proc_fs,
fs/smb/server/proc.c-27-			   show, v);
--
kernel/time/timer_list.c=349=static int __init init_timer_list_procfs(void)
--
kernel/time/timer_list.c-352-
kernel/time/timer_list.c:353:	pe = proc_create_seq_private("timer_list", 0400, NULL, &timer_list_sops,
kernel/time/timer_list.c-354-			sizeof(struct timer_list_iter), NULL);
--
lib/alloc_tag.c=927=static int __init alloc_tag_init(void)
--
lib/alloc_tag.c-948-
lib/alloc_tag.c:949:	if (!proc_create_seq_private(ALLOCINFO_FILE_NAME, 0400, NULL, &allocinfo_seq_op,
lib/alloc_tag.c-950-				     sizeof(struct allocinfo_private), NULL)) {
--
mm/vmalloc.c=5295=static int __init proc_vmalloc_init(void)
mm/vmalloc.c-5296-{
mm/vmalloc.c:5297:	proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show);
mm/vmalloc.c-5298-	return 0;
--
mm/vmstat.c=2268=void __init init_mm_internals(void)
--
mm/vmstat.c-2294-	proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
mm/vmstat.c:2295:	proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op);
mm/vmstat.c-2296-	proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
--
net/sunrpc/cache.c=1664=static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
--
net/sunrpc/cache.c-1688-	if (cd->cache_show) {
net/sunrpc/cache.c:1689:		p = proc_create_data("content", S_IFREG | 0400, cd->procfs,
net/sunrpc/cache.c-1690-				     &content_proc_ops, cd);
]

gemini-3-flash-preview

							input: 32285
							output: 23
							thoughts: 1401

**Security Analysis of /proc/timer_list in User Namespaces**

Okay, so I'm looking at these files with `0400` permissions: `vmallocinfo`, `pagetypeinfo`, and especially `timer_list`. If an unprivileged user in a user namespace could read these, it's a huge security hole – leaking sensitive kernel info. The `0400` is there *specifically* to prevent this.

Right, so, the key is whether the `proc` filesystem's `FS_USERNS_MOUNT` flag changes anything. Let me look at the code... Yep, `proc_fs_type` has `FS_USERNS_MOUNT`, meaning it's mountable inside a user namespace. When it's mounted, the superblock's `s_user_ns` is set to the namespace of the caller. But how does that affect permissions?

The `generic_permission` function is where permissions are checked. It uses `capable_wrt_inode_uidgid`. If the inode UID is 0 (root, globally), and that UID isn't mapped in the user namespace, the check should fail, right? I need to confirm that `proc_get_inode` doesn't mess with UIDs.

Ah, `proc_get_inode` just sets `inode->i_uid = de->uid`. And `de->uid` is a `kuid_t`, a *global* UID. So the inode always has a global UID of 0, and in a user namespace where global 0 isn't mapped, that's not "privileged".

There are some exceptions for `proc` files, "namespace-safe" files. But `timer_list` isn't one of them. And `proc_create_seq_private` is called with a `NULL` parent, putting `timer_list` right at the root of `/proc`.

If I'm in a user namespace and mount `proc`, the files are the *same* PDEs. The inodes might be new, but they're initialized from the same PDEs. So `/proc/timer_list` will *always* have `i_uid = 0`.

Can an unprivileged user *somehow* map global UID 0? Not unless they have `CAP_SETUID` in the parent namespace, which they *won't* if they're actually unprivileged.

So, the answer is "no," it shouldn't be possible. But let's verify. Let me check `proc_setattr`.

Okay, `proc_setattr` lets you change UID/GID, but NOT mode. But even to change UID/GID, you need to be the owner or have `CAP_CHOWN`. An unprivileged user is neither. And all `proc` mounts share the same PDE tree, so trying a different mount won't work.

But let's think this through. Can an unprivileged user read `/proc/timer_list` even in the *initial* namespace? No. It's `0400`, owned by root. If they can't read it there, they definitely can't read it in a more restricted user namespace.

Unless the user namespace somehow *makes* them the owner. As we saw, that only happens if global UID 0 is mapped to them. Which, as we know, can't happen.

What if they map their own UID (e.g., 1000) to 0 inside the namespace? They become UID 0 *inside* the namespace. But the file's `i_uid` is still global 0. Their global UID is still 1000. So, they're not the owner.

What if the `i_uid` *was* also mapped, though? Remember, `proc_get_inode` sets `inode->i_uid` to the global UID from the PDE. So, no.

Definitely "No."

Wait, let's check the code specifically in `kernel/time/timer_list.c`. Anything special for `timer_list_show`? Nope. It doesn't check permissions. Permissions are checked at `open()`. Is there any other way to access it? Maybe through another file? No. Is `timer_list` available in `/proc/self/`? No. What about in a network namespace? No, it's not in `/proc/net`.

Okay, finally, some documentation. Anything in `Documentation/admin-guide/kernel-parameters.txt`? Nope. Let's check `Documentation/filesystems/proc.rst`.

map[File:Documentation/filesystems/proc.rst]

map[Contents:.. SPDX-License-Identifier: GPL-2.0

====================
The /proc Filesystem
====================

=====================  =======================================  ================
/proc/sys              Terrehon Bowden <terrehon@pacbell.net>,  October 7 1999
                       Bodo Bauer <bb@ricochet.net>
2.4.x update	       Jorge Nerin <comandante@zaralinux.com>   November 14 2000
move /proc/sys	       Shen Feng <shen@cn.fujitsu.com>	        April 1 2009
fixes/update part 1.1  Stefani Seibold <stefani@seibold.net>    June 9 2009
=====================  =======================================  ================



.. Table of Contents

  0     Preface
  0.1	Introduction/Credits
  0.2	Legal Stuff

  1	Collecting System Information
  1.1	Process-Specific Subdirectories
  1.2	Kernel data
  1.3	IDE devices in /proc/ide
  1.4	Networking info in /proc/net
  1.5	SCSI info
  1.6	Parallel port info in /proc/parport
  1.7	TTY info in /proc/tty
  1.8	Miscellaneous kernel statistics in /proc/stat
  1.9	Ext4 file system parameters

  2	Modifying System Parameters

  3	Per-Process Parameters
  3.1	/proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
								score
  3.2	/proc/<pid>/oom_score - Display current oom-killer score
  3.3	/proc/<pid>/io - Display the IO accounting fields
  3.4	/proc/<pid>/coredump_filter - Core dump filtering settings
  3.5	/proc/<pid>/mountinfo - Information about mounts
  3.6	/proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
  3.7   /proc/<pid>/task/<tid>/children - Information about task children
  3.8   /proc/<pid>/fdinfo/<fd> - Information about opened file
  3.9   /proc/<pid>/map_files - Information about memory mapped files
  3.10  /proc/<pid>/timerslack_ns - Task timerslack value
  3.11	/proc/<pid>/patch_state - Livepatch patch operation state
  3.12	/proc/<pid>/arch_status - Task architecture specific information
  3.13  /proc/<pid>/fd - List of symlinks to open files
  3.14  /proc/<pid>/ksm_stat - Information about the process's ksm status.

  4	Configuring procfs
  4.1	Mount options

  5	Filesystem behavior

Preface
=======

0.1 Introduction/Credits
------------------------

We'd like  to  thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
other people for help compiling this documentation. We'd also like to extend a
special thank  you to Andi Kleen for documentation, which we relied on heavily
to create  this  document,  as well as the additional information he provided.
Thanks to  everybody  else  who contributed source or docs to the Linux kernel
and helped create a great piece of software... :)

The   latest   version    of   this   document   is    available   online   at
https://www.kernel.org/doc/html/latest/filesystems/proc.html

0.2 Legal Stuff
---------------

We don't  guarantee  the  correctness  of this document, and if you come to us
complaining about  how  you  screwed  up  your  system  because  of  incorrect
documentation, we won't feel responsible...

Chapter 1: Collecting System Information
========================================

In This Chapter
---------------
* Investigating  the  properties  of  the  pseudo  file  system  /proc and its
  ability to provide information on the running Linux system
* Examining /proc's structure
* Uncovering  various  information  about the kernel and the processes running
  on the system

------------------------------------------------------------------------------

The proc  file  system acts as an interface to internal data structures in the
kernel. It  can  be  used to obtain information about the system and to change
certain kernel parameters at runtime (sysctl).

First, we'll  take  a  look  at the read-only parts of /proc. In Chapter 2, we
show you how you can use /proc/sys to change settings.

1.1 Process-Specific Subdirectories
-----------------------------------

The directory  /proc  contains  (among other things) one subdirectory for each
process running on the system, which is named after the process ID (PID).

The link  'self'  points to  the process reading the file system. Each process
subdirectory has the entries listed in Table 1-1.

A process can read its own information from /proc/PID/* with no extra
permissions. When reading /proc/PID/* information for other processes, reading
process is required to have either CAP_SYS_PTRACE capability with
PTRACE_MODE_READ access permissions, or, alternatively, CAP_PERFMON
capability. This applies to all read-only information like `maps`, `environ`,
`pagemap`, etc. The only exception is `mem` file due to its read-write nature,
which requires CAP_SYS_PTRACE capabilities with more elevated
PTRACE_MODE_ATTACH permissions; CAP_PERFMON capability does not grant access
to /proc/PID/mem for other processes.

Note that an open file descriptor to /proc/<pid> or to any of its
contained files or subdirectories does not prevent <pid> being reused
for some other process in the event that <pid> exits. Operations on
open /proc/<pid> file descriptors corresponding to dead processes
never act on any new process that the kernel may, through chance, have
also assigned the process ID <pid>. Instead, operations on these FDs
usually fail with ESRCH.

.. table:: Table 1-1: Process specific entries in /proc

 =============  ===============================================================
 File		Content
 =============  ===============================================================
 clear_refs	Clears page referenced bits shown in smaps output
 cmdline	Command line arguments
 cpu		Current and last cpu in which it was executed	(2.4)(smp)
 cwd		Link to the current working directory
 environ	Values of environment variables
 exe		Link to the executable of this process
 fd		Directory, which contains all file descriptors
 maps		Memory maps to executables and library files	(2.4)
 mem		Memory held by this process
 root		Link to the root directory of this process
 stat		Process status
 statm		Process memory status information
 status		Process status in human readable form
 wchan		Present with CONFIG_KALLSYMS=y: it shows the kernel function
		symbol the task is blocked in - or "0" if not blocked.
 pagemap	Page table
 stack		Report full stack trace, enable via CONFIG_STACKTRACE
 smaps		An extension based on maps, showing the memory consumption of
		each mapping and flags associated with it
 smaps_rollup	Accumulated smaps stats for all mappings of the process.  This
		can be derived from smaps, but is faster and more convenient
 numa_maps	An extension based on maps, showing the memory locality and
		binding policy as well as mem usage (in pages) of each mapping.
 =============  ===============================================================

For example, to get the status information of a process, all you have to do is
read the file /proc/PID/status::

  >cat /proc/self/status
  Name:   cat
  State:  R (running)
  Tgid:   5452
  Pid:    5452
  PPid:   743
  TracerPid:      0						(2.4)
  Uid:    501     501     501     501
  Gid:    100     100     100     100
  FDSize: 256
  Groups: 100 14 16
  Kthread:    0
  VmPeak:     5004 kB
  VmSize:     5004 kB
  VmLck:         0 kB
  VmHWM:       476 kB
  VmRSS:       476 kB
  RssAnon:             352 kB
  RssFile:             120 kB
  RssShmem:              4 kB
  VmData:      156 kB
  VmStk:        88 kB
  VmExe:        68 kB
  VmLib:      1412 kB
  VmPTE:        20 kb
  VmSwap:        0 kB
  HugetlbPages:          0 kB
  CoreDumping:    0
  THP_enabled:	  1
  Threads:        1
  SigQ:   0/28578
  SigPnd: 0000000000000000
  ShdPnd: 0000000000000000
  SigBlk: 0000000000000000
  SigIgn: 0000000000000000
  SigCgt: 0000000000000000
  CapInh: 00000000fffffeff
  CapPrm: 0000000000000000
  CapEff: 0000000000000000
  CapBnd: ffffffffffffffff
  CapAmb: 0000000000000000
  NoNewPrivs:     0
  Seccomp:        0
  Speculation_Store_Bypass:       thread vulnerable
  SpeculationIndirectBranch:      conditional enabled
  voluntary_ctxt_switches:        0
  nonvoluntary_ctxt_switches:     1

This shows you nearly the same information you would get if you viewed it with
the ps  command.  In  fact,  ps  uses  the  proc  file  system  to  obtain its
information.  But you get a more detailed  view of the  process by reading the
file /proc/PID/status. It fields are described in table 1-2.

The  statm  file  contains  more  detailed  information about the process
memory usage. Its seven fields are explained in Table 1-3.  The stat file
contains detailed information about the process itself.  Its fields are
explained in Table 1-4.

(for SMP CONFIG users)

For making accounting scalable, RSS related information are handled in an
asynchronous manner and the value may not be very precise. To see a precise
snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
It's slow but very precise.

.. table:: Table 1-2: Contents of the status fields (as of 4.19)

 ==========================  ===================================================
 Field                       Content
 ==========================  ===================================================
 Name                        filename of the executable
 Umask                       file mode creation mask
 State                       state (R is running, S is sleeping, D is sleeping
                             in an uninterruptible wait, Z is zombie,
			     T is traced or stopped)
 Tgid                        thread group ID
 Ngid                        NUMA group ID (0 if none)
 Pid                         process id
 PPid                        process id of the parent process
 TracerPid                   PID of process tracing this process (0 if not, or
                             the tracer is outside of the current pid namespace)
 Uid                         Real, effective, saved set, and  file system UIDs
 Gid                         Real, effective, saved set, and  file system GIDs
 FDSize                      number of file descriptor slots currently allocated
 Groups                      supplementary group list
 NStgid                      descendant namespace thread group ID hierarchy
 NSpid                       descendant namespace process ID hierarchy
 NSpgid                      descendant namespace process group ID hierarchy
 NSsid                       descendant namespace session ID hierarchy
 Kthread                     kernel thread flag, 1 is yes, 0 is no
 VmPeak                      peak virtual memory size
 VmSize                      total program size
 VmLck                       locked memory size
 VmPin                       pinned memory size
 VmHWM                       peak resident set size ("high water mark")
 VmRSS                       size of memory portions. It contains the three
                             following parts
                             (VmRSS = RssAnon + RssFile + RssShmem)
 RssAnon                     size of resident anonymous memory
 RssFile                     size of resident file mappings
 RssShmem                    size of resident shmem memory (includes SysV shm,
                             mapping of tmpfs and shared anonymous mappings)
 VmData                      size of private data segments
 VmStk                       size of stack segments
 VmExe                       size of text segment
 VmLib                       size of shared library code
 VmPTE                       size of page table entries
 VmSwap                      amount of swap used by anonymous private data
                             (shmem swap usage is not included)
 HugetlbPages                size of hugetlb memory portions
 CoreDumping                 process's memory is currently being dumped
                             (killing the process may lead to a corrupted core)
 THP_enabled                 process is allowed to use THP (returns 0 when
                             PR_SET_THP_DISABLE is set on the process to disable
                             THP completely, not just partially)
 Threads                     number of threads
 SigQ                        number of signals queued/max. number for queue
 SigPnd                      bitmap of pending signals for the thread
 ShdPnd                      bitmap of shared pending signals for the process
 SigBlk                      bitmap of blocked signals
 SigIgn                      bitmap of ignored signals
 SigCgt                      bitmap of caught signals
 CapInh                      bitmap of inheritable capabilities
 CapPrm                      bitmap of permitted capabilities
 CapEff                      bitmap of effective capabilities
 CapBnd                      bitmap of capabilities bounding set
 CapAmb                      bitmap of ambient capabilities
 NoNewPrivs                  no_new_privs, like prctl(PR_GET_NO_NEW_PRIV, ...)
 Seccomp                     seccomp mode, like prctl(PR_GET_SECCOMP, ...)
 Speculation_Store_Bypass    speculative store bypass mitigation status
 SpeculationIndirectBranch   indirect branch speculation mode
 Cpus_allowed                mask of CPUs on which this process may run
 Cpus_allowed_list           Same as previous, but in "list format"
 Mems_allowed                mask of memory nodes allowed to this process
 Mems_allowed_list           Same as previous, but in "list format"
 voluntary_ctxt_switches     number of voluntary context switches
 nonvoluntary_ctxt_switches  number of non voluntary context switches
 ==========================  ===================================================


.. table:: Table 1-3: Contents of the statm fields (as of 2.6.8-rc3)

 ======== ===============================	==============================
 Field    Content
 ======== ===============================	==============================
 size     total program size (pages)		(same as VmSize in status)
 resident size of memory portions (pages)	(same as VmRSS in status)
 shared   number of pages that are shared	(i.e. backed by a file, same
						as RssFile+RssShmem in status)
 trs      number of pages that are 'code'	(not including libs; broken,
						includes data segment)
 lrs      number of pages of library		(always 0 on 2.6)
 drs      number of pages of data/stack		(including libs; broken,
						includes library text)
 dt       number of dirty pages			(always 0 on 2.6)
 ======== ===============================	==============================


.. table:: Table 1-4: Contents of the stat fields (as of 2.6.30-rc7)

  ============= ===============================================================
  Field         Content
  ============= ===============================================================
  pid           process id
  tcomm         filename of the executable
  state         state (R is running, S is sleeping, D is sleeping in an
                uninterruptible wait, Z is zombie, T is traced or stopped)
  ppid          process id of the parent process
  pgrp          pgrp of the process
  sid           session id
  tty_nr        tty the process uses
  tty_pgrp      pgrp of the tty
  flags         task flags
  min_flt       number of minor faults
  cmin_flt      number of minor faults with child's
  maj_flt       number of major faults
  cmaj_flt      number of major faults with child's
  utime         user mode jiffies
  stime         kernel mode jiffies
  cutime        user mode jiffies with child's
  cstime        kernel mode jiffies with child's
  priority      priority level
  nice          nice level
  num_threads   number of threads
  it_real_value	(obsolete, always 0)
  start_time    time the process started after system boot
  vsize         virtual memory size
  rss           resident set memory size
  rsslim        current limit in bytes on the rss
  start_code    address above which program text can run
  end_code      address below which program text can run
  start_stack   address of the start of the main process stack
  esp           current value of ESP
  eip           current value of EIP
  pending       bitmap of pending signals
  blocked       bitmap of blocked signals
  sigign        bitmap of ignored signals
  sigcatch      bitmap of caught signals
  0		(place holder, used to be the wchan address,
		use /proc/PID/wchan instead)
  0             (place holder)
  0             (place holder)
  exit_signal   signal to send to parent thread on exit
  task_cpu      which CPU the task is scheduled on
  rt_priority   realtime priority
  policy        scheduling policy (man sched_setscheduler)
  blkio_ticks   time spent waiting for block IO
  gtime         guest time of the task in jiffies
  cgtime        guest time of the task children in jiffies
  start_data    address above which program data+bss is placed
  end_data      address below which program data+bss is placed
  start_brk     address above which program heap can be expanded with brk()
  arg_start     address above which program command line is placed
  arg_end       address below which program command line is placed
  env_start     address above which program environment is placed
  env_end       address below which program environment is placed
  exit_code     the thread's exit_code in the form reported by the waitpid
		system call
  ============= ===============================================================

The /proc/PID/maps file contains the currently mapped memory regions and
their access permissions.

The format is::

    address           perms offset  dev   inode      pathname

    08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
    08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
    0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
    a7cb1000-a7cb2000 ---p 00000000 00:00 0
    a7cb2000-a7eb2000 rw-p 00000000 00:00 0
    a7eb2000-a7eb3000 ---p 00000000 00:00 0
    a7eb3000-a7ed5000 rw-p 00000000 00:00 0
    a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
    a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
    a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
    a800b000-a800e000 rw-p 00000000 00:00 0
    a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
    a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
    a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
    a8024000-a8027000 rw-p 00000000 00:00 0
    a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
    a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
    a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
    aff35000-aff4a000 rw-p 00000000 00:00 0          [stack]
    ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]

where "address" is the address space in the process that it occupies, "perms"
is a set of permissions::

 r = read
 w = write
 x = execute
 s = shared
 p = private (copy on write)

"offset" is the offset into the mapping, "dev" is the device (major:minor), and
"inode" is the inode  on that device.  0 indicates that  no inode is associated
with the memory region, as the case would be with BSS (uninitialized data).
The "pathname" shows the name associated file for this mapping.  If the mapping
is not associated with a file:

 ===================        ===========================================
 [heap]                     the heap of the program
 [stack]                    the stack of the main process
 [vdso]                     the "virtual dynamic shared object",
                            the kernel system call handler
 [anon:<name>]              a private anonymous mapping that has been
                            named by userspace
 [anon_shmem:<name>]        an anonymous shared memory mapping that has
                            been named by userspace
 ===================        ===========================================

 or if empty, the mapping is anonymous.

Starting with 6.11 kernel, /proc/PID/maps provides an alternative
ioctl()-based API that gives ability to flexibly and efficiently query and
filter individual VMAs. This interface is binary and is meant for more
efficient and easy programmatic use. `struct procmap_query`, defined in
linux/fs.h UAPI header, serves as an input/output argument to the
`PROCMAP_QUERY` ioctl() command. See comments in linus/fs.h UAPI header for
details on query semantics, supported flags, data returned, and general API
usage information.

The /proc/PID/smaps is an extension based on maps, showing the memory
consumption for each of the process's mappings. For each mapping (aka Virtual
Memory Area, or VMA) there is a series of lines such as the following::

    08048000-080bc000 r-xp 00000000 03:02 13130      /bin/bash

    Size:               1084 kB
    KernelPageSize:        4 kB
    MMUPageSize:           4 kB
    Rss:                 892 kB
    Pss:                 374 kB
    Pss_Dirty:             0 kB
    Shared_Clean:        892 kB
    Shared_Dirty:          0 kB
    Private_Clean:         0 kB
    Private_Dirty:         0 kB
    Referenced:          892 kB
    Anonymous:             0 kB
    KSM:                   0 kB
    LazyFree:              0 kB
    AnonHugePages:         0 kB
    FilePmdMapped:         0 kB
    ShmemPmdMapped:        0 kB
    Shared_Hugetlb:        0 kB
    Private_Hugetlb:       0 kB
    Swap:                  0 kB
    SwapPss:               0 kB
    Locked:                0 kB
    THPeligible:           0
    VmFlags: rd ex mr mw me dw

The first of these lines shows the same information as is displayed for
the mapping in /proc/PID/maps.  Following lines show the size of the
mapping (size); the smallest possible page size allocated when backing a
VMA (KernelPageSize), which is the granularity in which VMA modifications
can be performed; the smallest possible page size that could be used by the
MMU (MMUPageSize) when backing a VMA; the amount of the mapping that is
currently resident in RAM (RSS); the process's proportional share of this
mapping (PSS); and the number of clean and dirty shared and private pages
in the mapping.

"KernelPageSize" always corresponds to "MMUPageSize", except when a larger
kernel page size is emulated on a system with a smaller page size used by the
MMU, which is the case for some PPC64 setups with hugetlb.  Furthermore,
"KernelPageSize" and "MMUPageSize" always correspond to the smallest
possible granularity (fallback) that can be encountered in a VMA throughout
its lifetime.  These values are not affected by Transparent Huge Pages
being in effect, or any usage of larger MMU page sizes (either through
architectural huge-page mappings or other explicit/implicit coalescing of
virtual ranges performed by the MMU).  "AnonHugePages", "ShmemPmdMapped" and
"FilePmdMapped" provide insight into the usage of PMD-level architectural
huge-page mappings.

The "proportional set size" (PSS) of a process is the count of pages it has
in memory, where each page is divided by the number of processes sharing it.
So if a process has 1000 pages all to itself, and 1000 shared with one other
process, its PSS will be 1500.  "Pss_Dirty" is the portion of PSS which
consists of dirty pages.  ("Pss_Clean" is not included, but it can be
calculated by subtracting "Pss_Dirty" from "Pss".)

Traditionally, a page is accounted as "private" if it is mapped exactly once,
and a page is accounted as "shared" when mapped multiple times, even when
mapped in the same process multiple times. Note that this accounting is
independent of MAP_SHARED.

In some kernel configurations, the semantics of pages part of a larger
allocation (e.g., THP) can differ: a page is accounted as "private" if all
pages part of the corresponding large allocation are *certainly* mapped in the
same process, even if the page is mapped multiple times in that process. A
page is accounted as "shared" if any page page of the larger allocation
is *maybe* mapped in a different process. In some cases, a large allocation
might be treated as "maybe mapped by multiple processes" even though this
is no longer the case.

Some kernel configurations do not track the precise number of times a page part
of a larger allocation is mapped. In this case, when calculating the PSS, the
average number of mappings per page in this larger allocation might be used
as an approximation for the number of mappings of a page. The PSS calculation
will be imprecise in this case.

"Referenced" indicates the amount of memory currently marked as referenced or
accessed.

"Anonymous" shows the amount of memory that does not belong to any file.  Even
a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
and a page is modified, the file page is replaced by a private anonymous copy.

"KSM" reports how many of the pages are KSM pages. Note that KSM-placed zeropages
are not included, only actual KSM pages.

"LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE).
The memory isn't freed immediately with madvise(). It's freed in memory
pressure if the memory is clean. Please note that the printed value might
be lower than the real value due to optimizations used in the current
implementation. If this is not desirable please file a bug report.

"AnonHugePages", "ShmemPmdMapped" and "FilePmdMapped" show the amount of
memory backed by Transparent Huge Pages that are currently mapped by
architectural huge-page mappings at the PMD level. "AnonHugePages"
corresponds to memory that does not belong to a file, "ShmemPmdMapped" to
shared memory (shmem/tmpfs) and "FilePmdMapped" to file-backed memory
(excluding shmem/tmpfs).

There are no dedicated entries for Transparent Huge Pages (or similar concepts)
that are not mapped by architectural huge-page mappings at the PMD level.

"Shared_Hugetlb" and "Private_Hugetlb" show the amounts of memory backed by
hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.

"Swap" shows how much would-be-anonymous memory is also used, but out on swap.

For shmem mappings, "Swap" includes also the size of the mapped (and not
replaced by copy-on-write) part of the underlying shmem object out on swap.
"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this
does not take into account swapped out page of underlying shmem objects.
"Locked" indicates whether the mapping is locked in memory or not.

"THPeligible" indicates whether the mapping is eligible for allocating
naturally aligned THP pages of any currently enabled size. 1 if true, 0
otherwise.

If both the kernel and the CPU support protection keys (pkeys),
"ProtectionKey" indicates the memory protection key associated with the
virtual memory area.

"VmFlags" field deserves a separate description. This member represents the
kernel flags associated with the particular virtual memory area in two letter
encoded manner. The codes are the following:

    ==    =============================================================
    rd    readable
    wr    writeable
    ex    executable
    sh    shared
    mr    may read
    mw    may write
    me    may execute
    ms    may share
    gd    stack segment growns down
    pf    pure PFN range
    lo    pages are locked in memory
    io    memory mapped I/O area
    sr    sequential read advise provided
    rr    random read advise provided
    dc    do not copy area on fork
    de    do not expand area on remapping
    ac    area is accountable
    nr    swap space is not reserved for the area
    ht    area uses huge tlb pages
    sf    synchronous page fault
    ar    architecture specific flag
    wf    wipe on fork
    dd    do not include area into core dump
    sd    soft dirty flag
    mm    mixed map area
    hg    huge page advise flag
    nh    no huge page advise flag
    mg    mergeable advise flag
    bt    arm64 BTI guarded page
    mt    arm64 MTE allocation tags are enabled
    um    userfaultfd missing tracking
    uw    userfaultfd wr-protect tracking
    ui    userfaultfd minor fault
    ss    shadow/guarded control stack page
    sl    sealed
    lf    lock on fault pages
    dp    always lazily freeable mapping
    gu    maybe contains guard regions (if not set, definitely doesn't)
    ==    =============================================================

Note that there is no guarantee that every flag and associated mnemonic will
be present in all further kernel releases. Things get changed, the flags may
be vanished or the reverse -- new added. Interpretation of their meaning
might change in future as well. So each consumer of these flags has to
follow each specific kernel version for the exact semantic.

This file is only present if the CONFIG_MMU kernel configuration option is
enabled.

Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent
output can be achieved only in the single read call).

This typically manifests when doing partial reads of these files while the
memory map is being modified.  Despite the races, we do provide the following
guarantees:

1) The mapped addresses never go backwards, which implies no two
   regions will ever overlap.
2) If there is something at a given vaddr during the entirety of the
   life of the smaps/maps walk, there will be some output for it.

The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps,
but their values are the sums of the corresponding values for all mappings of
the process.  Additionally, it contains these fields:

- Pss_Anon
- Pss_File
- Pss_Shmem

They represent the proportional shares of anonymous, file, and shmem pages, as
described for smaps above.  These fields are omitted in smaps since each
mapping identifies the type (anon, file, or shmem) of all pages it contains.
Thus all information in smaps_rollup can be derived from smaps, but at a
significantly higher cost.

The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
bits on both physical and virtual pages associated with a process, and the
soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst
for details).
To clear the bits for all the pages associated with the process::

    > echo 1 > /proc/PID/clear_refs

To clear the bits for the anonymous pages associated with the process::

    > echo 2 > /proc/PID/clear_refs

To clear the bits for the file mapped pages associated with the process::

    > echo 3 > /proc/PID/clear_refs

To clear the soft-dirty bit::

    > echo 4 > /proc/PID/clear_refs

To reset the peak resident set size ("high water mark") to the process's
current value::

    > echo 5 > /proc/PID/clear_refs

Any other value written to /proc/PID/clear_refs will have no effect.

The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
using /proc/kpageflags and number of times a page is mapped using
/proc/kpagecount. For detailed explanation, see
Documentation/admin-guide/mm/pagemap.rst.

The /proc/pid/numa_maps is an extension based on maps, showing the memory
locality and binding policy, as well as the memory usage (in pages) of
each mapping. The output follows a general format where mapping details get
summarized separated by blank spaces, one mapping per each file line::

    address   policy    mapping details

    00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
    00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
    3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
    320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
    3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
    3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
    3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
    320698b000 default file=/lib64/libc-2.12.so
    3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
    3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
    3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
    7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
    7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
    7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
    7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
    7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4

Where:

"address" is the starting address for the mapping;

"policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst);

"mapping details" summarizes mapping data such as mapping type, page usage counters,
node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
size, in KB, that is backing the mapping up.

Note that some kernel configurations do not track the precise number of times
a page part of a larger allocation (e.g., THP) is mapped. In these
configurations, "mapmax" might corresponds to the average number of mappings
per page in such a larger allocation instead.

1.2 Kernel data
---------------

Similar to  the  process entries, the kernel data files give information about
the running kernel. The files used to obtain this information are contained in
/proc and  are  listed  in Table 1-5. Not all of these will be present in your
system. It  depends  on the kernel configuration and the loaded modules, which
files are there, and which are missing.

.. table:: Table 1-5: Kernel info in /proc

 ============ ===============================================================
 File         Content
 ============ ===============================================================
 allocinfo    Memory allocations profiling information
 apm          Advanced power management info
 bootconfig   Kernel command line obtained from boot config,
 	      and, if there were kernel parameters from the
	      boot loader, a "# Parameters from bootloader:"
	      line followed by a line containing those
	      parameters prefixed by "# ".			(5.5)
 buddyinfo    Kernel memory allocator information (see text)	(2.5)
 bus          Directory containing bus specific information
 cmdline      Kernel command line, both from bootloader and embedded
              in the kernel image
 cpuinfo      Info about the CPU
 devices      Available devices (block and character)
 dma          Used DMA channels
 filesystems  Supported filesystems
 driver       Various drivers grouped here, currently rtc	(2.4)
 execdomains  Execdomains, related to security			(2.4)
 fb 	      Frame Buffer devices				(2.4)
 fs 	      File system parameters, currently nfs/exports	(2.4)
 ide          Directory containing info about the IDE subsystem
 interrupts   Interrupt usage
 iomem 	      Memory map					(2.4)
 ioports      I/O port usage
 irq 	      Masks for irq to cpu affinity			(2.4)(smp?)
 isapnp       ISA PnP (Plug&Play) Info				(2.4)
 kcore        Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
 kmsg         Kernel messages
 ksyms        Kernel symbol table
 loadavg      Load average of last 1, 5 & 15 minutes;
                number of processes currently runnable (running or on ready queue);
                total number of processes in system;
                last pid created.
                All fields are separated by one space except "number of
                processes currently runnable" and "total number of processes
                in system", which are separated by a slash ('/'). Example:
                0.61 0.61 0.55 3/828 22084
 locks        Kernel locks
 meminfo      Memory info
 misc         Miscellaneous
 modules      List of loaded modules
 mounts       Mounted filesystems
 net          Networking info (see text)
 pagetypeinfo Additional page allocator information (see text)  (2.5)
 partitions   Table of partitions known to the system
 pci 	      Deprecated info of PCI bus (new way -> /proc/bus/pci/,
              decoupled by lspci				(2.4)
 rtc          Real time clock
 scsi         SCSI info (see text)
 slabinfo     Slab pool info
 softirqs     softirq usage
 stat         Overall statistics
 swaps        Swap space utilization
 sys          See chapter 2
 sysvipc      Info of SysVIPC Resources (msg, sem, shm)		(2.4)
 tty 	      Info of tty drivers
 uptime       Wall clock since boot, combined idle time of all cpus
 version      Kernel version
 video 	      bttv info of video resources			(2.4)
 vmallocinfo  Show vmalloced areas
 ============ ===============================================================

You can,  for  example,  check  which interrupts are currently in use and what
they are used for by looking in the file /proc/interrupts::

  > cat /proc/interrupts
             CPU0
    0:    8728810          XT-PIC  timer
    1:        895          XT-PIC  keyboard
    2:          0          XT-PIC  cascade
    3:     531695          XT-PIC  aha152x
    4:    2014133          XT-PIC  serial
    5:      44401          XT-PIC  pcnet_cs
    8:          2          XT-PIC  rtc
   11:          8          XT-PIC  i82365
   12:     182918          XT-PIC  PS/2 Mouse
   13:          1          XT-PIC  fpu
   14:    1232265          XT-PIC  ide0
   15:          7          XT-PIC  ide1
  NMI:          0

In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
output of a SMP machine)::

  > cat /proc/interrupts

             CPU0       CPU1
    0:    1243498    1214548    IO-APIC-edge  timer
    1:       8949       8958    IO-APIC-edge  keyboard
    2:          0          0          XT-PIC  cascade
    5:      11286      10161    IO-APIC-edge  soundblaster
    8:          1          0    IO-APIC-edge  rtc
    9:      27422      27407    IO-APIC-edge  3c503
   12:     113645     113873    IO-APIC-edge  PS/2 Mouse
   13:          0          0          XT-PIC  fpu
   14:      22491      24012    IO-APIC-edge  ide0
   15:       2183       2415    IO-APIC-edge  ide1
   17:      30564      30414   IO-APIC-level  eth0
   18:        177        164   IO-APIC-level  bttv
  NMI:    2457961    2457959
  LOC:    2457882    2457881
  ERR:       2155

NMI is incremented in this case because every timer interrupt generates a NMI
(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.

LOC is the local interrupt counter of the internal APIC of every CPU.

ERR is incremented in the case of errors in the IO-APIC bus (the bus that
connects the CPUs in a SMP system. This means that an error has been detected,
the IO-APIC automatically retry the transmission, so it should not be a big
problem, but you should read the SMP-FAQ.

In 2.6.2* /proc/interrupts was expanded again.  This time the goal was for
/proc/interrupts to display every IRQ vector in use by the system, not
just those considered 'most important'.  The new vectors are:

THR
  interrupt raised when a machine check threshold counter
  (typically counting ECC corrected errors of memory or cache) exceeds
  a configurable threshold.  Only available on some systems.

TRM
  a thermal event interrupt occurs when a temperature threshold
  has been exceeded for the CPU.  This interrupt may also be generated
  when the temperature drops back to normal.

SPU
  a spurious interrupt is some interrupt that was raised then lowered
  by some IO device before it could be fully processed by the APIC.  Hence
  the APIC sees the interrupt but does not know what device it came from.
  For this case the APIC will generate the interrupt with a IRQ vector
  of 0xff. This might also be generated by chipset bugs.

RES, CAL, TLB
  rescheduling, call and TLB flush interrupts are
  sent from one CPU to another per the needs of the OS.  Typically,
  their statistics are used by kernel developers and interested users to
  determine the occurrence of interrupts of the given type.

The above IRQ vectors are displayed only when relevant.  For example,
the threshold vector does not exist on x86_64 platforms.  Others are
suppressed when the system is a uniprocessor.  As of this writing, only
i386 and x86_64 platforms support the new IRQ vector displays.

Of some interest is the introduction of the /proc/irq directory to 2.4.
It could be used to set IRQ to CPU affinity. This means that you can "hook" an
IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
irq subdir is one subdir for each IRQ, and default_smp_affinity.

For example::

  > ls /proc/irq/
  0  10  12  14  16  18  2  4  6  8  default_smp_affinity
  1  11  13  15  17  19  3  5  7  9
  > ls /proc/irq/0/
  smp_affinity

smp_affinity is a bitmask, in which you can specify which CPUs can handle the
IRQ. You can set it by doing::

  > echo 1 > /proc/irq/10/smp_affinity

This means that only the first CPU will handle the IRQ, but you can also echo
5 which means that only the first and third CPU can handle the IRQ.

The contents of each smp_affinity file is the same by default::

  > cat /proc/irq/0/smp_affinity
  ffffffff

There is an alternate interface, smp_affinity_list which allows specifying
a CPU range instead of a bitmask::

  > cat /proc/irq/0/smp_affinity_list
  1024-1031

The default_smp_affinity mask applies to all non-active IRQs, which are the
IRQs which have not yet been allocated/activated, and hence which lack a
/proc/irq/[0-9]* directory.

The node file on an SMP system shows the node to which the device using the IRQ
reports itself as being attached. This hardware locality information does not
include information about any possible driver locality preference.

The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
between all the CPUs which are allowed to handle it. As usual the kernel has
more info than you and does a better job than you, so the defaults are the
best choice for almost everyone.  [Note this applies only to those IO-APIC's
that support "Round Robin" interrupt distribution.]

There are  three  more  important subdirectories in /proc: net, scsi, and sys.
The general  rule  is  that  the  contents,  or  even  the  existence of these
directories, depend  on your kernel configuration. If SCSI is not enabled, the
directory scsi  may  not  exist. The same is true with the net, which is there
only when networking support is present in the running kernel.

The slabinfo  file  gives  information  about  memory usage at the slab level.
Linux uses  slab  pools for memory management above page level in version 2.2.
Commonly used  objects  have  their  own  slab  pool (such as network buffers,
directory cache, and so on).

::

    > cat /proc/buddyinfo

    Node 0, zone      DMA      0      4      5      4      4      3 ...
    Node 0, zone   Normal      1      0      0      1    101      8 ...
    Node 0, zone  HighMem      2      0      0      1      1      0 ...

External fragmentation is a problem under some workloads, and buddyinfo is a
useful tool for helping diagnose these problems.  Buddyinfo will give you a
clue as to how big an area you can safely allocate, or why a previous
allocation failed.

Each column represents the number of pages of a certain order which are
available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
available in ZONE_NORMAL, etc...

More information relevant to external fragmentation can be found in
pagetypeinfo::

    > cat /proc/pagetypeinfo
    Page block order: 9
    Pages per block:  512

    Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
    Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
    Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
    Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
    Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
    Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
    Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
    Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
    Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
    Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
    Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0

    Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
    Node 0, zone      DMA            2            0            5            1            0
    Node 0, zone    DMA32           41            6          967            2            0

Fragmentation avoidance in the kernel works by grouping pages of different
migrate types into the same contiguous regions of memory called page blocks.
A page block is typically the size of the default hugepage size, e.g. 2MB on
X86-64. By keeping pages grouped based on their ability to move, the kernel
can reclaim pages within a page block to satisfy a high-order allocation.

The pagetypinfo begins with information on the size of a page block. It
then gives the same type of information as buddyinfo except broken down
by migrate-type and finishes with details on how many page blocks of each
type exist.

If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can
make an estimate of the likely number of huge pages that can be allocated
at a given point in time. All the "Movable" blocks should be allocatable
unless memory has been mlock()'d. Some of the Reclaimable blocks should
also be allocatable although a lot of filesystem metadata may have to be
reclaimed to achieve this.


allocinfo
~~~~~~~~~

Provides information about memory allocations at all locations in the code
base. Each allocation in the code is identified by its source file, line
number, module (if originates from a loadable module) and the function calling
the allocation. The number of bytes allocated and number of calls at each
location are reported. The first line indicates the version of the file, the
second line is the header listing fields in the file.
If file version is 2.0 or higher then each line may contain additional
<key>:<value> pairs representing extra information about the call site.
For example if the counters are not accurate, the line will be appended with
"accurate:no" pair.

Supported markers in v2:
accurate:no

              Absolute values of the counters in this line are not accurate
              because of the failure to allocate memory to track some of the
              allocations made at this location.  Deltas in these counters are
              accurate, therefore counters can be used to track allocation size
              and count changes.

Example output.

::

    > tail -n +3 /proc/allocinfo | sort -rn
   127664128    31168 mm/page_ext.c:270 func:alloc_page_ext
    56373248     4737 mm/slub.c:2259 func:alloc_slab_page
    14880768     3633 mm/readahead.c:247 func:page_cache_ra_unbounded
    14417920     3520 mm/mm_init.c:2530 func:alloc_large_system_hash
    13377536      234 block/blk-mq.c:3421 func:blk_mq_alloc_rqs
    11718656     2861 mm/filemap.c:1919 func:__filemap_get_folio
     9192960     2800 kernel/fork.c:307 func:alloc_thread_stack_node
     4206592        4 net/netfilter/nf_conntrack_core.c:2567 func:nf_ct_alloc_hashtable
     4136960     1010 drivers/staging/ctagmod/ctagmod.c:20 [ctagmod] func:ctagmod_start
     3940352      962 mm/memory.c:4214 func:alloc_anon_folio
     2894464    22613 fs/kernfs/dir.c:615 func:__kernfs_new_node
     ...


meminfo
~~~~~~~

Provides information about distribution and utilization of memory.  This
varies by architecture and compile options.  Some of the counters reported
here overlap.  The memory reported by the non overlapping counters may not
add up to the overall memory usage and the difference for some workloads
can be substantial.  In many cases there are other means to find out
additional memory using subsystem specific interfaces, for instance
/proc/net/sockstat for TCP memory allocations.

Example output. You may not have all of these fields.

::

    > cat /proc/meminfo

    MemTotal:       32858820 kB
    MemFree:        21001236 kB
    MemAvailable:   27214312 kB
    Buffers:          581092 kB
    Cached:          5587612 kB
    SwapCached:            0 kB
    Active:          3237152 kB
    Inactive:        7586256 kB
    Active(anon):      94064 kB
    Inactive(anon):  4570616 kB
    Active(file):    3143088 kB
    Inactive(file):  3015640 kB
    Unevictable:           0 kB
    Mlocked:               0 kB
    SwapTotal:             0 kB
    SwapFree:              0 kB
    Zswap:              1904 kB
    Zswapped:           7792 kB
    Dirty:                12 kB
    Writeback:             0 kB
    AnonPages:       4654780 kB
    Mapped:           266244 kB
    Shmem:              9976 kB
    KReclaimable:     517708 kB
    Slab:             660044 kB
    SReclaimable:     517708 kB
    SUnreclaim:       142336 kB
    KernelStack:       11168 kB
    PageTables:        20540 kB
    SecPageTables:         0 kB
    NFS_Unstable:          0 kB
    Bounce:                0 kB
    WritebackTmp:          0 kB
    CommitLimit:    16429408 kB
    Committed_AS:    7715148 kB
    VmallocTotal:   34359738367 kB
    VmallocUsed:       40444 kB
    VmallocChunk:          0 kB
    Percpu:            29312 kB
    EarlyMemtestBad:       0 kB
    HardwareCorrupted:     0 kB
    AnonHugePages:   4149248 kB
    ShmemHugePages:        0 kB
    ShmemPmdMapped:        0 kB
    FileHugePages:         0 kB
    FilePmdMapped:         0 kB
    CmaTotal:              0 kB
    CmaFree:               0 kB
    Unaccepted:            0 kB
    Balloon:               0 kB
    GPUActive:             0 kB
    GPUReclaim:            0 kB
    HugePages_Total:       0
    HugePages_Free:        0
    HugePages_Rsvd:        0
    HugePages_Surp:        0
    Hugepagesize:       2048 kB
    Hugetlb:               0 kB
    DirectMap4k:      401152 kB
    DirectMap2M:    10008576 kB
    DirectMap1G:    24117248 kB

MemTotal
              Total usable RAM (i.e. physical RAM minus a few reserved
              bits and the kernel binary code)
MemFree
              Total free RAM. On highmem systems, the sum of LowFree+HighFree
MemAvailable
              An estimate of how much memory is available for starting new
              applications, without swapping. Calculated from MemFree,
              SReclaimable, the size of the file LRU lists, and the low
              watermarks in each zone.
              The estimate takes into account that the system needs some
              page cache to function well, and that not all reclaimable
              slab will be reclaimable, due to items being in use. The
              impact of those factors will vary from system to system.
Buffers
              Relatively temporary storage for raw disk blocks
              shouldn't get tremendously large (20MB or so)
Cached
              In-memory cache for files read from the disk (the
              pagecache) as well as tmpfs & shmem.
              Doesn't include SwapCached.
SwapCached
              Memory that once was swapped out, is swapped back in but
              still also is in the swapfile (if memory is needed it
              doesn't need to be swapped out AGAIN because it is already
              in the swapfile. This saves I/O)
Active
              Memory that has been used more recently and usually not
              reclaimed unless absolutely necessary.
Inactive
              Memory which has been less recently used.  It is more
              eligible to be reclaimed for other purposes
Unevictable
              Memory allocated for userspace which cannot be reclaimed, such
              as mlocked pages, ramfs backing pages, secret memfd pages etc.
Mlocked
              Memory locked with mlock().
HighTotal, HighFree
              Highmem is all memory above ~860MB of physical memory.
              Highmem areas are for use by userspace programs, or
              for the pagecache.  The kernel must use tricks to access
              this memory, making it slower to access than lowmem.
LowTotal, LowFree
              Lowmem is memory which can be used for everything that
              highmem can be used for, but it is also available for the
              kernel's use for its own data structures.  Among many
              other things, it is where everything from the Slab is
              allocated.  Bad things happen when you're out of lowmem.
SwapTotal
              total amount of swap space available
SwapFree
              Memory which has been evicted from RAM, and is temporarily
              on the disk
Zswap
              Memory consumed by the zswap backend (compressed size)
Zswapped
              Amount of anonymous memory stored in zswap (original size)
Dirty
              Memory which is waiting to get written back to the disk
Writeback
              Memory which is actively being written back to the disk
AnonPages
              Non-file backed pages mapped into userspace page tables. Note that
              some kernel configurations might consider all pages part of a
              larger allocation (e.g., THP) as "mapped", as soon as a single
              page is mapped.
Mapped
              files which have been mmapped, such as libraries. Note that some
              kernel configurations might consider all pages part of a larger
              allocation (e.g., THP) as "mapped", as soon as a single page is
              mapped.
Shmem
              Total memory used by shared memory (shmem) and tmpfs
KReclaimable
              Kernel allocations that the kernel will attempt to reclaim
              under memory pressure. Includes SReclaimable (below), and other
              direct allocations with a shrinker.
Slab
              in-kernel data structures cache
SReclaimable
              Part of Slab, that might be reclaimed, such as caches
SUnreclaim
              Part of Slab, that cannot be reclaimed on memory pressure
KernelStack
              Memory consumed by the kernel stacks of all tasks
PageTables
              Memory consumed by userspace page tables
SecPageTables
              Memory consumed by secondary page tables, this currently includes
              KVM mmu and IOMMU allocations on x86 and arm64.
NFS_Unstable
              Always zero. Previously counted pages which had been written to
              the server, but has not been committed to stable storage.
Bounce
              Always zero. Previously memory used for block device
              "bounce buffers".
WritebackTmp
              Always zero. Previously memory used by FUSE for temporary
              writeback buffers.
CommitLimit
              Based on the overcommit ratio ('vm.overcommit_ratio'),
              this is the total amount of  memory currently available to
              be allocated on the system. This limit is only adhered to
              if strict overcommit accounting is enabled (mode 2 in
              'vm.overcommit_memory').

              The CommitLimit is calculated with the following formula::

                CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
                               overcommit_ratio / 100 + [total swap pages]

              For example, on a system with 1G of physical RAM and 7G
              of swap with a `vm.overcommit_ratio` of 30 it would
              yield a CommitLimit of 7.3G.

              For more details, see the memory overcommit documentation
              in mm/overcommit-accounting.
Committed_AS
              The amount of memory presently allocated on the system.
              The committed memory is a sum of all of the memory which
              has been allocated by processes, even if it has not been
              "used" by them as of yet. A process which malloc()'s 1G
              of memory, but only touches 300M of it will show up as
              using 1G. This 1G is memory which has been "committed" to
              by the VM and can be used at any time by the allocating
              application. With strict overcommit enabled on the system
              (mode 2 in 'vm.overcommit_memory'), allocations which would
              exceed the CommitLimit (detailed above) will not be permitted.
              This is useful if one needs to guarantee that processes will
              not fail due to lack of memory once that memory has been
              successfully allocated.
VmallocTotal
              total size of vmalloc virtual address space
VmallocUsed
              amount of vmalloc area which is used
VmallocChunk
              largest contiguous block of vmalloc area which is free
Percpu
              Memory allocated to the percpu allocator used to back percpu
              allocations. This stat excludes the cost of metadata.
EarlyMemtestBad
              The amount of RAM/memory in kB, that was identified as corrupted
              by early memtest. If memtest was not run, this field will not
              be displayed at all. Size is never rounded down to 0 kB.
              That means if 0 kB is reported, you can safely assume
              there was at least one pass of memtest and none of the passes
              found a single faulty byte of RAM.
HardwareCorrupted
              The amount of RAM/memory in KB, the kernel identifies as
              corrupted.
AnonHugePages
              Non-file backed huge pages mapped into userspace page tables
ShmemHugePages
              Memory used by shared memory (shmem) and tmpfs allocated
              with huge pages
ShmemPmdMapped
              Shared memory mapped into userspace with huge pages
FileHugePages
              Memory used for filesystem data (page cache) allocated
              with huge pages
FilePmdMapped
              Page cache mapped into userspace with huge pages
CmaTotal
              Memory reserved for the Contiguous Memory Allocator (CMA)
CmaFree
              Free remaining memory in the CMA reserves
Unaccepted
              Memory that has not been accepted by the guest
Balloon
              Memory returned to Host by VM Balloon Drivers
GPUActive
              System memory allocated to active GPU objects
GPUReclaim
              System memory stored in GPU pools for reuse. This memory is not
              counted in GPUActive. It is shrinker reclaimable memory kept in a reuse
              pool because it has non-standard page table attributes, like WC or UC.
HugePages_Total, HugePages_Free, HugePages_Rsvd, HugePages_Surp, Hugepagesize, Hugetlb
              See Documentation/admin-guide/mm/hugetlbpage.rst.
DirectMap4k, DirectMap2M, DirectMap1G
              Breakdown of page table sizes used in the kernel's
              identity mapping of RAM

vmallocinfo
~~~~~~~~~~~

Provides information about vmalloced/vmaped areas. One line per area,
containing the virtual address range of the area, size in bytes,
caller information of the creator, and optional information depending
on the kind of area:

 ==========  ===================================================
 pages=nr    number of pages
 phys=addr   if a physical address was specified
 ioremap     I/O mapping (ioremap() and friends)
 vmalloc     vmalloc() area
 vmap        vmap()ed pages
 user        VM_USERMAP area
 vpages      buffer for pages pointers was vmalloced (huge area)
 N<node>=nr  (Only on NUMA kernels)
             Number of pages allocated on memory node <node>
 ==========  ===================================================

::

    > cat /proc/vmallocinfo
    0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
    /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
    0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
    /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
    0xffffc20000302000-0xffffc20000304000    8192 acpi_tb_verify_table+0x21/0x4f...
    phys=7fee8000 ioremap
    0xffffc20000304000-0xffffc20000307000   12288 acpi_tb_verify_table+0x21/0x4f...
    phys=7fee7000 ioremap
    0xffffc2000031d000-0xffffc2000031f000    8192 init_vdso_vars+0x112/0x210
    0xffffc2000031f000-0xffffc2000032b000   49152 cramfs_uncompress_init+0x2e ...
    /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
    0xffffc2000033a000-0xffffc2000033d000   12288 sys_swapon+0x640/0xac0      ...
    pages=2 vmalloc N1=2
    0xffffc20000347000-0xffffc2000034c000   20480 xt_alloc_table_info+0xfe ...
    /0x130 [x_tables] pages=4 vmalloc N0=4
    0xffffffffa0000000-0xffffffffa000f000   61440 sys_init_module+0xc27/0x1d00 ...
    pages=14 vmalloc N2=14
    0xffffffffa000f000-0xffffffffa0014000   20480 sys_init_module+0xc27/0x1d00 ...
    pages=4 vmalloc N1=4
    0xffffffffa0014000-0xffffffffa0017000   12288 sys_init_module+0xc27/0x1d00 ...
    pages=2 vmalloc N1=2
    0xffffffffa0017000-0xffffffffa0022000   45056 sys_init_module+0xc27/0x1d00 ...
    pages=10 vmalloc N0=10


softirqs
~~~~~~~~

Provides counts of softirq handlers serviced since boot time, for each CPU.

::

    > cat /proc/softirqs
		  CPU0       CPU1       CPU2       CPU3
	HI:          0          0          0          0
    TIMER:       27166      27120      27097      27034
    NET_TX:          0          0          0         17
    NET_RX:         42          0          0         39
    BLOCK:           0          0        107       1121
    TASKLET:         0          0          0        290
    SCHED:       27035      26983      26971      26746
    HRTIMER:         0          0          0          0
	RCU:      1678       1769       2178       2250

1.3 Networking info in /proc/net
--------------------------------

The subdirectory  /proc/net  follows  the  usual  pattern. Table 1-8 shows the
additional values  you  get  for  IP  version 6 if you configure the kernel to
support this. Table 1-9 lists the files and their meaning.


.. table:: Table 1-8: IPv6 info in /proc/net

 ========== =====================================================
 File       Content
 ========== =====================================================
 udp6       UDP sockets (IPv6)
 tcp6       TCP sockets (IPv6)
 raw6       Raw device statistics (IPv6)
 igmp6      IP multicast addresses, which this host joined (IPv6)
 if_inet6   List of IPv6 interface addresses
 ipv6_route Kernel routing table for IPv6
 rt6_stats  Global IPv6 routing tables statistics
 sockstat6  Socket statistics (IPv6)
 snmp6      Snmp data (IPv6)
 ========== =====================================================

.. table:: Table 1-9: Network info in /proc/net

 ============= ================================================================
 File          Content
 ============= ================================================================
 arp           Kernel  ARP table
 dev           network devices with statistics
 dev_mcast     the Layer2 multicast groups a device is listening too
               (interface index, label, number of references, number of bound
               addresses).
 dev_stat      network device status
 ip_fwchains   Firewall chain linkage
 ip_fwnames    Firewall chain names
 ip_masq       Directory containing the masquerading tables
 ip_masquerade Major masquerading table
 netstat       Network statistics
 raw           raw device statistics
 route         Kernel routing table
 rpc           Directory containing rpc info
 rt_cache      Routing cache
 snmp          SNMP data
 sockstat      Socket statistics
 softnet_stat  Per-CPU incoming packets queues statistics of online CPUs
 tcp           TCP  sockets
 udp           UDP sockets
 unix          UNIX domain sockets
 wireless      Wireless interface data (Wavelan etc)
 igmp          IP multicast addresses, which this host joined
 psched        Global packet scheduler parameters.
 netlink       List of PF_NETLINK sockets
 ip_mr_vifs    List of multicast virtual interfaces
 ip_mr_cache   List of multicast routing cache
 ============= ================================================================

You can  use  this  information  to see which network devices are available in
your system and how much traffic was routed over those devices::

  > cat /proc/net/dev
  Inter-|Receive                                                   |[...
   face |bytes    packets errs drop fifo frame compressed multicast|[...
      lo:  908188   5596     0    0    0     0          0         0 [...
    ppp0:15475140  20721   410    0    0   410          0         0 [...
    eth0:  614530   7085     0    0    0     0          0         1 [...

  ...] Transmit
  ...] bytes    packets errs drop fifo colls carrier compressed
  ...]  908188     5596    0    0    0     0       0          0
  ...] 1375103    17405    0    0    0     0       0          0
  ...] 1703981     5535    0    0    0     3       0          0

In addition, each Channel Bond interface has its own directory.  For
example, the bond0 device will have a directory called /proc/net/bond0/.
It will contain information that is specific to that bond, such as the
current slaves of the bond, the link status of the slaves, and how
many times the slaves link has failed.

1.4 SCSI info
-------------

If you have a SCSI or ATA host adapter in your system, you'll find a
subdirectory named after the driver for this adapter in /proc/scsi.
You'll also see a list of all recognized SCSI devices in /proc/scsi::

  >cat /proc/scsi/scsi
  Attached devices:
  Host: scsi0 Channel: 00 Id: 00 Lun: 00
    Vendor: IBM      Model: DGHS09U          Rev: 03E0
    Type:   Direct-Access                    ANSI SCSI revision: 03
  Host: scsi0 Channel: 00 Id: 06 Lun: 00
    Vendor: PIONEER  Model: CD-ROM DR-U06S   Rev: 1.04
    Type:   CD-ROM                           ANSI SCSI revision: 02


The directory  named  after  the driver has one file for each adapter found in
the system.  These  files  contain information about the controller, including
the used  IRQ  and  the  IO  address range. The amount of information shown is
dependent on  the adapter you use. The example shows the output for an Adaptec
AHA-2940 SCSI adapter::

  > cat /proc/scsi/aic7xxx/0

  Adaptec AIC7xxx driver version: 5.1.19/3.2.4
  Compile Options:
    TCQ Enabled By Default : Disabled
    AIC7XXX_PROC_STATS     : Disabled
    AIC7XXX_RESET_DELAY    : 5
  Adapter Configuration:
             SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
                             Ultra Wide Controller
      PCI MMAPed I/O Base: 0xeb001000
   Adapter SEEPROM Config: SEEPROM found and used.
        Adaptec SCSI BIOS: Enabled
                      IRQ: 10
                     SCBs: Active 0, Max Active 2,
                           Allocated 15, HW 16, Page 255
               Interrupts: 160328
        BIOS Control Word: 0x18b6
     Adapter Control Word: 0x005b
     Extended Translation: Enabled
  Disconnect Enable Flags: 0xffff
       Ultra Enable Flags: 0x0001
   Tag Queue Enable Flags: 0x0000
  Ordered Queue Tag Flags: 0x0000
  Default Tag Queue Depth: 8
      Tagged Queue By Device array for aic7xxx host instance 0:
        {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
      Actual queue depth per device for aic7xxx host instance 0:
        {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
  Statistics:
  (scsi0:0:0:0)
    Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
    Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
    Total transfers 160151 (74577 reads and 85574 writes)
  (scsi0:0:6:0)
    Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
    Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
    Total transfers 0 (0 reads and 0 writes)


1.5 Parallel port info in /proc/parport
---------------------------------------

The directory  /proc/parport  contains information about the parallel ports of
your system.  It  has  one  subdirectory  for  each port, named after the port
number (0,1,2,...).

These directories contain the four files shown in Table 1-10.


.. table:: Table 1-10: Files in /proc/parport

 ========= ====================================================================
 File      Content
 ========= ====================================================================
 autoprobe Any IEEE-1284 device ID information that has been acquired.
 devices   list of the device drivers using that port. A + will appear by the
           name of the device currently using the port (it might not appear
           against any).
 hardware  Parallel port's base address, IRQ line and DMA channel.
 irq       IRQ that parport is using for that port. This is in a separate
           file to allow you to alter it by writing a new value in (IRQ
           number or none).
 ========= ====================================================================

1.6 TTY info in /proc/tty
-------------------------

Information about  the  available  and actually used tty's can be found in the
directory /proc/tty. You'll find  entries  for drivers and line disciplines in
this directory, as shown in Table 1-11.


.. table:: Table 1-11: Files in /proc/tty

 ============= ==============================================
 File          Content
 ============= ==============================================
 drivers       list of drivers and their usage
 ldiscs        registered line disciplines
 driver/serial usage statistic and status of single tty lines
 ============= ==============================================

To see  which  tty's  are  currently in use, you can simply look into the file
/proc/tty/drivers::

  > cat /proc/tty/drivers
  pty_slave            /dev/pts      136   0-255 pty:slave
  pty_master           /dev/ptm      128   0-255 pty:master
  pty_slave            /dev/ttyp       3   0-255 pty:slave
  pty_master           /dev/pty        2   0-255 pty:master
  serial               /dev/cua        5   64-67 serial:callout
  serial               /dev/ttyS       4   64-67 serial
  /dev/tty0            /dev/tty0       4       0 system:vtmaster
  /dev/ptmx            /dev/ptmx       5       2 system
  /dev/console         /dev/console    5       1 system:console
  /dev/tty             /dev/tty        5       0 system:/dev/tty
  unknown              /dev/tty        4    1-63 console


1.7 Miscellaneous kernel statistics in /proc/stat
-------------------------------------------------

Various pieces   of  information about  kernel activity  are  available in the
/proc/stat file.  All  of  the numbers reported  in  this file are  aggregates
since the system first booted.  For a quick look, simply cat the file::

  > cat /proc/stat
  cpu  237902850 368826709 106375398 1873517540 1135548 0 14507935 0 0 0
  cpu0 60045249 91891769 26331539 468411416 495718 0 5739640 0 0 0
  cpu1 59746288 91759249 26609887 468860630 312281 0 4384817 0 0 0
  cpu2 59489247 92985423 26904446 467808813 171668 0 2268998 0 0 0
  cpu3 58622065 92190267 26529524 468436680 155879 0 2114478 0 0 0
  intr 8688370575 8 3373 0 0 0 0 0 0 1 40791 0 0 353317 0 0 0 0 224789828 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 190974333 41958554 123983334 43 0 224593 0 0 0 <more 0's deleted>
  ctxt 22848221062
  btime 1605316999
  processes 746787147
  procs_running 2
  procs_blocked 0
  softirq 12121874454 100099120 3938138295 127375644 2795979 187870761 0 173808342 3072582055 52608 224184354

The very first  "cpu" line aggregates the  numbers in all  of the other "cpuN"
lines.  These numbers identify the amount of time the CPU has spent performing
different kinds of work.  Time units are in USER_HZ (typically hundredths of a
second).  The meanings of the columns are as follows, from left to right:

- user: normal processes executing in user mode
- nice: niced processes executing in user mode
- system: processes executing in kernel mode
- idle: twiddling thumbs
- iowait: In a word, iowait stands for waiting for I/O to complete. But there
  are several problems:

  1. CPU will not wait for I/O to complete, iowait is the time that a task is
     waiting for I/O to complete. When CPU goes into idle state for
     outstanding task I/O, another task will be scheduled on this CPU.
  2. In a multi-core CPU, the task waiting for I/O to complete is not running
     on any CPU, so the iowait of each CPU is difficult to calculate.
  3. The value of iowait field in /proc/stat will decrease in certain
     conditions.

  So, the iowait is not reliable by reading from /proc/stat.
- irq: servicing interrupts
- softirq: servicing softirqs
- steal: involuntary wait
- guest: running a normal guest
- guest_nice: running a niced guest

The "intr" line gives counts of interrupts  serviced since boot time, for each
of the  possible system interrupts.   The first  column  is the  total of  all
interrupts serviced  including  unnumbered  architecture specific  interrupts;
each  subsequent column is the  total for that particular numbered interrupt.
Unnumbered interrupts are not shown, only summed into the total.

The "ctxt" line gives the total number of context switches across all CPUs.

The "btime" line gives  the time at which the  system booted, in seconds since
the Unix epoch.

The "processes" line gives the number  of processes and threads created, which
includes (but  is not limited  to) those  created by  calls to the  fork() and
clone() system calls.

The "procs_running" line gives the total number of threads that are
running or ready to run (i.e., the total number of runnable threads).

The   "procs_blocked" line gives  the  number of  processes currently blocked,
waiting for I/O to complete.

The "softirq" line gives counts of softirqs serviced since boot time, for each
of the possible system softirqs. The first column is the total of all
softirqs serviced; each subsequent column is the total for that particular
softirq.


1.8 Ext4 file system parameters
-------------------------------

Information about mounted ext4 file systems can be found in
/proc/fs/ext4.  Each mounted filesystem will have a directory in
/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
/proc/fs/ext4/sda9 or /proc/fs/ext4/dm-0).   The files in each per-device
directory are shown in Table 1-12, below.

.. table:: Table 1-12: Files in /proc/fs/ext4/<devname>

 ==============  ==========================================================
 File            Content
 mb_groups       details of multiblock allocator buddy cache of free blocks
 ==============  ==========================================================

1.9 /proc/consoles
-------------------
Shows registered system console lines.

To see which character device lines are currently used for the system console
/dev/console, you may simply look into the file /proc/consoles::

  > cat /proc/consoles
  tty0                 -WU (ECp)       4:7
  ttyS0                -W- (Ep)        4:64

The columns are:

+--------------------+-------------------------------------------------------+
| device             | name of the device                                    |
+====================+=======================================================+
| operations         | * R = can do read operations                          |
|                    | * W = can do write operations                         |
|                    | * U = can do unblank                                  |
+--------------------+-------------------------------------------------------+
| flags              | * E = it is enabled                                   |
|                    | * C = it is preferred console                         |
|                    | * B = it is primary boot console                      |
|                    | * p = it is used for printk buffer                    |
|                    | * b = it is not a TTY but a Braille device            |
|                    | * a = it is safe to use when cpu is offline           |
+--------------------+-------------------------------------------------------+
| major:minor        | major and minor number of the device separated by a   |
|                    | colon                                                 |
+--------------------+-------------------------------------------------------+

Summary
-------

The /proc file system serves information about the running system. It not only
allows access to process data but also allows you to request the kernel status
by reading files in the hierarchy.

The directory  structure  of /proc reflects the types of information and makes
it easy, if not obvious, where to look for specific data.

Chapter 2: Modifying System Parameters
======================================

In This Chapter
---------------

* Modifying kernel parameters by writing into files found in /proc/sys
* Exploring the files which modify certain parameters
* Review of the /proc/sys file tree

------------------------------------------------------------------------------

A very  interesting part of /proc is the directory /proc/sys. This is not only
a source  of  information,  it also allows you to change parameters within the
kernel. Be  very  careful  when attempting this. You can optimize your system,
but you  can  also  cause  it  to  crash.  Never  alter kernel parameters on a
production system.  Set  up  a  development machine and test to make sure that
everything works  the  way  you want it to. You may have no alternative but to
reboot the machine once an error has been made.

To change  a  value,  simply  echo  the new value into the file.
You need to be root to do this. You  can  create  your  own  boot script
to perform this every time your system boots.

The files  in /proc/sys can be used to fine tune and monitor miscellaneous and
general things  in  the operation of the Linux kernel. Since some of the files
can inadvertently  disrupt  your  system,  it  is  advisable  to  read  both
documentation and  source  before actually making adjustments. In any case, be
very careful  when  writing  to  any  of these files. The entries in /proc may
change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
review the kernel documentation in the directory linux/Documentation.
This chapter  is  heavily  based  on the documentation included in the pre 2.2
kernels, and became part of it in version 2.2.1 of the Linux kernel.

Please see: Documentation/admin-guide/sysctl/ directory for descriptions of
these entries.

Summary
-------

Certain aspects  of  kernel  behavior  can be modified at runtime, without the
need to  recompile  the kernel, or even to reboot the system. The files in the
/proc/sys tree  can  not only be read, but also modified. You can use the echo
command to write value into these files, thereby changing the default settings
of the kernel.


Chapter 3: Per-process Parameters
=================================

3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
--------------------------------------------------------------------------------

These files can be used to adjust the badness heuristic used to select which
process gets killed in out of memory (oom) conditions.

The badness heuristic assigns a value to each candidate task ranging from 0
(never kill) to 1000 (always kill) to determine which process is targeted.  The
units are roughly a proportion along that range of allowed memory the process
may allocate from based on an estimation of its current memory and swap use.
For example, if a task is using all allowed memory, its badness score will be
1000.  If it is using half of its allowed memory, its score will be 500.

The amount of "allowed" memory depends on the context in which the oom killer
was called.  If it is due to the memory assigned to the allocating task's cpuset
being exhausted, the allowed memory represents the set of mems assigned to that
cpuset.  If it is due to a mempolicy's node(s) being exhausted, the allowed
memory represents the set of mempolicy nodes.  If it is due to a memory
limit (or swap limit) being reached, the allowed memory is that configured
limit.  Finally, if it is due to the entire system being out of memory, the
allowed memory represents all allocatable resources.

The value of /proc/<pid>/oom_score_adj is added to the badness score before it
is used to determine which task to kill.  Acceptable values range from -1000
(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX).  This allows userspace to
polarize the preference for oom killing either by always preferring a certain
task or completely disabling it.  The lowest possible value, -1000, is
equivalent to disabling oom killing entirely for that task since it will always
report a badness score of 0.

Consequently, it is very simple for userspace to define the amount of memory to
consider for each task.  Setting a /proc/<pid>/oom_score_adj value of +500, for
example, is roughly equivalent to allowing the remainder of tasks sharing the
same system, cpuset, mempolicy, or memory controller resources to use at least
50% more memory.  A value of -500, on the other hand, would be roughly
equivalent to discounting 50% of the task's allowed memory from being considered
as scoring against the task.

For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
be used to tune the badness score.  Its acceptable values range from -16
(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
(OOM_DISABLE) to disable oom killing entirely for that task.  Its value is
scaled linearly with /proc/<pid>/oom_score_adj.

The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
requires CAP_SYS_RESOURCE.


3.2 /proc/<pid>/oom_score - Display current oom-killer score
-------------------------------------------------------------

This file can be used to check the current score used by the oom-killer for
any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
process should be killed in an out-of-memory situation.

Please note that the exported value includes oom_score_adj so it is
effectively in range [0,2000].


3.3  /proc/<pid>/io - Display the IO accounting fields
-------------------------------------------------------

This file contains IO statistics for each running process.

Example
~~~~~~~

::

    test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
    [1] 3828

    test:/tmp # cat /proc/3828/io
    rchar: 323934931
    wchar: 323929600
    syscr: 632687
    syscw: 632675
    read_bytes: 0
    write_bytes: 323932160
    cancelled_write_bytes: 0


Description
~~~~~~~~~~~

rchar
^^^^^

I/O counter: chars read
The number of bytes which this task has caused to be read from storage. This
is simply the sum of bytes which this process passed to read() and pread().
It includes things like tty IO and it is unaffected by whether or not actual
physical disk IO was required (the read might have been satisfied from
pagecache).


wchar
^^^^^

I/O counter: chars written
The number of bytes which this task has caused, or shall cause to be written
to disk. Similar caveats apply here as with rchar.


syscr
^^^^^

I/O counter: read syscalls
Attempt to count the number of read I/O operations, i.e. syscalls like read()
and pread().


syscw
^^^^^

I/O counter: write syscalls
Attempt to count the number of write I/O operations, i.e. syscalls like
write() and pwrite().


read_bytes
^^^^^^^^^^

I/O counter: bytes read
Attempt to count the number of bytes which this process really did cause to
be fetched from the storage layer. Done at the submit_bio() level, so it is
accurate for block-backed filesystems. <please add status regarding NFS and
CIFS at a later time>


write_bytes
^^^^^^^^^^^

I/O counter: bytes written
Attempt to count the number of bytes which this process caused to be sent to
the storage layer. This is done at page-dirtying time.


cancelled_write_bytes
^^^^^^^^^^^^^^^^^^^^^

The big inaccuracy here is truncate. If a process writes 1MB to a file and
then deletes the file, it will in fact perform no writeout. But it will have
been accounted as having caused 1MB of write.
In other words: The number of bytes which this process caused to not happen,
by truncating pagecache. A task can cause "negative" IO too. If this task
truncates some dirty pagecache, some IO which another task has been accounted
for (in its write_bytes) will not be happening. We _could_ just subtract that
from the truncating task's write_bytes, but there is information loss in doing
that.


.. Note::

   At its current implementation state, this is a bit racy on 32-bit machines:
   if process A reads process B's /proc/pid/io while process B is updating one
   of those 64-bit counters, process A could see an intermediate result.


More information about this can be found within the taskstats documentation in
Documentation/accounting.

3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
---------------------------------------------------------------
When a process is dumped, all anonymous memory is written to a core file as
long as the size of the core file isn't limited. But sometimes we don't want
to dump some memory segments, for example, huge shared memory or DAX.
Conversely, sometimes we want to save file-backed memory segments into a core
file, not only the individual files.

/proc/<pid>/coredump_filter allows you to customize which memory segments
will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
of memory types. If a bit of the bitmask is set, memory segments of the
corresponding memory type are dumped, otherwise they are not dumped.

The following 9 memory types are supported:

  - (bit 0) anonymous private memory
  - (bit 1) anonymous shared memory
  - (bit 2) file-backed private memory
  - (bit 3) file-backed shared memory
  - (bit 4) ELF header pages in file-backed private memory areas (it is
    effective only if the bit 2 is cleared)
  - (bit 5) hugetlb private memory
  - (bit 6) hugetlb shared memory
  - (bit 7) DAX private memory
  - (bit 8) DAX shared memory

  Note that MMIO pages such as frame buffer are never dumped and vDSO pages
  are always dumped regardless of the bitmask status.

  Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is
  only affected by bit 5-6, and DAX is only affected by bits 7-8.

The default value of coredump_filter is 0x33; this means all anonymous memory
segments, ELF header pages and hugetlb private memory are dumped.

If you don't want to dump all shared memory segments attached to pid 1234,
write 0x31 to the process's proc file::

  $ echo 0x31 > /proc/1234/coredump_filter

When a new process is created, the process inherits the bitmask status from its
parent. It is useful to set up coredump_filter before the program runs.
For example::

  $ echo 0x7 > /proc/self/coredump_filter
  $ ./some_program

3.5	/proc/<pid>/mountinfo - Information about mounts
--------------------------------------------------------

This file contains lines of the form::

    36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
    (1)(2)(3)   (4)   (5)      (6)     (n…m) (m+1)(m+2) (m+3)         (m+4)

    (1)   mount ID:        unique identifier of the mount (may be reused after umount)
    (2)   parent ID:       ID of parent (or of self for the top of the mount tree)
    (3)   major:minor:     value of st_dev for files on filesystem
    (4)   root:            root of the mount within the filesystem
    (5)   mount point:     mount point relative to the process's root
    (6)   mount options:   per mount options
    (n…m) optional fields: zero or more fields of the form "tag[:value]"
    (m+1) separator:       marks the end of the optional fields
    (m+2) filesystem type: name of filesystem of the form "type[.subtype]"
    (m+3) mount source:    filesystem specific information or "none"
    (m+4) super options:   per super block options

Parsers should ignore all unrecognised optional fields.  Currently the
possible optional fields are:

================  ==============================================================
shared:X          mount is shared in peer group X
master:X          mount is slave to peer group X
propagate_from:X  mount is slave and receives propagation from peer group X [#]_
unbindable        mount is unbindable
================  ==============================================================

.. [#] X is the closest dominant peer group under the process's root.  If
       X is the immediate master of the mount, or if there's no dominant peer
       group under the same root, then only the "master:X" field is present
       and not the "propagate_from:X" field.

For more information on mount propagation see:

  Documentation/filesystems/sharedsubtree.rst


3.6	/proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
--------------------------------------------------------
These files provide a method to access a task's comm value. It also allows for
a task to set its own or one of its thread siblings comm value. The comm value
is limited in size compared to the cmdline value, so writing anything longer
then the kernel's TASK_COMM_LEN (currently 16 chars, including the NUL
terminator) will result in a truncated comm value.


3.7	/proc/<pid>/task/<tid>/children - Information about task children
-------------------------------------------------------------------------
This file provides a fast way to retrieve first level children pids
of a task pointed by <pid>/<tid> pair. The format is a space separated
stream of pids.

Note the "first level" here -- if a child has its own children they will
not be listed here; one needs to read /proc/<children-pid>/task/<tid>/children
to obtain the descendants.

Since this interface is intended to be fast and cheap it doesn't
guarantee to provide precise results and some children might be
skipped, especially if they've exited right after we printed their
pids, so one needs to either stop or freeze processes being inspected
if precise results are needed.


3.8	/proc/<pid>/fdinfo/<fd> - Information about opened file
---------------------------------------------------------------
This file provides information associated with an opened file. The regular
files have at least four fields -- 'pos', 'flags', 'mnt_id' and 'ino'.
The 'pos' represents the current offset of the opened file in decimal
form [see lseek(2) for details], 'flags' denotes the octal O_xxx mask the
file has been created with [see open(2) for details] and 'mnt_id' represents
mount ID of the file system containing the opened file [see 3.5
/proc/<pid>/mountinfo for details]. 'ino' represents the inode number of
the file.

A typical output is::

	pos:	0
	flags:	0100002
	mnt_id:	19
	ino:	63107

All locks associated with a file descriptor are shown in its fdinfo too::

    lock:       1: FLOCK  ADVISORY  WRITE 359 00:13:11691 0 EOF

The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
pair provide additional information particular to the objects they represent.

Eventfd files
~~~~~~~~~~~~~

::

	pos:	0
	flags:	04002
	mnt_id:	9
	ino:	63107
	eventfd-count:	5a

where 'eventfd-count' is hex value of a counter.

Signalfd files
~~~~~~~~~~~~~~

::

	pos:	0
	flags:	04002
	mnt_id:	9
	ino:	63107
	sigmask:	0000000000000200

where 'sigmask' is hex value of the signal mask associated
with a file.

Epoll files
~~~~~~~~~~~

::

	pos:	0
	flags:	02
	mnt_id:	9
	ino:	63107
	tfd:        5 events:       1d data: ffffffffffffffff pos:0 ino:61af sdev:7

where 'tfd' is a target file descriptor number in decimal form,
'events' is events mask being watched and the 'data' is data
associated with a target [see epoll(7) for more details].

The 'pos' is current offset of the target file in decimal form
[see lseek(2)], 'ino' and 'sdev' are inode and device numbers
where target file resides, all in hex format.

Fsnotify files
~~~~~~~~~~~~~~
For inotify files the format is the following::

	pos:	0
	flags:	02000000
	mnt_id:	9
	ino:	63107
	inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d

where 'wd' is a watch descriptor in decimal form, i.e. a target file
descriptor number, 'ino' and 'sdev' are inode and device where the
target file resides and the 'mask' is the mask of events, all in hex
form [see inotify(7) for more details].

If the kernel was built with exportfs support, the path to the target
file is encoded as a file handle.  The file handle is provided by three
fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
format.

If the kernel is built without exportfs support the file handle won't be
printed out.

If there is no inotify mark attached yet the 'inotify' line will be omitted.

For fanotify files the format is::

	pos:	0
	flags:	02
	mnt_id:	9
	ino:	63107
	fanotify flags:10 event-flags:0
	fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
	fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4

where fanotify 'flags' and 'event-flags' are values used in fanotify_init
call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
flags associated with mark which are tracked separately from events
mask. 'ino' and 'sdev' are target inode and device, 'mask' is the events
mask and 'ignored_mask' is the mask of events which are to be ignored.
All are in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
provide information about flags and mask used in fanotify_mark
call [see fsnotify manpage for details].

While the first three lines are mandatory and always printed, the rest is
optional and may be omitted if no marks created yet.

Timerfd files
~~~~~~~~~~~~~

::

	pos:	0
	flags:	02
	mnt_id:	9
	ino:	63107
	clockid: 0
	ticks: 0
	settime flags: 01
	it_value: (0, 49406829)
	it_interval: (1, 0)

where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
that have occurred [see timerfd_create(2) for details]. 'settime flags' are
flags in octal form been used to setup the timer [see timerfd_settime(2) for
details]. 'it_value' is remaining time until the timer expiration.
'it_interval' is the interval for the timer. Note the timer might be set up
with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
still exhibits timer's remaining time.

DMA Buffer files
~~~~~~~~~~~~~~~~

::

	pos:	0
	flags:	04002
	mnt_id:	9
	ino:	63107
	size:   32768
	count:  2
	exp_name:  system-heap

where 'size' is the size of the DMA buffer in bytes. 'count' is the file count of
the DMA buffer file. 'exp_name' is the name of the DMA buffer exporter.

VFIO Device files
~~~~~~~~~~~~~~~~~

::

	pos:    0
	flags:  02000002
	mnt_id: 17
	ino:    5122
	vfio-device-syspath: /sys/devices/pci0000:e0/0000:e0:01.1/0000:e1:00.0/0000:e2:05.0/0000:e8:00.0

where 'vfio-device-syspath' is the sysfs path corresponding to the VFIO device
file.

3.9	/proc/<pid>/map_files - Information about memory mapped files
---------------------------------------------------------------------
This directory contains symbolic links which represent memory mapped files
the process is maintaining.  Example output::

     | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
     | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
     | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so
     | ...
     | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1
     | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls

The name of a link represents the virtual memory bounds of a mapping, i.e.
vm_area_struct::vm_start-vm_area_struct::vm_end.

The main purpose of the map_files is to retrieve a set of memory mapped
files in a fast way instead of parsing /proc/<pid>/maps or
/proc/<pid>/smaps, both of which contain many more records.  At the same
time one can open(2) mappings from the listings of two processes and
comparing their inode numbers to figure out which anonymous memory areas
are actually shared.

3.10	/proc/<pid>/timerslack_ns - Task timerslack value
---------------------------------------------------------
This file provides the value of the task's timerslack value in nanoseconds.
This value specifies an amount of time that normal timers may be deferred
in order to coalesce timers and avoid unnecessary wakeups.

This allows a task's interactivity vs power consumption tradeoff to be
adjusted.

Writing 0 to the file will set the task's timerslack to the default value.

Valid values are from 0 - ULLONG_MAX

An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level
permissions on the task specified to change its timerslack_ns value.

3.11	/proc/<pid>/patch_state - Livepatch patch operation state
-----------------------------------------------------------------
When CONFIG_LIVEPATCH is enabled, this file displays the value of the
patch state for the task.

A value of '-1' indicates that no patch is in transition.

A value of '0' indicates that a patch is in transition and the task is
unpatched.  If the patch is being enabled, then the task hasn't been
patched yet.  If the patch is being disabled, then the task has already
been unpatched.

A value of '1' indicates that a patch is in transition and the task is
patched.  If the patch is being enabled, then the task has already been
patched.  If the patch is being disabled, then the task hasn't been
unpatched yet.

3.12 /proc/<pid>/arch_status - task architecture specific status
-------------------------------------------------------------------
When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the
architecture specific status of the task.

Example
~~~~~~~

::

 $ cat /proc/6753/arch_status
 AVX512_elapsed_ms:      8

Description
~~~~~~~~~~~

x86 specific entries
~~~~~~~~~~~~~~~~~~~~~

AVX512_elapsed_ms
^^^^^^^^^^^^^^^^^^

  If AVX512 is supported on the machine, this entry shows the milliseconds
  elapsed since the last time AVX512 usage was recorded. The recording
  happens on a best effort basis when a task is scheduled out. This means
  that the value depends on two factors:

    1) The time which the task spent on the CPU without being scheduled
       out. With CPU isolation and a single runnable task this can take
       several seconds.

    2) The time since the task was scheduled out last. Depending on the
       reason for being scheduled out (time slice exhausted, syscall ...)
       this can be arbitrary long time.

  As a consequence the value cannot be considered precise and authoritative
  information. The application which uses this information has to be aware
  of the overall scenario on the system in order to determine whether a
  task is a real AVX512 user or not. Precise information can be obtained
  with performance counters.

  A special value of '-1' indicates that no AVX512 usage was recorded, thus
  the task is unlikely an AVX512 user, but depends on the workload and the
  scheduling scenario, it also could be a false negative mentioned above.

3.13 /proc/<pid>/fd - List of symlinks to open files
-------------------------------------------------------
This directory contains symbolic links which represent open files
the process is maintaining.  Example output::

  lr-x------ 1 root root 64 Sep 20 17:53 0 -> /dev/null
  l-wx------ 1 root root 64 Sep 20 17:53 1 -> /dev/null
  lrwx------ 1 root root 64 Sep 20 17:53 10 -> 'socket:[12539]'
  lrwx------ 1 root root 64 Sep 20 17:53 11 -> 'socket:[12540]'
  lrwx------ 1 root root 64 Sep 20 17:53 12 -> 'socket:[12542]'

The number of open files for the process is stored in 'size' member
of stat() output for /proc/<pid>/fd for fast access.
-------------------------------------------------------

3.14 /proc/<pid>/ksm_stat - Information about the process's ksm status
----------------------------------------------------------------------
When CONFIG_KSM is enabled, each process has this file which displays
the information of ksm merging status.

Example
~~~~~~~

::

    / # cat /proc/self/ksm_stat
    ksm_rmap_items 0
    ksm_zero_pages 0
    ksm_merging_pages 0
    ksm_process_profit 0
    ksm_merge_any: no
    ksm_mergeable: no

Description
~~~~~~~~~~~

ksm_rmap_items
^^^^^^^^^^^^^^

The number of ksm_rmap_item structures in use.  The structure
ksm_rmap_item stores the reverse mapping information for virtual
addresses.  KSM will generate a ksm_rmap_item for each ksm-scanned page of
the process.

ksm_zero_pages
^^^^^^^^^^^^^^

When /sys/kernel/mm/ksm/use_zero_pages is enabled, it represent how many
empty pages are merged with kernel zero pages by KSM.

ksm_merging_pages
^^^^^^^^^^^^^^^^^

It represents how many pages of this process are involved in KSM merging
(not including ksm_zero_pages). It is the same with what
/proc/<pid>/ksm_merging_pages shows.

ksm_process_profit
^^^^^^^^^^^^^^^^^^

The profit that KSM brings (Saved bytes). KSM can save memory by merging
identical pages, but also can consume additional memory, because it needs
to generate a number of rmap_items to save each scanned page's brief rmap
information. Some of these pages may be merged, but some may not be abled
to be merged after being checked several times, which are unprofitable
memory consumed.

ksm_merge_any
^^^^^^^^^^^^^

It specifies whether the process's 'mm is added by prctl() into the
candidate list of KSM or not, and if KSM scanning is fully enabled at
process level.

ksm_mergeable
^^^^^^^^^^^^^

It specifies whether any VMAs of the process''s mms are currently
applicable to KSM.

More information about KSM can be found in
Documentation/admin-guide/mm/ksm.rst.


Chapter 4: Configuring procfs
=============================

4.1	Mount options
---------------------

The following mount options are supported:

	=========	========================================================
	hidepid=	Set /proc/<pid>/ access mode.
	gid=		Set the group authorized to learn processes information.
	subset=		Show only the specified subset of procfs.
	pidns=		Specify a the namespace used by this procfs.
	=========	========================================================

hidepid=off or hidepid=0 means classic mode - everybody may access all
/proc/<pid>/ directories (default).

hidepid=noaccess or hidepid=1 means users may not access any /proc/<pid>/
directories but their own.  Sensitive files like cmdline, sched*, status are now
protected against other users.  This makes it impossible to learn whether any
user runs specific program (given the program doesn't reveal itself by its
behaviour).  As an additional bonus, as /proc/<pid>/cmdline is unaccessible for
other users, poorly written programs passing sensitive information via program
arguments are now protected against local eavesdroppers.

hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be
fully invisible to other users.  It doesn't mean that it hides a fact whether a
process with a specific pid value exists (it can be learned by other means, e.g.
by "kill -0 $PID"), but it hides process's uid and gid, which may be learned by
stat()'ing /proc/<pid>/ otherwise.  It greatly complicates an intruder's task of
gathering information about running processes, whether some daemon runs with
elevated privileges, whether other user runs some sensitive program, whether
other users run any program at all, etc.

hidepid=ptraceable or hidepid=4 means that procfs should only contain
/proc/<pid>/ directories that the caller can ptrace.

gid= defines a group authorized to learn processes information otherwise
prohibited by hidepid=.  If you use some daemon like identd which needs to learn
information about processes information, just add identd to this group.

subset=pid hides all top level files and directories in the procfs that
are not related to tasks.

pidns= specifies a pid namespace (either as a string path to something like
`/proc/$pid/ns/pid`, or a file descriptor when using `FSCONFIG_SET_FD`) that
will be used by the procfs instance when translating pids. By default, procfs
will use the calling process's active pid namespace. Note that the pid
namespace of an existing procfs instance cannot be modified (attempting to do
so will give an `-EBUSY` error).

Chapter 5: Filesystem behavior
==============================

Originally, before the advent of pid namespace, procfs was a global file
system. It means that there was only one procfs instance in the system.

When pid namespace was added, a separate procfs instance was mounted in
each pid namespace. So, procfs mount options are global among all
mountpoints within the same namespace::

	# grep ^proc /proc/mounts
	proc /proc proc rw,relatime,hidepid=2 0 0

	# strace -e mount mount -o hidepid=1 -t proc proc /tmp/proc
	mount("proc", "/tmp/proc", "proc", 0, "hidepid=1") = 0
	+++ exited with 0 +++

	# grep ^proc /proc/mounts
	proc /proc proc rw,relatime,hidepid=2 0 0
	proc /tmp/proc proc rw,relatime,hidepid=2 0 0

and only after remounting procfs mount options will change at all
mountpoints::

	# mount -o remount,hidepid=1 -t proc proc /tmp/proc

	# grep ^proc /proc/mounts
	proc /proc proc rw,relatime,hidepid=1 0 0
	proc /tmp/proc proc rw,relatime,hidepid=1 0 0

This behavior is different from the behavior of other filesystems.

The new procfs behavior is more like other filesystems. Each procfs mount
creates a new procfs instance. Mount options affect own procfs instance.
It means that it became possible to have several procfs instances
displaying tasks with different filtering options in one pid namespace::

	# mount -o hidepid=invisible -t proc proc /proc
	# mount -o hidepid=noaccess -t proc proc /tmp/proc
	# grep ^proc /proc/mounts
	proc /proc proc rw,relatime,hidepid=invisible 0 0
	proc /tmp/proc proc rw,relatime,hidepid=noaccess 0 0
]

gemini-3-flash-preview

							input: 64945
							output: 464
							thoughts: 1576

**Analysis of `/proc/timer_list` Accessibility**

Okay, let's break this down systematically. The documentation mentions `timer_list` as residing within `/proc`, though it's strangely absent from the expected table. I can confirm its existence, however. I recall that the `/proc/sys` entries require root privileges, and there are specific access rules for `/proc/<pid>/`. For top-level files like `/proc/timer_list`, we're dealing with standard VFS permissions.

Given `timer_list`'s `0400` permissions and ownership by global root, the restriction to global root seems straightforward. So, my initial inclination is "No," it's not readable.

To be absolutely certain, I considered edge cases:

*   **User Namespace and Root:** If an unprivileged user created a namespace as root, they could map UID 0, but the scenario specifies an *unprivileged* user.
*   **`sudo`:** Using `sudo` grants privilege, violating the unprivileged constraint.
*   **`unshare -r`:** With `unshare -r`, the current UID is mapped to 0 inside the new namespace. If the current UID is 1000, then inside the namespace, UID 0 is global UID 1000. The file `/proc/timer_list` is owned by global UID 0. Global UID 0 is NOT mapped in the namespace. So the user (global 1000) is NOT the owner of the file (global 0).

I double-checked `proc_create_seq_private` to ensure it uses the parent's UID, which defaults to `proc_root` (UID 0), and I confirmed `proc_root.uid` is never modified. The `proc_set_user` function, in `__proc_create`, uses `(*parent)->uid` if `parent` is `proc_root`.

I needed to make sure that the `proc_root` isn't per-namespace. I searched for it, and confirmed that it is a global variable. `proc_net` is special; however, `timer_list` is a global file, not within the `net` subdirectory.

The crucial point is that capabilities like `CAP_DAC_OVERRIDE` and `CAP_DAC_READ_SEARCH` in a user namespace only apply to files where the owner UID is mapped within that namespace. Global UID 0, being unmapped, means these capabilities are ineffective.

I went back to the source code for the `timer_list` proc entry creation. There's no conditional mode setting. `proc_create_seq_private` is a function, not a macro, so no tricks there.

I also checked if creating the namespace with `CLONE_NEWUSER` but NOT `CLONE_NEWPID` would change things. No, since it's the same mount, the permissions are the same. A new PID namespace and a new `proc` mount use the same PDE tree and inodes inherit the same UID/GID.

Finally, does `kptr_restrict` matter? No, because the permission check happens before attempting to read the content.

The commit `8e7df2b5b7f2` specifically sets the mode to `0400` to restrict access.

**Conclusion:**

*   `/proc/timer_list`'s mode is explicitly `0400`.
*   It's owned by global root (UID 0).
*   Standard VFS permission logic applies to `/proc` files.
*   An unprivileged user in a user namespace does not have global UID 0.
*   Even with namespace capabilities, global UID 0 is unmapped.
*   Thus, an unprivileged user cannot read `/proc/timer_list`. My answer remains: "No."

gemini-3.1-pro-preview

							input: 14520
							output: 66
							thoughts: 484

**My Assessment of the Timer List Vulnerability**

Alright, let's break this down. First, the crucial aspect is that this isn't exploitable by unprivileged processes or within user namespaces. That's good. Now, onto the core issue: the data race. It's a read and write conflict on an 8-byte value – specifically, the `cpu_base->expires_next` field. The read is part of printing to a `seq_file`, and the write updates the same field.

From a security perspective, this looks benign. It's highly unlikely to cause memory corruption, a denial-of-service condition, or any other security concern. So, Exploitable is false, DenialOfService is false. Unprivileged and UserNamespace are also false. No VMGuestTrigger, VMHostTrigger, NetworkTrigger, RemoteTrigger, PeripheralTrigger, or FilesystemTrigger either.

I need to confirm all the entry points to `timer_list_show`, just in case. It's called from `sysrq_timer_list_show`, which is itself triggered by `sysrq_handle_show_timers`. SysRq access is limited to either a physical keyboard or `/proc/sysrq-trigger`, which is root-only. So, definitely not unprivileged. I also need to make sure that `print_cpu` can only be called from `timer_list_show`. This confirms that access is limited to root-only.

Let's revisit the data race itself. Could concurrently reading `cpu_base->expires_next` during a write cause a crash? No, it's an 8-byte read on a 64-bit architecture. On most architectures, it is atomic, but even if it's torn, the result is merely a garbage value being printed. The KCSAN report confirms this: the value changes from one read to the next, which is exactly what we expect from a data race on a primitive type like this.

Okay, I've got a clear picture of what's going on here. Time to fill out the results.

map[DenialOfService:false Exploitable:false FilesystemTrigger:false NetworkTrigger:false PeripheralTrigger:false RemoteTrigger:false Unprivileged:false UserNamespace:false VMGuestTrigger:false VMHostTrigger:false]

map[DenialOfService:false Exploitable:false FilesystemTrigger:false NetworkTrigger:false PeripheralTrigger:false RemoteTrigger:false Unprivileged:false UserNamespace:false VMGuestTrigger:false VMHostTrigger:false]

gemini-3.1-pro-preview

							input: 15578
							output: 383
							thoughts: 179

**Analyzing a Benign KCSAN Data-Race Report**

Okay, so I've got this KCSAN data-race report to look at. The core of it seems to be between the `hrtimer_interrupt` function, which is writing to `cpu_base->expires_next`, and `print_cpu`, which is reading it. `print_cpu` gets called when we look at `/proc/timer_list` or when SysRq-Q is triggered. The crucial thing here is that `/proc/timer_list` is created with mode 0400, meaning it's only readable by root. That immediately limits the scope; unprivileged users and user namespaces can't even get to this data.

Given that restriction, this data race is basically harmless. `print_cpu` is just reading the value to then print it to a sequential file. Even if it gets a torn read or some intermediate value, the worst that happens is a bit of garbage gets printed. It's not exploitable, there's no way this turns into a denial-of-service, and it has no security ramifications. I'll document my analysis to be thorough and state this clearly.

map[Explanation:The reported bug is a KCSAN data-race between a write to
`cpu_base->expires_next` in `hrtimer_interrupt` and a read of the same variable
in `print_cpu`.

**Analysis:**
1. **Trigger mechanism:** The read occurs in `print_cpu`, which is invoked by
`timer_list_show`. This function is executed when reading the `/proc/timer_list`
file or when triggering the SysRq-Q command.
2. **Privilege level:** The `/proc/timer_list` file is created with `0400`
permissions (`proc_create_seq_private("timer_list", 0400, ...)`), meaning it is
only readable by the global root user. Unprivileged users cannot read it.
Furthermore, it is not accessible from within an unprivileged user namespace
because the file is owned by the global root (UID 0), which is not mapped into
the user namespace, preventing `CAP_DAC_OVERRIDE` from bypassing the permission
check. SysRq triggers also require root privileges (writing to
`/proc/sysrq-trigger`) or physical access.
3. **Impact:** The data race is completely benign. `print_cpu` reads the 8-byte
`expires_next` value locklessly simply to print it for diagnostic purposes. If a
concurrent write occurs, the read might fetch an intermediate or torn value,
which would merely result in a garbage timestamp being printed to the seq_file.
This cannot cause memory corruption, control-flow hijacking, kernel crashes, or
any form of denial-of-service.

**Conclusion:**
This is a benign diagnostic data race restricted to the root user. It has no
security impact, is not exploitable, and cannot be triggered by unprivileged
users, network traffic, or other external vectors.]

LLM Calls Summary:
Total Calls	Total Tokens	Avg Tokens	Total Duration (Seconds)	Avg Duration (Seconds)

Tool Calls Summary:
Total Calls	Total Duration (Seconds)	Avg Duration (Seconds)

BaseBranch	master
BaseCommit	RC
BaseRepository	git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
BugTitle	KCSAN: data-race in hrtimer_interrupt / print_cpu
CrashLogID	4853388581273600
CrashReportID	5463843557343232
KernelCommit	e1914add2799225a87502051415fc5c32aeb02ae
KernelConfig	Show (260855 bytes) # # Automatically generated file; DO NOT EDIT. # Linux/x86_64 syzkaller Kernel Configuration # CONFIG_CC_VERSION_TEXT="Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50)" CONFIG_GCC_VERSION=0 CONFIG_CC_IS_CLANG=y CONFIG_CLANG_VERSION=210108 CONFIG_AS_IS_LLVM=y CONFIG_AS_VERSION=210108 CONFIG_LD_VERSION=0 CONFIG_LD_IS_LLD=y CONFIG_LLD_VERSION=210108 CONFIG_RUSTC_VERSION=109101 CONFIG_RUST_IS_AVAILABLE=y CONFIG_RUSTC_LLVM_VERSION=210102 CONFIG_RUSTC_LLVM_MAJOR_VERSION=21 CONFIG_RUSTC_CLANG_LLVM_COMPATIBLE=y CONFIG_CC_CAN_LINK=y CONFIG_CC_HAS_ASM_GOTO_OUTPUT=y CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT=y CONFIG_TOOLS_SUPPORT_RELR=y CONFIG_CC_HAS_ASM_INLINE=y CONFIG_CC_HAS_ASSUME=y CONFIG_CC_HAS_NO_PROFILE_FN_ATTR=y CONFIG_CC_HAS_COUNTED_BY=y CONFIG_CC_HAS_BROKEN_COUNTED_BY_REF=y CONFIG_CC_HAS_MULTIDIMENSIONAL_NONSTRING=y CONFIG_LD_CAN_USE_KEEP_IN_OVERLAY=y CONFIG_RUSTC_HAS_SPAN_FILE=y CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES=y CONFIG_RUSTC_HAS_FILE_WITH_NUL=y CONFIG_RUSTC_HAS_FILE_AS_C_STR=y CONFIG_PAHOLE_VERSION=130 CONFIG_CONSTRUCTORS=y CONFIG_IRQ_WORK=y CONFIG_BUILDTIME_TABLE_SORT=y CONFIG_THREAD_INFO_IN_TASK=y # # General setup # CONFIG_INIT_ENV_ARG_LIMIT=32 # CONFIG_COMPILE_TEST is not set # CONFIG_WERROR is not set CONFIG_LOCALVERSION="" CONFIG_LOCALVERSION_AUTO=y CONFIG_BUILD_SALT="" CONFIG_HAVE_KERNEL_GZIP=y CONFIG_HAVE_KERNEL_BZIP2=y CONFIG_HAVE_KERNEL_LZMA=y CONFIG_HAVE_KERNEL_XZ=y CONFIG_HAVE_KERNEL_LZO=y CONFIG_HAVE_KERNEL_LZ4=y CONFIG_HAVE_KERNEL_ZSTD=y CONFIG_KERNEL_GZIP=y # CONFIG_KERNEL_BZIP2 is not set # CONFIG_KERNEL_LZMA is not set # CONFIG_KERNEL_XZ is not set # CONFIG_KERNEL_LZO is not set # CONFIG_KERNEL_LZ4 is not set # CONFIG_KERNEL_ZSTD is not set CONFIG_DEFAULT_INIT="" CONFIG_DEFAULT_HOSTNAME="(none)" CONFIG_SYSVIPC=y CONFIG_SYSVIPC_SYSCTL=y CONFIG_SYSVIPC_COMPAT=y CONFIG_POSIX_MQUEUE=y CONFIG_POSIX_MQUEUE_SYSCTL=y # CONFIG_WATCH_QUEUE is not set CONFIG_CROSS_MEMORY_ATTACH=y CONFIG_AUDIT=y CONFIG_HAVE_ARCH_AUDITSYSCALL=y CONFIG_AUDITSYSCALL=y # # IRQ subsystem # CONFIG_GENERIC_IRQ_PROBE=y CONFIG_GENERIC_IRQ_SHOW=y CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK=y CONFIG_GENERIC_PENDING_IRQ=y CONFIG_GENERIC_IRQ_MIGRATION=y CONFIG_HARDIRQS_SW_RESEND=y CONFIG_IRQ_DOMAIN=y CONFIG_IRQ_DOMAIN_HIERARCHY=y CONFIG_GENERIC_MSI_IRQ=y CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR=y CONFIG_GENERIC_IRQ_RESERVATION_MODE=y CONFIG_IRQ_FORCED_THREADING=y CONFIG_SPARSE_IRQ=y # CONFIG_GENERIC_IRQ_DEBUGFS is not set # end of IRQ subsystem CONFIG_CLOCKSOURCE_WATCHDOG=y CONFIG_ARCH_CLOCKSOURCE_INIT=y CONFIG_ARCH_WANTS_CLOCKSOURCE_READ_INLINE=y CONFIG_GENERIC_TIME_VSYSCALL=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE=y CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=y CONFIG_GENERIC_CLOCKEVENTS_COUPLED=y CONFIG_GENERIC_CLOCKEVENTS_COUPLED_INLINE=y CONFIG_GENERIC_CMOS_UPDATE=y CONFIG_HRTIMER_REARM_DEFERRED=y CONFIG_HAVE_POSIX_CPU_TIMERS_TASK_WORK=y CONFIG_POSIX_CPU_TIMERS_TASK_WORK=y CONFIG_CONTEXT_TRACKING=y CONFIG_CONTEXT_TRACKING_IDLE=y # # Timers subsystem # CONFIG_TICK_ONESHOT=y CONFIG_NO_HZ_COMMON=y # CONFIG_HZ_PERIODIC is not set CONFIG_NO_HZ_IDLE=y # CONFIG_NO_HZ_FULL is not set CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y # CONFIG_POSIX_AUX_CLOCKS is not set # end of Timers subsystem CONFIG_BPF=y CONFIG_HAVE_EBPF_JIT=y CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y # # BPF subsystem # CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y # CONFIG_BPF_JIT_ALWAYS_ON is not set CONFIG_BPF_JIT_DEFAULT_ON=y # CONFIG_BPF_UNPRIV_DEFAULT_OFF is not set # CONFIG_BPF_PRELOAD is not set # CONFIG_BPF_LSM is not set # end of BPF subsystem CONFIG_PREEMPT_BUILD=y CONFIG_ARCH_HAS_PREEMPT_LAZY=y CONFIG_PREEMPT=y # CONFIG_PREEMPT_LAZY is not set # CONFIG_PREEMPT_RT is not set CONFIG_PREEMPT_COUNT=y CONFIG_PREEMPTION=y CONFIG_PREEMPT_DYNAMIC=y # CONFIG_SCHED_CORE is not set # # CPU/Task time and stats accounting # CONFIG_TICK_CPU_ACCOUNTING=y # CONFIG_VIRT_CPU_ACCOUNTING_GEN is not set # CONFIG_IRQ_TIME_ACCOUNTING is not set CONFIG_BSD_PROCESS_ACCT=y # CONFIG_BSD_PROCESS_ACCT_V3 is not set CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y # CONFIG_PSI is not set # end of CPU/Task time and stats accounting CONFIG_CPU_ISOLATION=y # # RCU Subsystem # CONFIG_TREE_RCU=y CONFIG_PREEMPT_RCU=y # CONFIG_RCU_EXPERT is not set CONFIG_TREE_SRCU=y CONFIG_TASKS_RCU_GENERIC=y CONFIG_NEED_TASKS_RCU=y CONFIG_TASKS_RCU=y CONFIG_TASKS_TRACE_RCU=y CONFIG_RCU_STALL_COMMON=y CONFIG_RCU_NEED_SEGCBLIST=y # end of RCU Subsystem # CONFIG_IKCONFIG is not set # CONFIG_IKHEADERS is not set CONFIG_LOG_BUF_SHIFT=18 CONFIG_LOG_CPU_MAX_BUF_SHIFT=12 # CONFIG_PRINTK_INDEX is not set CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y # # Scheduler features # # CONFIG_UCLAMP_TASK is not set # CONFIG_SCHED_PROXY_EXEC is not set # end of Scheduler features CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH=y CONFIG_CC_HAS_INT128=y CONFIG_CC_IMPLICIT_FALLTHROUGH="-Wimplicit-fallthrough" CONFIG_CC_MS_EXTENSIONS="-fms-extensions" CONFIG_GCC10_NO_ARRAY_BOUNDS=y CONFIG_GCC_NO_STRINGOP_OVERFLOW=y CONFIG_ARCH_SUPPORTS_INT128=y # CONFIG_NUMA_BALANCING is not set CONFIG_SLAB_OBJ_EXT=y CONFIG_CGROUPS=y CONFIG_PAGE_COUNTER=y # CONFIG_CGROUP_FAVOR_DYNMODS is not set CONFIG_MEMCG=y CONFIG_MEMCG_V1=y CONFIG_BLK_CGROUP=y CONFIG_CGROUP_WRITEBACK=y CONFIG_CGROUP_SCHED=y CONFIG_GROUP_SCHED_WEIGHT=y CONFIG_FAIR_GROUP_SCHED=y # CONFIG_CFS_BANDWIDTH is not set # CONFIG_RT_GROUP_SCHED is not set CONFIG_SCHED_MM_CID=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_RDMA=y # CONFIG_CGROUP_DMEM is not set CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y # CONFIG_CPUSETS_V1 is not set CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y # CONFIG_CGROUP_BPF is not set CONFIG_CGROUP_MISC=y CONFIG_CGROUP_DEBUG=y CONFIG_SOCK_CGROUP_DATA=y CONFIG_NAMESPACES=y CONFIG_UTS_NS=y CONFIG_TIME_NS=y CONFIG_TIME_NS_VDSO=y CONFIG_IPC_NS=y CONFIG_USER_NS=y CONFIG_PID_NS=y CONFIG_NET_NS=y # CONFIG_CHECKPOINT_RESTORE is not set # CONFIG_SCHED_AUTOGROUP is not set CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" CONFIG_RD_GZIP=y CONFIG_RD_BZIP2=y CONFIG_RD_LZMA=y CONFIG_RD_XZ=y CONFIG_RD_LZO=y CONFIG_RD_LZ4=y CONFIG_RD_ZSTD=y # CONFIG_BOOT_CONFIG is not set CONFIG_CMDLINE_LOG_WRAP_IDEAL_LEN=1021 CONFIG_INITRAMFS_PRESERVE_MTIME=y CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_LD_ORPHAN_WARN=y CONFIG_LD_ORPHAN_WARN_LEVEL="warn" CONFIG_SYSCTL=y CONFIG_HAVE_UID16=y CONFIG_SYSCTL_EXCEPTION_TRACE=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_HAVE_PCSPKR_PLATFORM=y CONFIG_EXPERT=y CONFIG_UID16=y CONFIG_MULTIUSER=y CONFIG_SGETMASK_SYSCALL=y CONFIG_FHANDLE=y CONFIG_POSIX_TIMERS=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y CONFIG_PCSPKR_PLATFORM=y # CONFIG_BASE_SMALL is not set CONFIG_FUTEX=y CONFIG_FUTEX_PI=y CONFIG_FUTEX_PRIVATE_HASH=y CONFIG_FUTEX_MPOL=y CONFIG_EPOLL=y CONFIG_SIGNALFD=y CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_AIO=y CONFIG_IO_URING=y # CONFIG_IO_URING_MOCK_FILE is not set CONFIG_ADVISE_SYSCALLS=y CONFIG_MEMBARRIER=y CONFIG_KCMP=y CONFIG_RSEQ=y # CONFIG_RSEQ_SLICE_EXTENSION is not set # CONFIG_RSEQ_STATS is not set # CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE is not set CONFIG_CACHESTAT_SYSCALL=y CONFIG_KALLSYMS=y # CONFIG_KALLSYMS_SELFTEST is not set CONFIG_KALLSYMS_ALL=y CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE=y CONFIG_ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS=y CONFIG_HAVE_PERF_EVENTS=y # # Kernel Performance Events And Counters # CONFIG_PERF_EVENTS=y # CONFIG_DEBUG_PERF_USE_VMALLOC is not set # end of Kernel Performance Events And Counters CONFIG_SYSTEM_DATA_VERIFICATION=y CONFIG_PROFILING=y # CONFIG_RUST is not set CONFIG_TRACEPOINTS=y # # Kexec and crash features # CONFIG_CRASH_RESERVE=y CONFIG_VMCORE_INFO=y CONFIG_KEXEC_CORE=y CONFIG_KEXEC=y # CONFIG_KEXEC_FILE is not set # CONFIG_KEXEC_JUMP is not set CONFIG_CRASH_DUMP=y CONFIG_CRASH_HOTPLUG=y CONFIG_CRASH_MAX_MEMORY_RANGES=8192 # end of Kexec and crash features # # Live Update and Kexec HandOver # # CONFIG_KEXEC_HANDOVER is not set # end of Live Update and Kexec HandOver # end of General setup CONFIG_64BIT=y CONFIG_X86_64=y CONFIG_X86=y CONFIG_INSTRUCTION_DECODER=y CONFIG_OUTPUT_FORMAT="elf64-x86-64" CONFIG_LOCKDEP_SUPPORT=y CONFIG_STACKTRACE_SUPPORT=y CONFIG_MMU=y CONFIG_ARCH_MMAP_RND_BITS_MIN=28 CONFIG_ARCH_MMAP_RND_BITS_MAX=32 CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN=8 CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX=16 CONFIG_GENERIC_ISA_DMA=y CONFIG_GENERIC_BUG=y CONFIG_GENERIC_BUG_RELATIVE_POINTERS=y CONFIG_ARCH_MAY_HAVE_PC_FDC=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_ARCH_HAS_CPU_RELAX=y CONFIG_ARCH_HIBERNATION_POSSIBLE=y CONFIG_ARCH_SUSPEND_POSSIBLE=y CONFIG_AUDIT_ARCH=y CONFIG_HAVE_INTEL_TXT=y CONFIG_ARCH_SUPPORTS_UPROBES=y CONFIG_FIX_EARLYCON_MEM=y CONFIG_PGTABLE_LEVELS=5 # # Processor type and features # CONFIG_SMP=y CONFIG_X86_X2APIC=y CONFIG_X86_MPPARSE=y # CONFIG_X86_CPU_RESCTRL is not set # CONFIG_X86_FRED is not set CONFIG_X86_EXTENDED_PLATFORM=y # CONFIG_X86_NUMACHIP is not set # CONFIG_X86_VSMP is not set # CONFIG_X86_INTEL_MID is not set # CONFIG_X86_GOLDFISH is not set # CONFIG_X86_INTEL_LPSS is not set # CONFIG_X86_AMD_PLATFORM_DEVICE is not set CONFIG_IOSF_MBI=y # CONFIG_IOSF_MBI_DEBUG is not set CONFIG_X86_SUPPORTS_MEMORY_FAILURE=y CONFIG_SCHED_OMIT_FRAME_POINTER=y CONFIG_HYPERVISOR_GUEST=y CONFIG_PARAVIRT=y CONFIG_PARAVIRT_SPINLOCKS=y CONFIG_X86_HV_CALLBACK_VECTOR=y # CONFIG_XEN is not set CONFIG_KVM_GUEST=y CONFIG_ARCH_CPUIDLE_HALTPOLL=y CONFIG_PVH=y # CONFIG_PARAVIRT_TIME_ACCOUNTING is not set CONFIG_PARAVIRT_CLOCK=y # CONFIG_JAILHOUSE_GUEST is not set # CONFIG_ACRN_GUEST is not set # CONFIG_BHYVE_GUEST is not set CONFIG_CC_HAS_MARCH_NATIVE=y # CONFIG_X86_NATIVE_CPU is not set CONFIG_X86_INTERNODE_CACHE_SHIFT=6 CONFIG_X86_L1_CACHE_SHIFT=6 CONFIG_X86_TSC=y CONFIG_X86_HAVE_PAE=y CONFIG_X86_CX8=y CONFIG_X86_CMOV=y CONFIG_X86_MINIMUM_CPU_FAMILY=64 CONFIG_X86_DEBUGCTLMSR=y CONFIG_IA32_FEAT_CTL=y CONFIG_X86_VMX_FEATURE_NAMES=y CONFIG_PROCESSOR_SELECT=y CONFIG_BROADCAST_TLB_FLUSH=y CONFIG_CPU_SUP_INTEL=y CONFIG_CPU_SUP_AMD=y # CONFIG_CPU_SUP_HYGON is not set # CONFIG_CPU_SUP_CENTAUR is not set # CONFIG_CPU_SUP_ZHAOXIN is not set CONFIG_HPET_TIMER=y CONFIG_HPET_EMULATE_RTC=y CONFIG_DMI=y # CONFIG_GART_IOMMU is not set # CONFIG_MAXSMP is not set CONFIG_NR_CPUS_RANGE_BEGIN=2 CONFIG_NR_CPUS_RANGE_END=512 CONFIG_NR_CPUS_DEFAULT=64 CONFIG_NR_CPUS=8 CONFIG_SCHED_MC_PRIO=y CONFIG_X86_LOCAL_APIC=y CONFIG_ACPI_MADT_WAKEUP=y CONFIG_X86_IO_APIC=y CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y CONFIG_X86_MCE=y # CONFIG_X86_MCELOG_LEGACY is not set CONFIG_X86_MCE_INTEL=y CONFIG_X86_MCE_AMD=y CONFIG_X86_MCE_THRESHOLD=y # CONFIG_X86_MCE_INJECT is not set # # Performance monitoring # CONFIG_PERF_EVENTS_INTEL_UNCORE=y CONFIG_PERF_EVENTS_INTEL_RAPL=y CONFIG_PERF_EVENTS_INTEL_CSTATE=y # CONFIG_PERF_EVENTS_AMD_POWER is not set CONFIG_PERF_EVENTS_AMD_UNCORE=y # CONFIG_PERF_EVENTS_AMD_BRS is not set # end of Performance monitoring CONFIG_X86_16BIT=y CONFIG_X86_ESPFIX64=y CONFIG_X86_VSYSCALL_EMULATION=y CONFIG_X86_IOPL_IOPERM=y CONFIG_MICROCODE=y # CONFIG_MICROCODE_LATE_LOADING is not set # CONFIG_MICROCODE_DBG is not set CONFIG_X86_MSR=y CONFIG_X86_CPUID=y CONFIG_X86_DIRECT_GBPAGES=y # CONFIG_X86_CPA_STATISTICS is not set CONFIG_NUMA=y CONFIG_AMD_NUMA=y CONFIG_X86_64_ACPI_NUMA=y CONFIG_NODES_SHIFT=6 CONFIG_ARCH_SPARSEMEM_ENABLE=y CONFIG_ARCH_SPARSEMEM_DEFAULT=y CONFIG_ARCH_PROC_KCORE_TEXT=y CONFIG_ILLEGAL_POINTER_VALUE=0xdead000000000000 # CONFIG_X86_PMEM_LEGACY is not set CONFIG_X86_CHECK_BIOS_CORRUPTION=y CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y CONFIG_MTRR=y # CONFIG_MTRR_SANITIZER is not set CONFIG_X86_PAT=y CONFIG_X86_UMIP=y CONFIG_CC_HAS_IBT=y CONFIG_X86_CET=y CONFIG_X86_KERNEL_IBT=y CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS=y CONFIG_ARCH_PKEY_BITS=4 # CONFIG_X86_INTEL_TSX_MODE_OFF is not set CONFIG_X86_INTEL_TSX_MODE_ON=y # CONFIG_X86_INTEL_TSX_MODE_AUTO is not set # CONFIG_X86_SGX is not set # CONFIG_X86_USER_SHADOW_STACK is not set # CONFIG_EFI is not set CONFIG_HZ_100=y # CONFIG_HZ_250 is not set # CONFIG_HZ_300 is not set # CONFIG_HZ_1000 is not set CONFIG_HZ=100 CONFIG_SCHED_HRTICK=y CONFIG_ARCH_SUPPORTS_KEXEC=y CONFIG_ARCH_SUPPORTS_KEXEC_FILE=y CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY=y CONFIG_ARCH_SUPPORTS_KEXEC_SIG=y CONFIG_ARCH_SUPPORTS_KEXEC_SIG_FORCE=y CONFIG_ARCH_SUPPORTS_KEXEC_BZIMAGE_VERIFY_SIG=y CONFIG_ARCH_SUPPORTS_KEXEC_JUMP=y CONFIG_ARCH_SUPPORTS_KEXEC_HANDOVER=y CONFIG_ARCH_SUPPORTS_CRASH_DUMP=y CONFIG_ARCH_DEFAULT_CRASH_DUMP=y CONFIG_ARCH_SUPPORTS_CRASH_HOTPLUG=y CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION=y CONFIG_PHYSICAL_START=0x1000000 # CONFIG_RELOCATABLE is not set CONFIG_PHYSICAL_ALIGN=0x200000 CONFIG_HOTPLUG_CPU=y # CONFIG_COMPAT_VDSO is not set CONFIG_LEGACY_VSYSCALL_XONLY=y # CONFIG_LEGACY_VSYSCALL_NONE is not set CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlyprintk=serial net.ifnames=0 sysctl.kernel.hung_task_all_cpu_backtrace=1 ima_policy=tcb nf-conntrack-ftp.ports=20000 nf-conntrack-tftp.ports=20000 nf-conntrack-sip.ports=20000 nf-conntrack-irc.ports=20000 nf-conntrack-sane.ports=20000 binder.debug_mask=0 rcupdate.rcu_expedited=1 rcupdate.rcu_cpu_stall_cputime=1 no_hash_pointers page_owner=on sysctl.vm.nr_hugepages=4 sysctl.vm.nr_overcommit_hugepages=4 secretmem.enable=1 sysctl.max_rcu_stall_to_panic=1 msr.allow_writes=off coredump_filter=0xffff root=/dev/sda console=ttyS0 vsyscall=native numa=fake=2 kvm-intel.nested=1 spec_store_bypass_disable=prctl nopcid vivid.n_devs=64 vivid.multiplanar=1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2,1,2 netrom.nr_ndevs=32 rose.rose_ndevs=32 smp.csd_lock_timeout=100000 watchdog_thresh=55 workqueue.watchdog_thresh=140 sysctl.net.core.netdev_unregister_timeout_secs=140 dummy_hcd.num=32 max_loop=32 nbds_max=32" # CONFIG_CMDLINE_OVERRIDE is not set CONFIG_MODIFY_LDT_SYSCALL=y # CONFIG_STRICT_SIGALTSTACK_SIZE is not set CONFIG_HAVE_LIVEPATCH=y CONFIG_HAVE_KLP_BUILD=y CONFIG_X86_BUS_LOCK_DETECT=y # end of Processor type and features CONFIG_CC_HAS_SLS=y CONFIG_CC_HAS_RETURN_THUNK=y CONFIG_CC_HAS_ENTRY_PADDING=y CONFIG_CC_HAS_KCFI_ARITY=y CONFIG_FUNCTION_PADDING_CFI=11 CONFIG_FUNCTION_PADDING_BYTES=16 CONFIG_CALL_PADDING=y CONFIG_HAVE_CALL_THUNKS=y CONFIG_CALL_THUNKS=y CONFIG_PREFIX_SYMBOLS=y CONFIG_CPU_MITIGATIONS=y CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=y CONFIG_MITIGATION_RETPOLINE=y CONFIG_MITIGATION_RETHUNK=y CONFIG_MITIGATION_UNRET_ENTRY=y CONFIG_MITIGATION_CALL_DEPTH_TRACKING=y # CONFIG_CALL_THUNKS_DEBUG is not set CONFIG_MITIGATION_IBPB_ENTRY=y CONFIG_MITIGATION_IBRS_ENTRY=y CONFIG_MITIGATION_SRSO=y # CONFIG_MITIGATION_SLS is not set CONFIG_MITIGATION_GDS=y CONFIG_MITIGATION_RFDS=y CONFIG_MITIGATION_SPECTRE_BHI=y CONFIG_MITIGATION_MDS=y CONFIG_MITIGATION_TAA=y CONFIG_MITIGATION_MMIO_STALE_DATA=y CONFIG_MITIGATION_L1TF=y CONFIG_MITIGATION_RETBLEED=y CONFIG_MITIGATION_SPECTRE_V1=y CONFIG_MITIGATION_SPECTRE_V2=y CONFIG_MITIGATION_SRBDS=y CONFIG_MITIGATION_SSB=y CONFIG_MITIGATION_ITS=y CONFIG_MITIGATION_TSA=y CONFIG_ARCH_HAS_ADD_PAGES=y # # Power management and ACPI options # CONFIG_ARCH_HIBERNATION_HEADER=y CONFIG_SUSPEND=y CONFIG_SUSPEND_FREEZER=y # CONFIG_SUSPEND_SKIP_SYNC is not set CONFIG_HIBERNATE_CALLBACKS=y CONFIG_HIBERNATION=y CONFIG_HIBERNATION_SNAPSHOT_DEV=y CONFIG_HIBERNATION_COMP_LZO=y CONFIG_HIBERNATION_DEF_COMP="lzo" CONFIG_PM_STD_PARTITION="" CONFIG_PM_SLEEP=y CONFIG_PM_SLEEP_SMP=y # CONFIG_PM_AUTOSLEEP is not set # CONFIG_PM_USERSPACE_AUTOSLEEP is not set # CONFIG_PM_WAKELOCKS is not set # CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP is not set CONFIG_PM=y CONFIG_PM_DEBUG=y # CONFIG_PM_ADVANCED_DEBUG is not set # CONFIG_PM_TEST_SUSPEND is not set CONFIG_PM_SLEEP_DEBUG=y CONFIG_PM_TRACE=y CONFIG_PM_TRACE_RTC=y CONFIG_PM_CLK=y # CONFIG_WQ_POWER_EFFICIENT_DEFAULT is not set # CONFIG_ENERGY_MODEL is not set CONFIG_ARCH_SUPPORTS_ACPI=y CONFIG_ACPI=y CONFIG_ACPI_LEGACY_TABLES_LOOKUP=y CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC=y CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT=y CONFIG_ACPI_THERMAL_LIB=y # CONFIG_ACPI_DEBUGGER is not set CONFIG_ACPI_SPCR_TABLE=y # CONFIG_ACPI_FPDT is not set CONFIG_ACPI_LPIT=y CONFIG_ACPI_SLEEP=y CONFIG_ACPI_REV_OVERRIDE_POSSIBLE=y CONFIG_ACPI_EC=y # CONFIG_ACPI_EC_DEBUGFS is not set CONFIG_ACPI_AC=y CONFIG_ACPI_BATTERY=y CONFIG_ACPI_BUTTON=y CONFIG_ACPI_VIDEO=y CONFIG_ACPI_FAN=y # CONFIG_ACPI_TAD is not set CONFIG_ACPI_DOCK=y CONFIG_ACPI_CPU_FREQ_PSS=y CONFIG_ACPI_PROCESSOR_CSTATE=y CONFIG_ACPI_PROCESSOR_IDLE=y CONFIG_ACPI_CPPC_LIB=y CONFIG_ACPI_PROCESSOR=y CONFIG_ACPI_HOTPLUG_CPU=y # CONFIG_ACPI_PROCESSOR_AGGREGATOR is not set CONFIG_ACPI_THERMAL=y CONFIG_ACPI_PLATFORM_PROFILE=y CONFIG_ARCH_HAS_ACPI_TABLE_UPGRADE=y CONFIG_ACPI_TABLE_UPGRADE=y CONFIG_ACPI_DEBUG=y # CONFIG_ACPI_PCI_SLOT is not set CONFIG_ACPI_CONTAINER=y CONFIG_ACPI_HOTPLUG_IOAPIC=y # CONFIG_ACPI_SBS is not set # CONFIG_ACPI_HED is not set # CONFIG_ACPI_REDUCED_HARDWARE_ONLY is not set CONFIG_ACPI_NHLT=y # CONFIG_ACPI_NFIT is not set CONFIG_ACPI_NUMA=y # CONFIG_ACPI_HMAT is not set CONFIG_HAVE_ACPI_APEI=y CONFIG_HAVE_ACPI_APEI_NMI=y # CONFIG_ACPI_APEI is not set # CONFIG_ACPI_DPTF is not set # CONFIG_ACPI_EXTLOG is not set # CONFIG_ACPI_CONFIGFS is not set # CONFIG_ACPI_PFRUT is not set CONFIG_ACPI_PCC=y # CONFIG_ACPI_FFH is not set CONFIG_ACPI_MRRM=y CONFIG_PMIC_OPREGION=y CONFIG_BXT_WC_PMIC_OPREGION=y # CONFIG_CHT_WC_PMIC_OPREGION is not set CONFIG_X86_PM_TIMER=y # # CPU Frequency scaling # CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_ATTR_SET=y CONFIG_CPU_FREQ_GOV_COMMON=y # CONFIG_CPU_FREQ_STAT is not set # CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set # CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y # CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL is not set CONFIG_CPU_FREQ_GOV_PERFORMANCE=y # CONFIG_CPU_FREQ_GOV_POWERSAVE is not set CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y # CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y # # CPU frequency scaling drivers # # CONFIG_CPUFREQ_DT is not set # CONFIG_CPUFREQ_DT_PLATDEV is not set CONFIG_X86_INTEL_PSTATE=y # CONFIG_X86_PCC_CPUFREQ is not set CONFIG_X86_AMD_PSTATE=y CONFIG_X86_AMD_PSTATE_DEFAULT_MODE=3 # CONFIG_X86_AMD_PSTATE_DYNAMIC_EPP is not set # CONFIG_X86_AMD_PSTATE_UT is not set CONFIG_X86_ACPI_CPUFREQ=y CONFIG_X86_ACPI_CPUFREQ_CPB=y # CONFIG_X86_POWERNOW_K8 is not set # CONFIG_X86_AMD_FREQ_SENSITIVITY is not set # CONFIG_X86_SPEEDSTEP_CENTRINO is not set # CONFIG_X86_P4_CLOCKMOD is not set # # shared options # CONFIG_CPUFREQ_ARCH_CUR_FREQ=y # end of CPU Frequency scaling # # CPU Idle # CONFIG_CPU_IDLE=y # CONFIG_CPU_IDLE_GOV_LADDER is not set CONFIG_CPU_IDLE_GOV_MENU=y # CONFIG_CPU_IDLE_GOV_TEO is not set CONFIG_CPU_IDLE_GOV_HALTPOLL=y CONFIG_HALTPOLL_CPUIDLE=y # end of CPU Idle CONFIG_INTEL_IDLE=y # end of Power management and ACPI options # # Bus options (PCI etc.) # CONFIG_PCI_DIRECT=y CONFIG_PCI_MMCONFIG=y CONFIG_MMCONF_FAM10H=y # CONFIG_ISA_BUS is not set CONFIG_ISA_DMA_API=y CONFIG_AMD_NB=y CONFIG_AMD_NODE=y # end of Bus options (PCI etc.) # # Binary Emulations # CONFIG_IA32_EMULATION=y # CONFIG_IA32_EMULATION_DEFAULT_DISABLED is not set CONFIG_COMPAT_32=y CONFIG_COMPAT=y CONFIG_COMPAT_FOR_U64_ALIGNMENT=y # end of Binary Emulations CONFIG_VIRTUALIZATION=y # CONFIG_KVM is not set CONFIG_X86_REQUIRED_FEATURE_ALWAYS=y CONFIG_X86_REQUIRED_FEATURE_NOPL=y CONFIG_X86_REQUIRED_FEATURE_CX8=y CONFIG_X86_REQUIRED_FEATURE_CMOV=y CONFIG_X86_REQUIRED_FEATURE_SYSFAST32=y CONFIG_X86_REQUIRED_FEATURE_CPUID=y CONFIG_X86_REQUIRED_FEATURE_FPU=y CONFIG_X86_REQUIRED_FEATURE_PAE=y CONFIG_X86_REQUIRED_FEATURE_PSE=y CONFIG_X86_REQUIRED_FEATURE_PGE=y CONFIG_X86_REQUIRED_FEATURE_MSR=y CONFIG_X86_REQUIRED_FEATURE_FXSR=y CONFIG_X86_REQUIRED_FEATURE_XMM=y CONFIG_X86_REQUIRED_FEATURE_XMM2=y CONFIG_X86_REQUIRED_FEATURE_LM=y CONFIG_X86_DISABLED_FEATURE_VME=y CONFIG_X86_DISABLED_FEATURE_K6_MTRR=y CONFIG_X86_DISABLED_FEATURE_CYRIX_ARR=y CONFIG_X86_DISABLED_FEATURE_CENTAUR_MCR=y CONFIG_X86_DISABLED_FEATURE_LAM=y CONFIG_X86_DISABLED_FEATURE_ENQCMD=y CONFIG_X86_DISABLED_FEATURE_SGX=y CONFIG_X86_DISABLED_FEATURE_XENPV=y CONFIG_X86_DISABLED_FEATURE_TDX_GUEST=y CONFIG_X86_DISABLED_FEATURE_USER_SHSTK=y CONFIG_X86_DISABLED_FEATURE_FRED=y CONFIG_X86_DISABLED_FEATURE_SEV_SNP=y CONFIG_AS_WRUSS=y CONFIG_ARCH_CONFIGURES_CPU_MITIGATIONS=y # # General architecture-dependent options # CONFIG_HOTPLUG_SMT=y CONFIG_ARCH_SUPPORTS_SCHED_SMT=y CONFIG_ARCH_SUPPORTS_SCHED_CLUSTER=y CONFIG_ARCH_SUPPORTS_SCHED_MC=y CONFIG_SCHED_SMT=y CONFIG_SCHED_CLUSTER=y CONFIG_SCHED_MC=y CONFIG_HOTPLUG_CORE_SYNC=y CONFIG_HOTPLUG_CORE_SYNC_DEAD=y CONFIG_HOTPLUG_CORE_SYNC_FULL=y CONFIG_HOTPLUG_SPLIT_STARTUP=y CONFIG_HOTPLUG_PARALLEL=y CONFIG_GENERIC_IRQ_ENTRY=y CONFIG_GENERIC_SYSCALL=y CONFIG_GENERIC_ENTRY=y # CONFIG_KPROBES is not set CONFIG_JUMP_LABEL=y # CONFIG_STATIC_KEYS_SELFTEST is not set # CONFIG_STATIC_CALL_SELFTEST is not set CONFIG_UPROBES=y CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y CONFIG_ARCH_USE_BUILTIN_BSWAP=y CONFIG_HAVE_IOREMAP_PROT=y CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y CONFIG_HAVE_OPTPROBES=y CONFIG_HAVE_KPROBES_ON_FTRACE=y CONFIG_ARCH_CORRECT_STACKTRACE_ON_KRETPROBE=y CONFIG_HAVE_FUNCTION_ERROR_INJECTION=y CONFIG_HAVE_NMI=y CONFIG_TRACE_IRQFLAGS_SUPPORT=y CONFIG_TRACE_IRQFLAGS_NMI_SUPPORT=y CONFIG_HAVE_ARCH_TRACEHOOK=y CONFIG_HAVE_DMA_CONTIGUOUS=y CONFIG_GENERIC_SMP_IDLE_THREAD=y CONFIG_ARCH_HAS_FORTIFY_SOURCE=y CONFIG_ARCH_HAS_SET_MEMORY=y CONFIG_ARCH_HAS_SET_DIRECT_MAP=y CONFIG_ARCH_HAS_CPU_FINALIZE_INIT=y CONFIG_ARCH_HAS_CPU_PASID=y CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST=y CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT=y CONFIG_ARCH_WANTS_NO_INSTR=y CONFIG_HAVE_ASM_MODVERSIONS=y CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y CONFIG_HAVE_RSEQ=y CONFIG_HAVE_RUST=y CONFIG_HAVE_FUNCTION_ARG_ACCESS_API=y CONFIG_HAVE_HW_BREAKPOINT=y CONFIG_HAVE_MIXED_BREAKPOINTS_REGS=y CONFIG_HAVE_USER_RETURN_NOTIFIER=y CONFIG_HAVE_PERF_EVENTS_NMI=y CONFIG_HAVE_HARDLOCKUP_DETECTOR_PERF=y CONFIG_UNWIND_USER=y CONFIG_HAVE_UNWIND_USER_FP=y CONFIG_HAVE_PERF_REGS=y CONFIG_HAVE_PERF_USER_STACK_DUMP=y CONFIG_HAVE_ARCH_JUMP_LABEL=y CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE=y CONFIG_MMU_GATHER_TABLE_FREE=y CONFIG_MMU_GATHER_RCU_TABLE_FREE=y CONFIG_MMU_GATHER_MERGE_VMAS=y CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM=y CONFIG_MMU_LAZY_TLB_REFCOUNT=y CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y CONFIG_ARCH_HAVE_EXTRA_ELF_NOTES=y CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS=y CONFIG_HAVE_ALIGNED_STRUCT_PAGE=y CONFIG_HAVE_CMPXCHG_LOCAL=y CONFIG_HAVE_CMPXCHG_DOUBLE=y CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION=y CONFIG_ARCH_WANT_OLD_COMPAT_IPC=y CONFIG_HAVE_ARCH_SECCOMP=y CONFIG_HAVE_ARCH_SECCOMP_FILTER=y CONFIG_SECCOMP=y CONFIG_SECCOMP_FILTER=y # CONFIG_SECCOMP_CACHE_DEBUG is not set CONFIG_HAVE_ARCH_KSTACK_ERASE=y CONFIG_HAVE_STACKPROTECTOR=y CONFIG_STACKPROTECTOR=y CONFIG_STACKPROTECTOR_STRONG=y CONFIG_ARCH_SUPPORTS_LTO_CLANG=y CONFIG_ARCH_SUPPORTS_LTO_CLANG_THIN=y CONFIG_HAS_LTO_CLANG=y CONFIG_LTO_NONE=y # CONFIG_LTO_CLANG_FULL is not set # CONFIG_LTO_CLANG_THIN is not set CONFIG_ARCH_SUPPORTS_AUTOFDO_CLANG=y CONFIG_AUTOFDO_CLANG=y CONFIG_ARCH_SUPPORTS_PROPELLER_CLANG=y CONFIG_PROPELLER_CLANG=y CONFIG_ARCH_SUPPORTS_CFI=y # CONFIG_CFI is not set CONFIG_HAVE_CFI_ICALL_NORMALIZE_INTEGERS=y CONFIG_HAVE_CFI_ICALL_NORMALIZE_INTEGERS_RUSTC=y CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES=y CONFIG_HAVE_CONTEXT_TRACKING_USER=y CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK=y CONFIG_HAVE_VIRT_CPU_ACCOUNTING_GEN=y CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y CONFIG_HAVE_PV_STEAL_CLOCK_GEN=y CONFIG_HAVE_MOVE_PUD=y CONFIG_HAVE_MOVE_PMD=y CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD=y CONFIG_HAVE_ARCH_HUGE_VMAP=y CONFIG_HAVE_ARCH_HUGE_VMALLOC=y CONFIG_ARCH_WANT_HUGE_PMD_SHARE=y CONFIG_HAVE_ARCH_SOFT_DIRTY=y CONFIG_HAVE_MOD_ARCH_SPECIFIC=y CONFIG_MODULES_USE_ELF_RELA=y CONFIG_ARCH_HAS_EXECMEM_ROX=y CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK=y CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK=y CONFIG_SOFTIRQ_ON_OWN_STACK=y CONFIG_ARCH_HAS_ELF_RANDOMIZE=y CONFIG_HAVE_ARCH_MMAP_RND_BITS=y CONFIG_HAVE_EXIT_THREAD=y CONFIG_ARCH_MMAP_RND_BITS=28 CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS=y CONFIG_ARCH_MMAP_RND_COMPAT_BITS=8 CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES=y CONFIG_HAVE_PAGE_SIZE_4KB=y CONFIG_PAGE_SIZE_4KB=y CONFIG_PAGE_SIZE_LESS_THAN_64KB=y CONFIG_PAGE_SIZE_LESS_THAN_256KB=y CONFIG_PAGE_SHIFT=12 CONFIG_HAVE_OBJTOOL=y CONFIG_HAVE_JUMP_LABEL_HACK=y CONFIG_HAVE_NOINSTR_HACK=y CONFIG_HAVE_NOINSTR_VALIDATION=y CONFIG_HAVE_UACCESS_VALIDATION=y CONFIG_HAVE_STACK_VALIDATION=y CONFIG_HAVE_RELIABLE_STACKTRACE=y CONFIG_OLD_SIGSUSPEND3=y CONFIG_COMPAT_OLD_SIGACTION=y CONFIG_COMPAT_32BIT_TIME=y CONFIG_ARCH_SUPPORTS_RT=y CONFIG_HAVE_ARCH_VMAP_STACK=y CONFIG_VMAP_STACK=y CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET=y CONFIG_RANDOMIZE_KSTACK_OFFSET=y # CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT is not set CONFIG_ARCH_HAS_STRICT_KERNEL_RWX=y CONFIG_STRICT_KERNEL_RWX=y CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y CONFIG_STRICT_MODULE_RWX=y CONFIG_HAVE_ARCH_PREL32_RELOCATIONS=y # CONFIG_LOCK_EVENT_COUNTS is not set CONFIG_ARCH_HAS_MEM_ENCRYPT=y CONFIG_HAVE_STATIC_CALL=y CONFIG_HAVE_STATIC_CALL_INLINE=y CONFIG_HAVE_PREEMPT_DYNAMIC=y CONFIG_HAVE_PREEMPT_DYNAMIC_CALL=y CONFIG_ARCH_WANT_LD_ORPHAN_WARN=y CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y CONFIG_ARCH_SUPPORTS_PAGE_TABLE_CHECK=y CONFIG_ARCH_HAS_ELFCORE_COMPAT=y CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH=y CONFIG_DYNAMIC_SIGFRAME=y CONFIG_ARCH_HAS_HW_PTE_YOUNG=y CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG=y CONFIG_ARCH_HAS_KERNEL_FPU_SUPPORT=y CONFIG_HAVE_GENERIC_TIF_BITS=y # # GCOV-based kernel profiling # # CONFIG_GCOV_KERNEL is not set CONFIG_ARCH_HAS_GCOV_PROFILE_ALL=y # end of GCOV-based kernel profiling CONFIG_HAVE_GCC_PLUGINS=y CONFIG_FUNCTION_ALIGNMENT_4B=y CONFIG_FUNCTION_ALIGNMENT_16B=y CONFIG_FUNCTION_ALIGNMENT=16 CONFIG_CC_HAS_SANE_FUNCTION_ALIGNMENT=y CONFIG_ARCH_HAS_CPU_ATTACK_VECTORS=y # end of General architecture-dependent options CONFIG_RT_MUTEXES=y CONFIG_MODULES=y # CONFIG_MODULE_DEBUG is not set # CONFIG_MODULE_FORCE_LOAD is not set CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_MODULE_UNLOAD_TAINT_TRACKING is not set CONFIG_MODVERSIONS=y # CONFIG_GENKSYMS is not set CONFIG_GENDWARFKSYMS=y CONFIG_ASM_MODVERSIONS=y # CONFIG_EXTENDED_MODVERSIONS is not set # CONFIG_BASIC_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set # CONFIG_MODULE_SIG is not set # CONFIG_MODULE_COMPRESS is not set # CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS is not set CONFIG_MODPROBE_PATH="/sbin/modprobe" # CONFIG_TRIM_UNUSED_KSYMS is not set CONFIG_MODULES_TREE_LOOKUP=y CONFIG_BLOCK=y CONFIG_BLOCK_LEGACY_AUTOLOAD=y CONFIG_BLK_RQ_ALLOC_TIME=y CONFIG_BLK_DEV_BSG_COMMON=y CONFIG_BLK_DEV_BSGLIB=y # CONFIG_BLK_DEV_INTEGRITY is not set # CONFIG_BLK_DEV_WRITE_MOUNTED is not set # CONFIG_BLK_DEV_ZONED is not set # CONFIG_BLK_DEV_THROTTLING is not set # CONFIG_BLK_WBT is not set CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y CONFIG_BLK_CGROUP_IOPRIO=y CONFIG_BLK_DEBUG_FS=y # CONFIG_BLK_SED_OPAL is not set # CONFIG_BLK_INLINE_ENCRYPTION is not set # # Partition Types # # CONFIG_PARTITION_ADVANCED is not set CONFIG_MSDOS_PARTITION=y CONFIG_EFI_PARTITION=y # end of Partition Types CONFIG_BLK_PM=y CONFIG_BLOCK_HOLDER_DEPRECATED=y CONFIG_BLK_MQ_STACKING=y # # IO Schedulers # CONFIG_MQ_IOSCHED_DEADLINE=y CONFIG_MQ_IOSCHED_KYBER=y # CONFIG_IOSCHED_BFQ is not set # end of IO Schedulers CONFIG_PADATA=y CONFIG_ASN1=y CONFIG_UNINLINE_SPIN_UNLOCK=y CONFIG_ARCH_SUPPORTS_ATOMIC_RMW=y CONFIG_MUTEX_SPIN_ON_OWNER=y CONFIG_RWSEM_SPIN_ON_OWNER=y CONFIG_LOCK_SPIN_ON_OWNER=y CONFIG_ARCH_USE_QUEUED_SPINLOCKS=y CONFIG_QUEUED_SPINLOCKS=y CONFIG_ARCH_USE_QUEUED_RWLOCKS=y CONFIG_QUEUED_RWLOCKS=y CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE=y CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE=y CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y CONFIG_FREEZER=y # # Executable file formats # CONFIG_BINFMT_ELF=y CONFIG_COMPAT_BINFMT_ELF=y CONFIG_ELFCORE=y CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y CONFIG_BINFMT_SCRIPT=y CONFIG_BINFMT_MISC=y CONFIG_COREDUMP=y # end of Executable file formats # # Memory Management options # CONFIG_SWAP=y # CONFIG_ZSWAP is not set # # Slab allocator options # CONFIG_SLUB=y CONFIG_KVFREE_RCU_BATCHED=y # CONFIG_SLUB_TINY is not set CONFIG_SLAB_MERGE_DEFAULT=y # CONFIG_SLAB_FREELIST_RANDOM is not set # CONFIG_SLAB_FREELIST_HARDENED is not set # CONFIG_SLAB_BUCKETS is not set # CONFIG_SLUB_STATS is not set # CONFIG_RANDOM_KMALLOC_CACHES is not set # end of Slab allocator options # CONFIG_SHUFFLE_PAGE_ALLOCATOR is not set # CONFIG_COMPAT_BRK is not set CONFIG_SPARSEMEM=y CONFIG_SPARSEMEM_EXTREME=y CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y CONFIG_SPARSEMEM_VMEMMAP=y CONFIG_SPARSEMEM_VMEMMAP_PREINIT=y CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP=y CONFIG_ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP=y CONFIG_ARCH_WANT_HUGETLB_VMEMMAP_PREINIT=y CONFIG_HAVE_GUP_FAST=y CONFIG_EXCLUSIVE_SYSTEM_RAM=y CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y # CONFIG_MEMORY_HOTPLUG is not set CONFIG_ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE=y CONFIG_SPLIT_PTE_PTLOCKS=y CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y CONFIG_SPLIT_PMD_PTLOCKS=y CONFIG_COMPACTION=y CONFIG_COMPACT_UNEVICTABLE_DEFAULT=1 # CONFIG_PAGE_REPORTING is not set CONFIG_NUMA_MIGRATION=y CONFIG_MIGRATION=y CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION=y CONFIG_PCP_BATCH_SCALE_MAX=5 CONFIG_PHYS_ADDR_T_64BIT=y CONFIG_MMU_NOTIFIER=y # CONFIG_KSM is not set CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 CONFIG_ARCH_SUPPORTS_MEMORY_FAILURE=y # CONFIG_MEMORY_FAILURE is not set CONFIG_ARCH_WANT_GENERAL_HUGETLB=y CONFIG_ARCH_WANTS_THP_SWAP=y # CONFIG_TRANSPARENT_HUGEPAGE is not set CONFIG_PAGE_MAPCOUNT=y CONFIG_PGTABLE_HAS_HUGE_LEAVES=y CONFIG_HAVE_GIGANTIC_FOLIOS=y CONFIG_ASYNC_KERNEL_PGTABLE_FREE=y CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y CONFIG_USE_PERCPU_NUMA_NODE_ID=y CONFIG_HAVE_SETUP_PER_CPU_AREA=y # CONFIG_CMA is not set CONFIG_PAGE_BLOCK_MAX_ORDER=10 CONFIG_GENERIC_EARLY_IOREMAP=y # CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set # CONFIG_IDLE_PAGE_TRACKING is not set CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y CONFIG_ARCH_HAS_CURRENT_STACK_POINTER=y CONFIG_ARCH_HAS_ZONE_DMA_SET=y CONFIG_ZONE_DMA=y CONFIG_ZONE_DMA32=y CONFIG_HMM_MIRROR=y CONFIG_VMAP_PFN=y CONFIG_ARCH_USES_HIGH_VMA_FLAGS=y CONFIG_ARCH_HAS_PKEYS=y CONFIG_ARCH_USES_PG_ARCH_2=y CONFIG_VM_EVENT_COUNTERS=y # CONFIG_PERCPU_STATS is not set # CONFIG_GUP_TEST is not set # CONFIG_DMAPOOL_TEST is not set CONFIG_ARCH_HAS_PTE_SPECIAL=y CONFIG_MEMFD_CREATE=y CONFIG_SECRETMEM=y # CONFIG_ANON_VMA_NAME is not set # CONFIG_USERFAULTFD is not set CONFIG_LRU_GEN=y CONFIG_LRU_GEN_ENABLED=y # CONFIG_LRU_GEN_STATS is not set CONFIG_LRU_GEN_WALKS_MMU=y CONFIG_ARCH_SUPPORTS_PER_VMA_LOCK=y CONFIG_PER_VMA_LOCK=y CONFIG_LOCK_MM_AND_FIND_VMA=y CONFIG_IOMMU_MM_DATA=y CONFIG_EXECMEM=y CONFIG_NUMA_MEMBLKS=y # CONFIG_NUMA_EMU is not set CONFIG_PT_RECLAIM=y # # Data Access Monitoring # # CONFIG_DAMON is not set # end of Data Access Monitoring # end of Memory Management options CONFIG_NET=y CONFIG_WANT_COMPAT_NETLINK_MESSAGES=y CONFIG_COMPAT_NETLINK_MESSAGES=y CONFIG_NET_INGRESS=y CONFIG_NET_EGRESS=y CONFIG_NET_XGRESS=y CONFIG_NET_REDIRECT=y CONFIG_SKB_DECRYPTED=y CONFIG_SKB_EXTENSIONS=y CONFIG_NET_DEVMEM=y CONFIG_NET_SHAPER=y CONFIG_NET_CRC32C=y # # Networking options # CONFIG_PACKET=y CONFIG_PACKET_DIAG=y CONFIG_INET_PSP=y CONFIG_UNIX=y CONFIG_AF_UNIX_OOB=y CONFIG_UNIX_DIAG=y CONFIG_TLS=y CONFIG_TLS_DEVICE=y CONFIG_TLS_TOE=y CONFIG_XFRM=y CONFIG_XFRM_OFFLOAD=y CONFIG_XFRM_ALGO=y CONFIG_XFRM_USER=y CONFIG_XFRM_USER_COMPAT=y CONFIG_XFRM_INTERFACE=y CONFIG_XFRM_SUB_POLICY=y CONFIG_XFRM_MIGRATE=y CONFIG_XFRM_STATISTICS=y CONFIG_XFRM_AH=y CONFIG_XFRM_ESP=y CONFIG_XFRM_IPCOMP=y CONFIG_NET_KEY=y CONFIG_NET_KEY_MIGRATE=y # CONFIG_XFRM_IPTFS is not set CONFIG_XFRM_ESPINTCP=y CONFIG_SMC=y CONFIG_SMC_DIAG=y # CONFIG_SMC_HS_CTRL_BPF is not set CONFIG_DIBS=y CONFIG_DIBS_LO=y CONFIG_XDP_SOCKETS=y CONFIG_XDP_SOCKETS_DIAG=y CONFIG_NET_HANDSHAKE=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_FIB_TRIE_STATS=y CONFIG_IP_MULTIPLE_TABLES=y CONFIG_IP_ROUTE_MULTIPATH=y CONFIG_IP_ROUTE_VERBOSE=y CONFIG_IP_ROUTE_CLASSID=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NET_IPIP=y CONFIG_NET_IPGRE_DEMUX=y CONFIG_NET_IP_TUNNEL=y CONFIG_NET_IPGRE=y CONFIG_NET_IPGRE_BROADCAST=y CONFIG_IP_MROUTE_COMMON=y CONFIG_IP_MROUTE=y CONFIG_IP_MROUTE_MULTIPLE_TABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=y CONFIG_NET_UDP_TUNNEL=y CONFIG_NET_FOU=y CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_INET_AH=y CONFIG_INET_ESP=y CONFIG_INET_ESP_OFFLOAD=y CONFIG_INET_ESPINTCP=y CONFIG_INET_IPCOMP=y CONFIG_INET_TABLE_PERTURB_ORDER=16 CONFIG_INET_XFRM_TUNNEL=y CONFIG_INET_TUNNEL=y CONFIG_INET_DIAG=y CONFIG_INET_TCP_DIAG=y CONFIG_INET_UDP_DIAG=y CONFIG_INET_RAW_DIAG=y CONFIG_INET_DIAG_DESTROY=y CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_CONG_BIC=y CONFIG_TCP_CONG_CUBIC=y CONFIG_TCP_CONG_WESTWOOD=y CONFIG_TCP_CONG_HTCP=y CONFIG_TCP_CONG_HSTCP=y CONFIG_TCP_CONG_HYBLA=y CONFIG_TCP_CONG_VEGAS=y CONFIG_TCP_CONG_NV=y CONFIG_TCP_CONG_SCALABLE=y CONFIG_TCP_CONG_LP=y CONFIG_TCP_CONG_VENO=y CONFIG_TCP_CONG_YEAH=y CONFIG_TCP_CONG_ILLINOIS=y CONFIG_TCP_CONG_DCTCP=y CONFIG_TCP_CONG_CDG=y CONFIG_TCP_CONG_BBR=y # CONFIG_DEFAULT_BIC is not set CONFIG_DEFAULT_CUBIC=y # CONFIG_DEFAULT_HTCP is not set # CONFIG_DEFAULT_HYBLA is not set # CONFIG_DEFAULT_VEGAS is not set # CONFIG_DEFAULT_VENO is not set # CONFIG_DEFAULT_WESTWOOD is not set # CONFIG_DEFAULT_DCTCP is not set # CONFIG_DEFAULT_CDG is not set # CONFIG_DEFAULT_BBR is not set # CONFIG_DEFAULT_RENO is not set CONFIG_DEFAULT_TCP_CONG="cubic" # CONFIG_TCP_AO is not set CONFIG_TCP_MD5SIG=y CONFIG_IPV6=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y CONFIG_IPV6_OPTIMISTIC_DAD=y CONFIG_INET6_AH=y CONFIG_INET6_ESP=y CONFIG_INET6_ESP_OFFLOAD=y CONFIG_INET6_ESPINTCP=y CONFIG_INET6_IPCOMP=y CONFIG_IPV6_MIP6=y CONFIG_IPV6_ILA=y CONFIG_INET6_XFRM_TUNNEL=y CONFIG_INET6_TUNNEL=y CONFIG_IPV6_VTI=y CONFIG_IPV6_SIT=y CONFIG_IPV6_SIT_6RD=y CONFIG_IPV6_NDISC_NODETYPE=y CONFIG_IPV6_TUNNEL=y CONFIG_IPV6_GRE=y CONFIG_IPV6_FOU=y CONFIG_IPV6_FOU_TUNNEL=y CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_SUBTREES=y CONFIG_IPV6_MROUTE=y CONFIG_IPV6_MROUTE_MULTIPLE_TABLES=y CONFIG_IPV6_PIMSM_V2=y CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPV6_SEG6_HMAC=y CONFIG_IPV6_SEG6_BPF=y CONFIG_IPV6_RPL_LWTUNNEL=y # CONFIG_IPV6_IOAM6_LWTUNNEL is not set CONFIG_NETLABEL=y CONFIG_MPTCP=y CONFIG_INET_MPTCP_DIAG=y CONFIG_MPTCP_IPV6=y CONFIG_NETWORK_SECMARK=y CONFIG_NET_PTP_CLASSIFY=y # CONFIG_NETWORK_PHY_TIMESTAMPING is not set CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_BRIDGE_NETFILTER=y # # Core Netfilter Configuration # CONFIG_NETFILTER_INGRESS=y CONFIG_NETFILTER_EGRESS=y CONFIG_NETFILTER_SKIP_EGRESS=y CONFIG_NETFILTER_NETLINK=y CONFIG_NETFILTER_FAMILY_BRIDGE=y CONFIG_NETFILTER_FAMILY_ARP=y CONFIG_NETFILTER_BPF_LINK=y # CONFIG_NETFILTER_NETLINK_HOOK is not set CONFIG_NETFILTER_NETLINK_ACCT=y CONFIG_NETFILTER_NETLINK_QUEUE=y CONFIG_NETFILTER_NETLINK_LOG=y CONFIG_NETFILTER_NETLINK_OSF=y CONFIG_NF_CONNTRACK=y CONFIG_NF_LOG_SYSLOG=y CONFIG_NETFILTER_CONNCOUNT=y CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_ZONES=y # CONFIG_NF_CONNTRACK_PROCFS is not set CONFIG_NF_CONNTRACK_EVENTS=y CONFIG_NF_CONNTRACK_TIMEOUT=y CONFIG_NF_CONNTRACK_TIMESTAMP=y CONFIG_NF_CONNTRACK_LABELS=y CONFIG_NF_CONNTRACK_OVS=y CONFIG_NF_CT_PROTO_GRE=y CONFIG_NF_CT_PROTO_SCTP=y CONFIG_NF_CONNTRACK_AMANDA=y CONFIG_NF_CONNTRACK_FTP=y CONFIG_NF_CONNTRACK_H323=y CONFIG_NF_CONNTRACK_IRC=y CONFIG_NF_CONNTRACK_BROADCAST=y CONFIG_NF_CONNTRACK_NETBIOS_NS=y CONFIG_NF_CONNTRACK_SNMP=y CONFIG_NF_CONNTRACK_PPTP=y CONFIG_NF_CONNTRACK_SANE=y CONFIG_NF_CONNTRACK_SIP=y CONFIG_NF_CONNTRACK_TFTP=y CONFIG_NF_CT_NETLINK=y CONFIG_NF_CT_NETLINK_TIMEOUT=y CONFIG_NF_CT_NETLINK_HELPER=y CONFIG_NETFILTER_NETLINK_GLUE_CT=y CONFIG_NF_NAT=y CONFIG_NF_NAT_AMANDA=y CONFIG_NF_NAT_FTP=y CONFIG_NF_NAT_IRC=y CONFIG_NF_NAT_SIP=y CONFIG_NF_NAT_TFTP=y CONFIG_NF_NAT_REDIRECT=y CONFIG_NF_NAT_MASQUERADE=y CONFIG_NF_NAT_OVS=y CONFIG_NETFILTER_SYNPROXY=y CONFIG_NF_TABLES=y CONFIG_NF_TABLES_INET=y CONFIG_NF_TABLES_NETDEV=y CONFIG_NFT_NUMGEN=y CONFIG_NFT_CT=y CONFIG_NFT_EXTHDR_DCCP=y CONFIG_NFT_FLOW_OFFLOAD=y CONFIG_NFT_CONNLIMIT=y CONFIG_NFT_LOG=y CONFIG_NFT_LIMIT=y CONFIG_NFT_MASQ=y CONFIG_NFT_REDIR=y CONFIG_NFT_NAT=y CONFIG_NFT_TUNNEL=y CONFIG_NFT_QUEUE=y CONFIG_NFT_QUOTA=y CONFIG_NFT_REJECT=y CONFIG_NFT_REJECT_INET=y CONFIG_NFT_COMPAT=y CONFIG_NFT_HASH=y CONFIG_NFT_FIB=y CONFIG_NFT_FIB_INET=y CONFIG_NFT_XFRM=y CONFIG_NFT_SOCKET=y CONFIG_NFT_OSF=y CONFIG_NFT_TPROXY=y CONFIG_NFT_SYNPROXY=y CONFIG_NF_DUP_NETDEV=y CONFIG_NFT_DUP_NETDEV=y CONFIG_NFT_FWD_NETDEV=y CONFIG_NFT_FIB_NETDEV=y CONFIG_NFT_REJECT_NETDEV=y CONFIG_NF_FLOW_TABLE_INET=y CONFIG_NF_FLOW_TABLE=y # CONFIG_NF_FLOW_TABLE_PROCFS is not set CONFIG_NETFILTER_XTABLES=y CONFIG_NETFILTER_XTABLES_COMPAT=y CONFIG_NETFILTER_XTABLES_LEGACY=y # # Xtables combined modules # CONFIG_NETFILTER_XT_MARK=y CONFIG_NETFILTER_XT_CONNMARK=y CONFIG_NETFILTER_XT_SET=y # # Xtables targets # CONFIG_NETFILTER_XT_TARGET_AUDIT=y CONFIG_NETFILTER_XT_TARGET_CHECKSUM=y CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y CONFIG_NETFILTER_XT_TARGET_CONNMARK=y CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y CONFIG_NETFILTER_XT_TARGET_CT=y CONFIG_NETFILTER_XT_TARGET_DSCP=y CONFIG_NETFILTER_XT_TARGET_HL=y CONFIG_NETFILTER_XT_TARGET_HMARK=y CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y CONFIG_NETFILTER_XT_TARGET_LED=y CONFIG_NETFILTER_XT_TARGET_LOG=y CONFIG_NETFILTER_XT_TARGET_MARK=y CONFIG_NETFILTER_XT_NAT=y CONFIG_NETFILTER_XT_TARGET_NETMAP=y CONFIG_NETFILTER_XT_TARGET_NFLOG=y CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y CONFIG_NETFILTER_XT_TARGET_NOTRACK=y CONFIG_NETFILTER_XT_TARGET_RATEEST=y CONFIG_NETFILTER_XT_TARGET_REDIRECT=y CONFIG_NETFILTER_XT_TARGET_MASQUERADE=y CONFIG_NETFILTER_XT_TARGET_TEE=y CONFIG_NETFILTER_XT_TARGET_TPROXY=y CONFIG_NETFILTER_XT_TARGET_TRACE=y CONFIG_NETFILTER_XT_TARGET_SECMARK=y CONFIG_NETFILTER_XT_TARGET_TCPMSS=y CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=y # # Xtables matches # CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=y CONFIG_NETFILTER_XT_MATCH_BPF=y CONFIG_NETFILTER_XT_MATCH_CGROUP=y CONFIG_NETFILTER_XT_MATCH_CLUSTER=y CONFIG_NETFILTER_XT_MATCH_COMMENT=y CONFIG_NETFILTER_XT_MATCH_CONNBYTES=y CONFIG_NETFILTER_XT_MATCH_CONNLABEL=y CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y CONFIG_NETFILTER_XT_MATCH_CONNMARK=y CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y CONFIG_NETFILTER_XT_MATCH_CPU=y CONFIG_NETFILTER_XT_MATCH_DCCP=y CONFIG_NETFILTER_XT_MATCH_DEVGROUP=y CONFIG_NETFILTER_XT_MATCH_DSCP=y CONFIG_NETFILTER_XT_MATCH_ECN=y CONFIG_NETFILTER_XT_MATCH_ESP=y CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y CONFIG_NETFILTER_XT_MATCH_HELPER=y CONFIG_NETFILTER_XT_MATCH_HL=y CONFIG_NETFILTER_XT_MATCH_IPCOMP=y CONFIG_NETFILTER_XT_MATCH_IPRANGE=y CONFIG_NETFILTER_XT_MATCH_IPVS=y CONFIG_NETFILTER_XT_MATCH_L2TP=y CONFIG_NETFILTER_XT_MATCH_LENGTH=y CONFIG_NETFILTER_XT_MATCH_LIMIT=y CONFIG_NETFILTER_XT_MATCH_MAC=y CONFIG_NETFILTER_XT_MATCH_MARK=y CONFIG_NETFILTER_XT_MATCH_MULTIPORT=y CONFIG_NETFILTER_XT_MATCH_NFACCT=y CONFIG_NETFILTER_XT_MATCH_OSF=y CONFIG_NETFILTER_XT_MATCH_OWNER=y CONFIG_NETFILTER_XT_MATCH_POLICY=y CONFIG_NETFILTER_XT_MATCH_PHYSDEV=y CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y CONFIG_NETFILTER_XT_MATCH_QUOTA=y CONFIG_NETFILTER_XT_MATCH_RATEEST=y CONFIG_NETFILTER_XT_MATCH_REALM=y CONFIG_NETFILTER_XT_MATCH_RECENT=y CONFIG_NETFILTER_XT_MATCH_SCTP=y CONFIG_NETFILTER_XT_MATCH_SOCKET=y CONFIG_NETFILTER_XT_MATCH_STATE=y CONFIG_NETFILTER_XT_MATCH_STATISTIC=y CONFIG_NETFILTER_XT_MATCH_STRING=y CONFIG_NETFILTER_XT_MATCH_TCPMSS=y CONFIG_NETFILTER_XT_MATCH_TIME=y CONFIG_NETFILTER_XT_MATCH_U32=y # end of Core Netfilter Configuration CONFIG_IP_SET=y CONFIG_IP_SET_MAX=256 CONFIG_IP_SET_BITMAP_IP=y CONFIG_IP_SET_BITMAP_IPMAC=y CONFIG_IP_SET_BITMAP_PORT=y CONFIG_IP_SET_HASH_IP=y CONFIG_IP_SET_HASH_IPMARK=y CONFIG_IP_SET_HASH_IPPORT=y CONFIG_IP_SET_HASH_IPPORTIP=y CONFIG_IP_SET_HASH_IPPORTNET=y CONFIG_IP_SET_HASH_IPMAC=y CONFIG_IP_SET_HASH_MAC=y CONFIG_IP_SET_HASH_NETPORTNET=y CONFIG_IP_SET_HASH_NET=y CONFIG_IP_SET_HASH_NETNET=y CONFIG_IP_SET_HASH_NETPORT=y CONFIG_IP_SET_HASH_NETIFACE=y CONFIG_IP_SET_LIST_SET=y CONFIG_IP_VS=y CONFIG_IP_VS_IPV6=y # CONFIG_IP_VS_DEBUG is not set CONFIG_IP_VS_TAB_BITS=12 # # IPVS transport protocol load balancing support # CONFIG_IP_VS_PROTO_TCP=y CONFIG_IP_VS_PROTO_UDP=y CONFIG_IP_VS_PROTO_AH_ESP=y CONFIG_IP_VS_PROTO_ESP=y CONFIG_IP_VS_PROTO_AH=y CONFIG_IP_VS_PROTO_SCTP=y # # IPVS scheduler # CONFIG_IP_VS_RR=y CONFIG_IP_VS_WRR=y CONFIG_IP_VS_LC=y CONFIG_IP_VS_WLC=y CONFIG_IP_VS_FO=y CONFIG_IP_VS_OVF=y CONFIG_IP_VS_LBLC=y CONFIG_IP_VS_LBLCR=y CONFIG_IP_VS_DH=y CONFIG_IP_VS_SH=y CONFIG_IP_VS_MH=y CONFIG_IP_VS_SED=y CONFIG_IP_VS_NQ=y CONFIG_IP_VS_TWOS=y # # IPVS SH scheduler # CONFIG_IP_VS_SH_TAB_BITS=8 # # IPVS MH scheduler # CONFIG_IP_VS_MH_TAB_INDEX=12 # # IPVS application helper # CONFIG_IP_VS_FTP=y CONFIG_IP_VS_NFCT=y CONFIG_IP_VS_PE_SIP=y # # IP: Netfilter Configuration # CONFIG_NF_DEFRAG_IPV4=y CONFIG_IP_NF_IPTABLES_LEGACY=y CONFIG_NF_SOCKET_IPV4=y CONFIG_NF_TPROXY_IPV4=y CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_REJECT_IPV4=y CONFIG_NFT_DUP_IPV4=y CONFIG_NFT_FIB_IPV4=y CONFIG_NF_TABLES_ARP=y CONFIG_NF_DUP_IPV4=y CONFIG_NF_LOG_ARP=y CONFIG_NF_LOG_IPV4=y CONFIG_NF_REJECT_IPV4=y CONFIG_NF_NAT_SNMP_BASIC=y CONFIG_NF_NAT_PPTP=y CONFIG_NF_NAT_H323=y CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_MATCH_AH=y CONFIG_IP_NF_MATCH_ECN=y CONFIG_IP_NF_MATCH_RPFILTER=y CONFIG_IP_NF_MATCH_TTL=y CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y CONFIG_IP_NF_TARGET_SYNPROXY=y CONFIG_IP_NF_NAT=y CONFIG_IP_NF_TARGET_MASQUERADE=y CONFIG_IP_NF_TARGET_NETMAP=y CONFIG_IP_NF_TARGET_REDIRECT=y CONFIG_IP_NF_MANGLE=y CONFIG_IP_NF_TARGET_ECN=y CONFIG_IP_NF_TARGET_TTL=y CONFIG_IP_NF_RAW=y CONFIG_IP_NF_SECURITY=y CONFIG_IP_NF_ARPTABLES=y CONFIG_NFT_COMPAT_ARP=y CONFIG_IP_NF_ARPFILTER=y CONFIG_IP_NF_ARP_MANGLE=y # end of IP: Netfilter Configuration # # IPv6: Netfilter Configuration # CONFIG_IP6_NF_IPTABLES_LEGACY=y CONFIG_NF_SOCKET_IPV6=y CONFIG_NF_TPROXY_IPV6=y CONFIG_NF_TABLES_IPV6=y CONFIG_NFT_REJECT_IPV6=y CONFIG_NFT_DUP_IPV6=y CONFIG_NFT_FIB_IPV6=y CONFIG_NF_DUP_IPV6=y CONFIG_NF_REJECT_IPV6=y CONFIG_NF_LOG_IPV6=y CONFIG_IP6_NF_IPTABLES=y CONFIG_IP6_NF_MATCH_AH=y CONFIG_IP6_NF_MATCH_EUI64=y CONFIG_IP6_NF_MATCH_FRAG=y CONFIG_IP6_NF_MATCH_OPTS=y CONFIG_IP6_NF_MATCH_HL=y CONFIG_IP6_NF_MATCH_IPV6HEADER=y CONFIG_IP6_NF_MATCH_MH=y CONFIG_IP6_NF_MATCH_RPFILTER=y CONFIG_IP6_NF_MATCH_RT=y CONFIG_IP6_NF_MATCH_SRH=y CONFIG_IP6_NF_TARGET_HL=y CONFIG_IP6_NF_FILTER=y CONFIG_IP6_NF_TARGET_REJECT=y CONFIG_IP6_NF_TARGET_SYNPROXY=y CONFIG_IP6_NF_MANGLE=y CONFIG_IP6_NF_RAW=y CONFIG_IP6_NF_SECURITY=y CONFIG_IP6_NF_NAT=y CONFIG_IP6_NF_TARGET_MASQUERADE=y CONFIG_IP6_NF_TARGET_NPT=y # end of IPv6: Netfilter Configuration CONFIG_NF_DEFRAG_IPV6=y CONFIG_NF_TABLES_BRIDGE=y CONFIG_NFT_BRIDGE_META=y CONFIG_NFT_BRIDGE_REJECT=y CONFIG_NF_CONNTRACK_BRIDGE=y CONFIG_BRIDGE_NF_EBTABLES_LEGACY=y CONFIG_BRIDGE_NF_EBTABLES=y CONFIG_BRIDGE_EBT_BROUTE=y CONFIG_BRIDGE_EBT_T_FILTER=y CONFIG_BRIDGE_EBT_T_NAT=y CONFIG_BRIDGE_EBT_802_3=y CONFIG_BRIDGE_EBT_AMONG=y CONFIG_BRIDGE_EBT_ARP=y CONFIG_BRIDGE_EBT_IP=y CONFIG_BRIDGE_EBT_IP6=y CONFIG_BRIDGE_EBT_LIMIT=y CONFIG_BRIDGE_EBT_MARK=y CONFIG_BRIDGE_EBT_PKTTYPE=y CONFIG_BRIDGE_EBT_STP=y CONFIG_BRIDGE_EBT_VLAN=y CONFIG_BRIDGE_EBT_ARPREPLY=y CONFIG_BRIDGE_EBT_DNAT=y CONFIG_BRIDGE_EBT_MARK_T=y CONFIG_BRIDGE_EBT_REDIRECT=y CONFIG_BRIDGE_EBT_SNAT=y CONFIG_BRIDGE_EBT_LOG=y CONFIG_BRIDGE_EBT_NFLOG=y CONFIG_IP_SCTP=y # CONFIG_SCTP_DBG_OBJCNT is not set CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA256=y # CONFIG_SCTP_DEFAULT_COOKIE_HMAC_NONE is not set CONFIG_INET_SCTP_DIAG=y CONFIG_RDS=y CONFIG_RDS_RDMA=y CONFIG_RDS_TCP=y # CONFIG_RDS_DEBUG is not set CONFIG_TIPC=y CONFIG_TIPC_MEDIA_IB=y CONFIG_TIPC_MEDIA_UDP=y CONFIG_TIPC_CRYPTO=y CONFIG_TIPC_DIAG=y CONFIG_ATM=y CONFIG_ATM_BR2684=y # CONFIG_ATM_BR2684_IPFILTER is not set CONFIG_L2TP=y # CONFIG_L2TP_DEBUGFS is not set CONFIG_L2TP_V3=y CONFIG_L2TP_IP=y CONFIG_L2TP_ETH=y CONFIG_STP=y CONFIG_GARP=y CONFIG_MRP=y CONFIG_BRIDGE=y CONFIG_BRIDGE_IGMP_SNOOPING=y CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_BRIDGE_MRP=y CONFIG_BRIDGE_CFM=y CONFIG_NET_DSA=y # CONFIG_NET_DSA_TAG_NONE is not set # CONFIG_NET_DSA_TAG_AR9331 is not set CONFIG_NET_DSA_TAG_BRCM_COMMON=y CONFIG_NET_DSA_TAG_BRCM=y # CONFIG_NET_DSA_TAG_BRCM_LEGACY is not set # CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS is not set CONFIG_NET_DSA_TAG_BRCM_PREPEND=y # CONFIG_NET_DSA_TAG_HELLCREEK is not set # CONFIG_NET_DSA_TAG_GSWIP is not set # CONFIG_NET_DSA_TAG_DSA is not set # CONFIG_NET_DSA_TAG_EDSA is not set CONFIG_NET_DSA_TAG_MTK=y # CONFIG_NET_DSA_TAG_MXL_862XX is not set # CONFIG_NET_DSA_TAG_MXL_GSW1XX is not set # CONFIG_NET_DSA_TAG_KSZ is not set # CONFIG_NET_DSA_TAG_OCELOT is not set # CONFIG_NET_DSA_TAG_OCELOT_8021Q is not set CONFIG_NET_DSA_TAG_QCA=y CONFIG_NET_DSA_TAG_RTL4_A=y # CONFIG_NET_DSA_TAG_RTL8_4 is not set # CONFIG_NET_DSA_TAG_RZN1_A5PSW is not set # CONFIG_NET_DSA_TAG_LAN9303 is not set # CONFIG_NET_DSA_TAG_SJA1105 is not set # CONFIG_NET_DSA_TAG_TRAILER is not set # CONFIG_NET_DSA_TAG_VSC73XX_8021Q is not set # CONFIG_NET_DSA_TAG_XRS700X is not set # CONFIG_NET_DSA_TAG_YT921X is not set CONFIG_VLAN_8021Q=y CONFIG_VLAN_8021Q_GVRP=y CONFIG_VLAN_8021Q_MVRP=y CONFIG_LLC=y CONFIG_LLC2=y # CONFIG_ATALK is not set CONFIG_X25=y CONFIG_LAPB=y CONFIG_PHONET=y CONFIG_6LOWPAN=y # CONFIG_6LOWPAN_DEBUGFS is not set CONFIG_6LOWPAN_NHC=y CONFIG_6LOWPAN_NHC_DEST=y CONFIG_6LOWPAN_NHC_FRAGMENT=y CONFIG_6LOWPAN_NHC_HOP=y CONFIG_6LOWPAN_NHC_IPV6=y CONFIG_6LOWPAN_NHC_MOBILITY=y CONFIG_6LOWPAN_NHC_ROUTING=y CONFIG_6LOWPAN_NHC_UDP=y CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=y CONFIG_6LOWPAN_GHC_UDP=y CONFIG_6LOWPAN_GHC_ICMPV6=y CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=y CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=y CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=y CONFIG_IEEE802154=y CONFIG_IEEE802154_NL802154_EXPERIMENTAL=y CONFIG_IEEE802154_SOCKET=y CONFIG_IEEE802154_6LOWPAN=y CONFIG_MAC802154=y CONFIG_NET_SCHED=y # # Queueing/Scheduling # CONFIG_NET_SCH_HTB=y CONFIG_NET_SCH_HFSC=y CONFIG_NET_SCH_PRIO=y CONFIG_NET_SCH_MULTIQ=y CONFIG_NET_SCH_RED=y CONFIG_NET_SCH_SFB=y CONFIG_NET_SCH_SFQ=y CONFIG_NET_SCH_TEQL=y CONFIG_NET_SCH_TBF=y CONFIG_NET_SCH_CBS=y CONFIG_NET_SCH_ETF=y CONFIG_NET_SCH_MQPRIO_LIB=y CONFIG_NET_SCH_TAPRIO=y CONFIG_NET_SCH_GRED=y CONFIG_NET_SCH_NETEM=y CONFIG_NET_SCH_DRR=y CONFIG_NET_SCH_MQPRIO=y CONFIG_NET_SCH_SKBPRIO=y CONFIG_NET_SCH_CHOKE=y CONFIG_NET_SCH_QFQ=y CONFIG_NET_SCH_CODEL=y CONFIG_NET_SCH_FQ_CODEL=y CONFIG_NET_SCH_CAKE=y CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_HHF=y CONFIG_NET_SCH_PIE=y CONFIG_NET_SCH_FQ_PIE=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_SCH_PLUG=y CONFIG_NET_SCH_ETS=y # CONFIG_NET_SCH_DUALPI2 is not set CONFIG_NET_SCH_DEFAULT=y # CONFIG_DEFAULT_FQ is not set CONFIG_DEFAULT_CODEL=y # CONFIG_DEFAULT_FQ_CODEL is not set # CONFIG_DEFAULT_FQ_PIE is not set # CONFIG_DEFAULT_SFQ is not set # CONFIG_DEFAULT_PFIFO_FAST is not set CONFIG_DEFAULT_NET_SCH="pfifo_fast" # # Classification # CONFIG_NET_CLS=y CONFIG_NET_CLS_BASIC=y CONFIG_NET_CLS_ROUTE4=y CONFIG_NET_CLS_FW=y CONFIG_NET_CLS_U32=y CONFIG_CLS_U32_PERF=y CONFIG_CLS_U32_MARK=y CONFIG_NET_CLS_FLOW=y CONFIG_NET_CLS_CGROUP=y CONFIG_NET_CLS_BPF=y CONFIG_NET_CLS_FLOWER=y CONFIG_NET_CLS_MATCHALL=y CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_STACK=32 CONFIG_NET_EMATCH_CMP=y CONFIG_NET_EMATCH_NBYTE=y CONFIG_NET_EMATCH_U32=y CONFIG_NET_EMATCH_META=y CONFIG_NET_EMATCH_TEXT=y CONFIG_NET_EMATCH_CANID=y CONFIG_NET_EMATCH_IPSET=y CONFIG_NET_EMATCH_IPT=y CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=y CONFIG_NET_ACT_GACT=y CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=y CONFIG_NET_ACT_SAMPLE=y CONFIG_NET_ACT_NAT=y CONFIG_NET_ACT_PEDIT=y CONFIG_NET_ACT_SIMP=y CONFIG_NET_ACT_SKBEDIT=y CONFIG_NET_ACT_CSUM=y CONFIG_NET_ACT_MPLS=y CONFIG_NET_ACT_VLAN=y CONFIG_NET_ACT_BPF=y CONFIG_NET_ACT_CONNMARK=y CONFIG_NET_ACT_CTINFO=y CONFIG_NET_ACT_SKBMOD=y CONFIG_NET_ACT_IFE=y CONFIG_NET_ACT_TUNNEL_KEY=y CONFIG_NET_ACT_CT=y CONFIG_NET_ACT_GATE=y CONFIG_NET_IFE_SKBMARK=y CONFIG_NET_IFE_SKBPRIO=y CONFIG_NET_IFE_SKBTCINDEX=y CONFIG_NET_TC_SKB_EXT=y CONFIG_NET_SCH_FIFO=y CONFIG_DCB=y CONFIG_DNS_RESOLVER=y CONFIG_BATMAN_ADV=y CONFIG_BATMAN_ADV_BATMAN_V=y CONFIG_BATMAN_ADV_BLA=y CONFIG_BATMAN_ADV_DAT=y CONFIG_BATMAN_ADV_MCAST=y # CONFIG_BATMAN_ADV_DEBUG is not set # CONFIG_BATMAN_ADV_TRACING is not set CONFIG_OPENVSWITCH=y CONFIG_OPENVSWITCH_GRE=y CONFIG_OPENVSWITCH_VXLAN=y CONFIG_OPENVSWITCH_GENEVE=y CONFIG_VSOCKETS=y CONFIG_VSOCKETS_DIAG=y CONFIG_VSOCKETS_LOOPBACK=y CONFIG_VIRTIO_VSOCKETS=y CONFIG_VIRTIO_VSOCKETS_COMMON=y CONFIG_NETLINK_DIAG=y CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=y CONFIG_MPLS_ROUTING=y CONFIG_MPLS_IPTUNNEL=y CONFIG_NET_NSH=y CONFIG_HSR=y CONFIG_NET_SWITCHDEV=y CONFIG_NET_L3_MASTER_DEV=y CONFIG_QRTR=y CONFIG_QRTR_TUN=y CONFIG_NET_NCSI=y # CONFIG_NCSI_OEM_CMD_GET_MAC is not set # CONFIG_NCSI_OEM_CMD_KEEP_PHY is not set # CONFIG_PCPU_DEV_REFCNT is not set CONFIG_MAX_SKB_FRAGS=17 CONFIG_RPS=y CONFIG_RFS_ACCEL=y CONFIG_SOCK_RX_QUEUE_MAPPING=y CONFIG_XPS=y CONFIG_CGROUP_NET_PRIO=y CONFIG_CGROUP_NET_CLASSID=y CONFIG_NET_RX_BUSY_POLL=y CONFIG_BQL=y CONFIG_NET_FLOW_LIMIT=y # # Network testing # # CONFIG_NET_PKTGEN is not set CONFIG_NET_DROP_MONITOR=y # end of Network testing # end of Networking options CONFIG_CAN=y CONFIG_CAN_RAW=y CONFIG_CAN_BCM=y CONFIG_CAN_GW=y CONFIG_CAN_J1939=y CONFIG_CAN_ISOTP=y CONFIG_BT=y CONFIG_BT_BREDR=y # CONFIG_BT_RFCOMM is not set # CONFIG_BT_BNEP is not set CONFIG_BT_HIDP=y # CONFIG_BT_LE is not set # CONFIG_BT_LEDS is not set # CONFIG_BT_MSFTEXT is not set # CONFIG_BT_AOSPEXT is not set # CONFIG_BT_DEBUGFS is not set # CONFIG_BT_SELFTEST is not set # CONFIG_BT_FEATURE_DEBUG is not set # # Bluetooth device drivers # CONFIG_BT_INTEL=y CONFIG_BT_BCM=y CONFIG_BT_RTL=y CONFIG_BT_MTK=y CONFIG_BT_HCIBTUSB=y CONFIG_BT_HCIBTUSB_AUTOSUSPEND=y CONFIG_BT_HCIBTUSB_POLL_SYNC=y CONFIG_BT_HCIBTUSB_BCM=y CONFIG_BT_HCIBTUSB_MTK=y CONFIG_BT_HCIBTUSB_RTL=y # CONFIG_BT_HCIBTSDIO is not set CONFIG_BT_HCIUART=y CONFIG_BT_HCIUART_SERDEV=y CONFIG_BT_HCIUART_H4=y # CONFIG_BT_HCIUART_NOKIA is not set # CONFIG_BT_HCIUART_BCSP is not set # CONFIG_BT_HCIUART_ATH3K is not set # CONFIG_BT_HCIUART_LL is not set # CONFIG_BT_HCIUART_3WIRE is not set # CONFIG_BT_HCIUART_INTEL is not set # CONFIG_BT_HCIUART_RTL is not set # CONFIG_BT_HCIUART_QCA is not set # CONFIG_BT_HCIUART_AG6XX is not set # CONFIG_BT_HCIUART_MRVL is not set # CONFIG_BT_HCIUART_AML is not set CONFIG_BT_HCIBCM203X=y # CONFIG_BT_HCIBCM4377 is not set CONFIG_BT_HCIBPA10X=y CONFIG_BT_HCIBFUSB=y # CONFIG_BT_HCIDTL1 is not set # CONFIG_BT_HCIBT3C is not set # CONFIG_BT_HCIBLUECARD is not set # CONFIG_BT_HCIVHCI is not set CONFIG_BT_MRVL=y CONFIG_BT_MRVL_SDIO=y CONFIG_BT_ATH3K=y CONFIG_BT_MTKSDIO=y CONFIG_BT_MTKUART=y # CONFIG_BT_VIRTIO is not set # CONFIG_BT_NXPUART is not set # CONFIG_BT_INTEL_PCIE is not set # end of Bluetooth device drivers CONFIG_AF_RXRPC=y CONFIG_AF_RXRPC_IPV6=y # CONFIG_AF_RXRPC_INJECT_LOSS is not set # CONFIG_AF_RXRPC_INJECT_RX_DELAY is not set # CONFIG_AF_RXRPC_DEBUG is not set CONFIG_RXKAD=y # CONFIG_RXGK is not set # CONFIG_RXPERF is not set CONFIG_AF_KCM=y CONFIG_STREAM_PARSER=y CONFIG_MCTP=y CONFIG_FIB_RULES=y CONFIG_WIRELESS=y CONFIG_CFG80211=y # CONFIG_NL80211_TESTMODE is not set # CONFIG_CFG80211_DEVELOPER_WARNINGS is not set # CONFIG_CFG80211_CERTIFICATION_ONUS is not set CONFIG_CFG80211_REQUIRE_SIGNED_REGDB=y CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS=y CONFIG_CFG80211_DEFAULT_PS=y CONFIG_CFG80211_DEBUGFS=y CONFIG_CFG80211_CRDA_SUPPORT=y # CONFIG_CFG80211_WEXT is not set CONFIG_MAC80211=y CONFIG_MAC80211_HAS_RC=y CONFIG_MAC80211_RC_MINSTREL=y CONFIG_MAC80211_RC_DEFAULT_MINSTREL=y CONFIG_MAC80211_RC_DEFAULT="minstrel_ht" # CONFIG_MAC80211_MESH is not set CONFIG_MAC80211_LEDS=y CONFIG_MAC80211_DEBUGFS=y # CONFIG_MAC80211_MESSAGE_TRACING is not set # CONFIG_MAC80211_DEBUG_MENU is not set CONFIG_MAC80211_STA_HASH_MAX_SIZE=0 CONFIG_RFKILL=y CONFIG_RFKILL_LEDS=y CONFIG_RFKILL_INPUT=y # CONFIG_RFKILL_GPIO is not set CONFIG_NET_9P=y CONFIG_NET_9P_FD=y CONFIG_NET_9P_VIRTIO=y # CONFIG_NET_9P_USBG is not set CONFIG_NET_9P_RDMA=y # CONFIG_NET_9P_DEBUG is not set CONFIG_CEPH_LIB=y # CONFIG_CEPH_LIB_PRETTYDEBUG is not set CONFIG_CEPH_LIB_USE_DNS_RESOLVER=y CONFIG_NFC=y CONFIG_NFC_DIGITAL=y CONFIG_NFC_NCI=y # CONFIG_NFC_NCI_SPI is not set CONFIG_NFC_NCI_UART=y CONFIG_NFC_HCI=y CONFIG_NFC_SHDLC=y # # Near Field Communication (NFC) devices # # CONFIG_NFC_TRF7970A is not set # CONFIG_NFC_MEI_PHY is not set CONFIG_NFC_SIM=y CONFIG_NFC_PORT100=y CONFIG_NFC_VIRTUAL_NCI=y CONFIG_NFC_FDP=y # CONFIG_NFC_FDP_I2C is not set # CONFIG_NFC_PN544_I2C is not set CONFIG_NFC_PN533=y CONFIG_NFC_PN533_USB=y # CONFIG_NFC_PN533_I2C is not set # CONFIG_NFC_PN532_UART is not set # CONFIG_NFC_MICROREAD_I2C is not set CONFIG_NFC_MRVL=y CONFIG_NFC_MRVL_USB=y # CONFIG_NFC_MRVL_UART is not set # CONFIG_NFC_MRVL_I2C is not set # CONFIG_NFC_ST21NFCA_I2C is not set # CONFIG_NFC_ST_NCI_I2C is not set # CONFIG_NFC_ST_NCI_SPI is not set # CONFIG_NFC_NXP_NCI is not set # CONFIG_NFC_S3FWRN5_I2C is not set # CONFIG_NFC_S3FWRN82_UART is not set # CONFIG_NFC_ST95HF is not set # end of Near Field Communication (NFC) devices CONFIG_PSAMPLE=y CONFIG_NET_IFE=y CONFIG_LWTUNNEL=y CONFIG_LWTUNNEL_BPF=y CONFIG_DST_CACHE=y CONFIG_GRO_CELLS=y CONFIG_SOCK_VALIDATE_XMIT=y CONFIG_NET_SELFTESTS=y CONFIG_NET_SOCK_MSG=y CONFIG_NET_DEVLINK=y CONFIG_PAGE_POOL=y # CONFIG_PAGE_POOL_STATS is not set CONFIG_FAILOVER=y CONFIG_ETHTOOL_NETLINK=y # # Device Drivers # CONFIG_HAVE_PCI=y CONFIG_GENERIC_PCI_IOMAP=y CONFIG_PCI=y CONFIG_PCI_DOMAINS=y CONFIG_PCIEPORTBUS=y # CONFIG_HOTPLUG_PCI_PCIE is not set # CONFIG_PCIEAER is not set CONFIG_PCIEASPM=y CONFIG_PCIEASPM_DEFAULT=y # CONFIG_PCIEASPM_POWERSAVE is not set # CONFIG_PCIEASPM_POWER_SUPERSAVE is not set # CONFIG_PCIEASPM_PERFORMANCE is not set CONFIG_PCIE_PME=y # CONFIG_PCIE_PTM is not set CONFIG_PCI_MSI=y CONFIG_PCI_QUIRKS=y # CONFIG_PCI_DEBUG is not set # CONFIG_PCI_STUB is not set CONFIG_PCI_ATS=y CONFIG_PCI_IDE=y CONFIG_PCI_TSM=y CONFIG_PCI_DOE=y CONFIG_PCI_ECAM=y CONFIG_PCI_LOCKLESS_CONFIG=y # CONFIG_PCI_IOV is not set # CONFIG_PCI_NPEM is not set CONFIG_PCI_PRI=y CONFIG_PCI_PASID=y # CONFIG_PCIE_TPH is not set CONFIG_PCI_LABEL=y # CONFIG_PCI_DYNAMIC_OF_NODES is not set # CONFIG_PCIE_BUS_TUNE_OFF is not set CONFIG_PCIE_BUS_DEFAULT=y # CONFIG_PCIE_BUS_SAFE is not set # CONFIG_PCIE_BUS_PERFORMANCE is not set # CONFIG_PCIE_BUS_PEER2PEER is not set CONFIG_VGA_ARB=y CONFIG_VGA_ARB_MAX_GPUS=16 CONFIG_HOTPLUG_PCI=y # CONFIG_HOTPLUG_PCI_ACPI is not set # CONFIG_HOTPLUG_PCI_CPCI is not set # CONFIG_HOTPLUG_PCI_OCTEONEP is not set # CONFIG_HOTPLUG_PCI_SHPC is not set # # PCI controller drivers # CONFIG_PCI_HOST_COMMON=y # CONFIG_PCI_FTPCI100 is not set CONFIG_PCI_HOST_GENERIC=y # CONFIG_VMD is not set # CONFIG_PCIE_XILINX is not set # # Cadence-based PCIe controllers # # CONFIG_PCIE_CADENCE_PLAT_HOST is not set # end of Cadence-based PCIe controllers # # DesignWare-based PCIe controllers # # CONFIG_PCI_MESON is not set # CONFIG_PCIE_INTEL_GW is not set # CONFIG_PCIE_DW_PLAT_HOST is not set # end of DesignWare-based PCIe controllers # # Mobiveil-based PCIe controllers # # end of Mobiveil-based PCIe controllers # # PLDA-based PCIe controllers # # CONFIG_PCIE_MICROCHIP_HOST is not set # end of PLDA-based PCIe controllers # end of PCI controller drivers # # PCI Endpoint # # CONFIG_PCI_ENDPOINT is not set # end of PCI Endpoint # # PCI switch controller drivers # # CONFIG_PCI_SW_SWITCHTEC is not set # end of PCI switch controller drivers # CONFIG_PCI_PWRCTRL_GENERIC is not set # CONFIG_PCI_PWRCTRL_TC9563 is not set # CONFIG_CXL_BUS is not set CONFIG_PCCARD=y CONFIG_PCMCIA=y CONFIG_PCMCIA_LOAD_CIS=y CONFIG_CARDBUS=y # # PC-card bridges # CONFIG_YENTA=y CONFIG_YENTA_O2=y CONFIG_YENTA_RICOH=y CONFIG_YENTA_TI=y CONFIG_YENTA_ENE_TUNE=y CONFIG_YENTA_TOSHIBA=y # CONFIG_PD6729 is not set CONFIG_PCCARD_NONSTATIC=y # CONFIG_RAPIDIO is not set # CONFIG_PC104 is not set # # Generic Driver Options # CONFIG_AUXILIARY_BUS=y CONFIG_UEVENT_HELPER=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_DEVTMPFS_SAFE is not set CONFIG_DRIVER_DEFERRED_PROBE_TIMEOUT=10 CONFIG_STANDALONE=y CONFIG_PREVENT_FIRMWARE_BUILD=y # # Firmware loader # CONFIG_FW_LOADER=y CONFIG_EXTRA_FIRMWARE="" # CONFIG_FW_LOADER_USER_HELPER is not set # CONFIG_FW_LOADER_COMPRESS is not set CONFIG_FW_CACHE=y # CONFIG_FW_UPLOAD is not set # end of Firmware loader CONFIG_WANT_DEV_COREDUMP=y CONFIG_ALLOW_DEV_COREDUMP=y CONFIG_DEV_COREDUMP=y # CONFIG_DEBUG_DRIVER is not set CONFIG_DEBUG_DEVRES=y # CONFIG_DEBUG_TEST_DRIVER_REMOVE is not set # CONFIG_TEST_ASYNC_DRIVER_PROBE is not set CONFIG_GENERIC_CPU_DEVICES=y CONFIG_GENERIC_CPU_AUTOPROBE=y CONFIG_GENERIC_CPU_VULNERABILITIES=y CONFIG_REGMAP=y CONFIG_REGMAP_I2C=y CONFIG_REGMAP_SPI=y CONFIG_REGMAP_MMIO=y CONFIG_REGMAP_IRQ=y CONFIG_DMA_SHARED_BUFFER=y # CONFIG_DMA_FENCE_TRACE is not set # CONFIG_FW_DEVLINK_SYNC_STATE_TIMEOUT is not set # end of Generic Driver Options # # Bus devices # # CONFIG_MOXTET is not set # CONFIG_MHI_BUS is not set # CONFIG_MHI_BUS_EP is not set # end of Bus devices CONFIG_CONNECTOR=y CONFIG_PROC_EVENTS=y # # Firmware Drivers # # # ARM System Control and Management Interface Protocol # # end of ARM System Control and Management Interface Protocol # CONFIG_EDD is not set CONFIG_FIRMWARE_MEMMAP=y CONFIG_DMIID=y # CONFIG_DMI_SYSFS is not set CONFIG_DMI_SCAN_MACHINE_NON_EFI_FALLBACK=y # CONFIG_ISCSI_IBFT is not set # CONFIG_FW_CFG_SYSFS is not set # CONFIG_SYSFB_SIMPLEFB is not set # CONFIG_GOOGLE_FIRMWARE is not set # # Qualcomm firmware drivers # # end of Qualcomm firmware drivers # # Tegra firmware driver # # end of Tegra firmware driver # end of Firmware Drivers # CONFIG_FWCTL is not set CONFIG_GNSS=y # CONFIG_GNSS_MTK_SERIAL is not set # CONFIG_GNSS_SIRF_SERIAL is not set # CONFIG_GNSS_UBX_SERIAL is not set CONFIG_GNSS_USB=y # CONFIG_MTD is not set CONFIG_DTC=y CONFIG_OF=y # CONFIG_OF_UNITTEST is not set CONFIG_OF_FLATTREE=y CONFIG_OF_EARLY_FLATTREE=y CONFIG_OF_KOBJ=y CONFIG_OF_ADDRESS=y CONFIG_OF_IRQ=y CONFIG_OF_RESERVED_MEM=y # CONFIG_OF_OVERLAY is not set CONFIG_OF_NUMA=y CONFIG_ARCH_MIGHT_HAVE_PC_PARPORT=y CONFIG_PARPORT=y # CONFIG_PARPORT_PC is not set # CONFIG_PARPORT_1284 is not set CONFIG_PARPORT_NOT_PC=y CONFIG_PNP=y CONFIG_PNP_DEBUG_MESSAGES=y # # Protocols # CONFIG_PNPACPI=y CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_NULL_BLK is not set # CONFIG_BLK_DEV_FD is not set CONFIG_CDROM=y # CONFIG_BLK_DEV_PCIESSD_MTIP32XX is not set # CONFIG_ZRAM is not set CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_LOOP_MIN_COUNT=8 # CONFIG_BLK_DEV_DRBD is not set # CONFIG_BLK_DEV_NBD is not set # CONFIG_BLK_DEV_RAM is not set # CONFIG_ATA_OVER_ETH is not set CONFIG_VIRTIO_BLK=y # CONFIG_BLK_DEV_RBD is not set # CONFIG_BLK_DEV_UBLK is not set # CONFIG_BLK_DEV_RNBD_CLIENT is not set # # NVME Support # # CONFIG_BLK_DEV_NVME is not set # CONFIG_NVME_RDMA is not set # CONFIG_NVME_FC is not set # CONFIG_NVME_TCP is not set # CONFIG_NVME_TARGET is not set # end of NVME Support # # Misc devices # # CONFIG_AD525X_DPOT is not set # CONFIG_DUMMY_IRQ is not set # CONFIG_IBM_ASM is not set # CONFIG_PHANTOM is not set # CONFIG_RPMB is not set # CONFIG_TI_FPC202 is not set # CONFIG_TIFM_CORE is not set # CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set # CONFIG_HP_ILO is not set # CONFIG_APDS9802ALS is not set # CONFIG_ISL29003 is not set # CONFIG_ISL29020 is not set # CONFIG_SENSORS_TSL2550 is not set # CONFIG_SENSORS_BH1770 is not set # CONFIG_SENSORS_APDS990X is not set # CONFIG_HMC6352 is not set # CONFIG_DS1682 is not set # CONFIG_LATTICE_ECP3_CONFIG is not set # CONFIG_SRAM is not set # CONFIG_DW_XDATA_PCIE is not set # CONFIG_PCI_ENDPOINT_TEST is not set # CONFIG_XILINX_SDFEC is not set CONFIG_MISC_RTSX=y # CONFIG_HISI_HIKEY_USB is not set # CONFIG_OPEN_DICE is not set # CONFIG_NTSYNC is not set # CONFIG_VCPU_STALL_DETECTOR is not set # CONFIG_NSM is not set # CONFIG_C2PORT is not set # # EEPROM support # # CONFIG_EEPROM_AT24 is not set # CONFIG_EEPROM_AT25 is not set # CONFIG_EEPROM_MAX6875 is not set CONFIG_EEPROM_93CX6=y # CONFIG_EEPROM_93XX46 is not set # CONFIG_EEPROM_IDT_89HPESX is not set # CONFIG_EEPROM_EE1004 is not set # CONFIG_EEPROM_M24LR is not set # end of EEPROM support # CONFIG_CB710_CORE is not set # CONFIG_SENSORS_LIS3_I2C is not set # CONFIG_ALTERA_STAPL is not set CONFIG_INTEL_MEI=y CONFIG_INTEL_MEI_ME=y # CONFIG_INTEL_MEI_TXE is not set # CONFIG_INTEL_MEI_GSC is not set # CONFIG_INTEL_MEI_CSC is not set # CONFIG_INTEL_MEI_VSC_HW is not set # CONFIG_INTEL_MEI_HDCP is not set # CONFIG_INTEL_MEI_PXP is not set # CONFIG_INTEL_MEI_GSC_PROXY is not set # CONFIG_VMWARE_VMCI is not set # CONFIG_GENWQE is not set # CONFIG_BCM_VK is not set # CONFIG_MISC_ALCOR_PCI is not set # CONFIG_MISC_RTSX_PCI is not set CONFIG_MISC_RTSX_USB=y # CONFIG_UACCE is not set # CONFIG_PVPANIC is not set # CONFIG_GP_PCI1XXXX is not set # CONFIG_KEBA_CP500 is not set # CONFIG_MISC_RP1 is not set # end of Misc devices # # SCSI device support # CONFIG_SCSI_MOD=y # CONFIG_RAID_ATTRS is not set CONFIG_SCSI_COMMON=y CONFIG_SCSI=y CONFIG_SCSI_DMA=y CONFIG_SCSI_PROC_FS=y # # SCSI support type (disk, tape, CD-ROM) # CONFIG_BLK_DEV_SD=y # CONFIG_CHR_DEV_ST is not set CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y CONFIG_BLK_DEV_BSG=y # CONFIG_CHR_DEV_SCH is not set CONFIG_SCSI_CONSTANTS=y # CONFIG_SCSI_LOGGING is not set # CONFIG_SCSI_SCAN_ASYNC is not set # # SCSI Transports # CONFIG_SCSI_SPI_ATTRS=y # CONFIG_SCSI_FC_ATTRS is not set CONFIG_SCSI_ISCSI_ATTRS=y # CONFIG_SCSI_SAS_ATTRS is not set # CONFIG_SCSI_SAS_LIBSAS is not set CONFIG_SCSI_SRP_ATTRS=y # end of SCSI Transports CONFIG_SCSI_LOWLEVEL=y # CONFIG_ISCSI_TCP is not set # CONFIG_ISCSI_BOOT_SYSFS is not set # CONFIG_SCSI_CXGB3_ISCSI is not set # CONFIG_SCSI_CXGB4_ISCSI is not set # CONFIG_SCSI_BNX2_ISCSI is not set # CONFIG_BE2ISCSI is not set # CONFIG_BLK_DEV_3W_XXXX_RAID is not set # CONFIG_SCSI_HPSA is not set # CONFIG_SCSI_3W_9XXX is not set # CONFIG_SCSI_3W_SAS is not set # CONFIG_SCSI_ACARD is not set # CONFIG_SCSI_AACRAID is not set # CONFIG_SCSI_AIC7XXX is not set # CONFIG_SCSI_AIC79XX is not set # CONFIG_SCSI_AIC94XX is not set # CONFIG_SCSI_MVSAS is not set # CONFIG_SCSI_MVUMI is not set # CONFIG_SCSI_ADVANSYS is not set # CONFIG_SCSI_ARCMSR is not set # CONFIG_SCSI_ESAS2R is not set # CONFIG_MEGARAID_NEWGEN is not set # CONFIG_MEGARAID_LEGACY is not set # CONFIG_MEGARAID_SAS is not set # CONFIG_SCSI_MPT3SAS is not set # CONFIG_SCSI_MPT2SAS is not set # CONFIG_SCSI_MPI3MR is not set # CONFIG_SCSI_SMARTPQI is not set # CONFIG_SCSI_HPTIOP is not set # CONFIG_SCSI_BUSLOGIC is not set # CONFIG_SCSI_MYRB is not set # CONFIG_SCSI_MYRS is not set # CONFIG_VMWARE_PVSCSI is not set # CONFIG_SCSI_SNIC is not set # CONFIG_SCSI_DMX3191D is not set # CONFIG_SCSI_FDOMAIN_PCI is not set # CONFIG_SCSI_ISCI is not set # CONFIG_SCSI_IPS is not set # CONFIG_SCSI_INITIO is not set # CONFIG_SCSI_INIA100 is not set # CONFIG_SCSI_STEX is not set # CONFIG_SCSI_SYM53C8XX_2 is not set # CONFIG_SCSI_IPR is not set # CONFIG_SCSI_QLOGIC_1280 is not set # CONFIG_SCSI_QLA_ISCSI is not set # CONFIG_SCSI_DC395x is not set # CONFIG_SCSI_AM53C974 is not set # CONFIG_SCSI_WD719X is not set # CONFIG_SCSI_DEBUG is not set # CONFIG_SCSI_PMCRAID is not set # CONFIG_SCSI_PM8001 is not set CONFIG_SCSI_VIRTIO=y # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set # CONFIG_SCSI_DH is not set # end of SCSI device support CONFIG_ATA=y CONFIG_SATA_HOST=y CONFIG_PATA_TIMINGS=y CONFIG_ATA_VERBOSE_ERROR=y CONFIG_ATA_FORCE=y CONFIG_ATA_ACPI=y # CONFIG_SATA_ZPODD is not set CONFIG_SATA_PMP=y # # Controllers with non-SFF native interface # CONFIG_SATA_AHCI=y CONFIG_SATA_MOBILE_LPM_POLICY=3 # CONFIG_SATA_AHCI_PLATFORM is not set # CONFIG_AHCI_DWC is not set # CONFIG_AHCI_CEVA is not set # CONFIG_SATA_INIC162X is not set # CONFIG_SATA_ACARD_AHCI is not set # CONFIG_SATA_SIL24 is not set CONFIG_ATA_SFF=y # # SFF controllers with custom DMA interface # # CONFIG_PDC_ADMA is not set # CONFIG_SATA_QSTOR is not set # CONFIG_SATA_SX4 is not set CONFIG_ATA_BMDMA=y # # SATA SFF controllers with BMDMA # CONFIG_ATA_PIIX=y # CONFIG_SATA_DWC is not set # CONFIG_SATA_MV is not set # CONFIG_SATA_NV is not set # CONFIG_SATA_PROMISE is not set # CONFIG_SATA_SIL is not set # CONFIG_SATA_SIS is not set # CONFIG_SATA_SVW is not set # CONFIG_SATA_ULI is not set # CONFIG_SATA_VIA is not set # CONFIG_SATA_VITESSE is not set # # PATA SFF controllers with BMDMA # # CONFIG_PATA_ALI is not set CONFIG_PATA_AMD=y # CONFIG_PATA_ARTOP is not set # CONFIG_PATA_ATIIXP is not set # CONFIG_PATA_ATP867X is not set # CONFIG_PATA_CMD64X is not set # CONFIG_PATA_CYPRESS is not set # CONFIG_PATA_EFAR is not set # CONFIG_PATA_HPT366 is not set # CONFIG_PATA_HPT37X is not set # CONFIG_PATA_HPT3X2N is not set # CONFIG_PATA_HPT3X3 is not set # CONFIG_PATA_IT8213 is not set # CONFIG_PATA_IT821X is not set # CONFIG_PATA_JMICRON is not set # CONFIG_PATA_MARVELL is not set # CONFIG_PATA_NETCELL is not set # CONFIG_PATA_NINJA32 is not set # CONFIG_PATA_NS87415 is not set CONFIG_PATA_OLDPIIX=y # CONFIG_PATA_OPTIDMA is not set # CONFIG_PATA_PDC2027X is not set # CONFIG_PATA_PDC_OLD is not set # CONFIG_PATA_RADISYS is not set # CONFIG_PATA_RDC is not set CONFIG_PATA_SCH=y # CONFIG_PATA_SERVERWORKS is not set # CONFIG_PATA_SIL680 is not set # CONFIG_PATA_SIS is not set # CONFIG_PATA_TOSHIBA is not set # CONFIG_PATA_TRIFLEX is not set # CONFIG_PATA_VIA is not set # CONFIG_PATA_WINBOND is not set # # PIO-only SFF controllers # # CONFIG_PATA_CMD640_PCI is not set # CONFIG_PATA_MPIIX is not set # CONFIG_PATA_NS87410 is not set # CONFIG_PATA_OPTI is not set # CONFIG_PATA_PCMCIA is not set # CONFIG_PATA_OF_PLATFORM is not set # CONFIG_PATA_RZ1000 is not set # # Generic fallback / legacy drivers # # CONFIG_PATA_ACPI is not set # CONFIG_ATA_GENERIC is not set # CONFIG_PATA_LEGACY is not set CONFIG_MD=y CONFIG_BLK_DEV_MD=y CONFIG_MD_BITMAP=y # CONFIG_MD_LLBITMAP is not set CONFIG_MD_AUTODETECT=y CONFIG_MD_BITMAP_FILE=y # CONFIG_MD_LINEAR is not set # CONFIG_MD_RAID0 is not set # CONFIG_MD_RAID1 is not set # CONFIG_MD_RAID10 is not set # CONFIG_MD_RAID456 is not set # CONFIG_BCACHE is not set CONFIG_BLK_DEV_DM_BUILTIN=y CONFIG_BLK_DEV_DM=y # CONFIG_DM_DEBUG is not set # CONFIG_DM_UNSTRIPED is not set # CONFIG_DM_CRYPT is not set # CONFIG_DM_SNAPSHOT is not set # CONFIG_DM_THIN_PROVISIONING is not set # CONFIG_DM_CACHE is not set # CONFIG_DM_WRITECACHE is not set # CONFIG_DM_EBS is not set # CONFIG_DM_ERA is not set # CONFIG_DM_CLONE is not set CONFIG_DM_MIRROR=y # CONFIG_DM_LOG_USERSPACE is not set # CONFIG_DM_RAID is not set CONFIG_DM_ZERO=y # CONFIG_DM_MULTIPATH is not set # CONFIG_DM_DELAY is not set # CONFIG_DM_DUST is not set # CONFIG_DM_INIT is not set # CONFIG_DM_UEVENT is not set # CONFIG_DM_FLAKEY is not set # CONFIG_DM_VERITY is not set # CONFIG_DM_SWITCH is not set # CONFIG_DM_LOG_WRITES is not set # CONFIG_DM_INTEGRITY is not set # CONFIG_DM_AUDIT is not set # CONFIG_DM_VDO is not set CONFIG_TARGET_CORE=y # CONFIG_TCM_IBLOCK is not set # CONFIG_TCM_FILEIO is not set # CONFIG_TCM_PSCSI is not set # CONFIG_LOOPBACK_TARGET is not set # CONFIG_ISCSI_TARGET is not set # CONFIG_REMOTE_TARGET is not set # CONFIG_FUSION is not set # # IEEE 1394 (FireWire) support # # CONFIG_FIREWIRE is not set # CONFIG_FIREWIRE_NOSY is not set # end of IEEE 1394 (FireWire) support CONFIG_MACINTOSH_DRIVERS=y CONFIG_MAC_EMUMOUSEBTN=y CONFIG_NETDEVICES=y CONFIG_MII=y CONFIG_NET_CORE=y CONFIG_BONDING=y CONFIG_DUMMY=y CONFIG_WIREGUARD=y # CONFIG_WIREGUARD_DEBUG is not set # CONFIG_OVPN is not set CONFIG_EQUALIZER=y CONFIG_NET_FC=y CONFIG_IFB=y CONFIG_NET_TEAM=y CONFIG_NET_TEAM_MODE_BROADCAST=y CONFIG_NET_TEAM_MODE_ROUNDROBIN=y CONFIG_NET_TEAM_MODE_RANDOM=y CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y CONFIG_MACVLAN=y CONFIG_MACVTAP=y CONFIG_IPVLAN_L3S=y CONFIG_IPVLAN=y CONFIG_IPVTAP=y CONFIG_VXLAN=y CONFIG_GENEVE=y CONFIG_BAREUDP=y CONFIG_GTP=y # CONFIG_PFCP is not set # CONFIG_AMT is not set CONFIG_MACSEC=y CONFIG_NETCONSOLE=y # CONFIG_NETCONSOLE_DYNAMIC is not set # CONFIG_NETCONSOLE_EXTENDED_LOG is not set CONFIG_NETPOLL=y CONFIG_NET_POLL_CONTROLLER=y CONFIG_TUN=y CONFIG_TAP=y CONFIG_TUN_VNET_CROSS_LE=y CONFIG_VETH=y CONFIG_VIRTIO_NET=y CONFIG_NLMON=y # CONFIG_NETKIT is not set CONFIG_NET_VRF=y # CONFIG_ARCNET is not set CONFIG_ATM_DRIVERS=y # CONFIG_ATM_SOLOS is not set # # Distributed Switch Architecture drivers # # CONFIG_B53 is not set # CONFIG_NET_DSA_BCM_SF2 is not set # CONFIG_NET_DSA_LOOP is not set # CONFIG_NET_DSA_HIRSCHMANN_HELLCREEK is not set # CONFIG_NET_DSA_LANTIQ_GSWIP is not set # CONFIG_NET_DSA_MXL_GSW1XX is not set # CONFIG_NET_DSA_MT7530 is not set # CONFIG_NET_DSA_MV88E6060 is not set # CONFIG_NET_DSA_MICROCHIP_KSZ_COMMON is not set # CONFIG_NET_DSA_MV88E6XXX is not set # CONFIG_NET_DSA_MXL862 is not set # CONFIG_NET_DSA_AR9331 is not set # CONFIG_NET_DSA_QCA8K is not set # CONFIG_NET_DSA_SJA1105 is not set # CONFIG_NET_DSA_XRS700X_I2C is not set # CONFIG_NET_DSA_XRS700X_MDIO is not set # CONFIG_NET_DSA_REALTEK is not set # CONFIG_NET_DSA_KS8995 is not set # CONFIG_NET_DSA_SMSC_LAN9303_I2C is not set # CONFIG_NET_DSA_SMSC_LAN9303_MDIO is not set # CONFIG_NET_DSA_VITESSE_VSC73XX_SPI is not set # CONFIG_NET_DSA_VITESSE_VSC73XX_PLATFORM is not set # CONFIG_NET_DSA_YT921X is not set # end of Distributed Switch Architecture drivers CONFIG_ETHERNET=y # CONFIG_NET_VENDOR_3COM is not set # CONFIG_NET_VENDOR_ADAPTEC is not set # CONFIG_NET_VENDOR_AGERE is not set # CONFIG_NET_VENDOR_ALACRITECH is not set # CONFIG_ALTERA_TSE is not set CONFIG_NET_VENDOR_AMAZON=y # CONFIG_ENA_ETHERNET is not set # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set CONFIG_NET_VENDOR_ASIX=y # CONFIG_SPI_AX88796C is not set # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_CX_ECAT is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_CADENCE is not set # CONFIG_NET_VENDOR_CAVIUM is not set # CONFIG_NET_VENDOR_CHELSIO is not set CONFIG_NET_VENDOR_CISCO=y # CONFIG_ENIC is not set # CONFIG_NET_VENDOR_CORTINA is not set CONFIG_NET_VENDOR_DAVICOM=y # CONFIG_DM9051 is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set CONFIG_NET_VENDOR_ENGLEDER=y # CONFIG_TSNEP is not set # CONFIG_NET_VENDOR_EZCHIP is not set CONFIG_NET_VENDOR_FUNGIBLE=y # CONFIG_FUN_ETH is not set CONFIG_NET_VENDOR_GOOGLE=y CONFIG_GVE=y CONFIG_NET_VENDOR_HISILICON=y # CONFIG_HIBMCGE is not set # CONFIG_NET_VENDOR_HUAWEI is not set CONFIG_NET_VENDOR_I825XX=y CONFIG_NET_VENDOR_INTEL=y CONFIG_E100=y CONFIG_E1000=y CONFIG_E1000E=y CONFIG_E1000E_HWTS=y # CONFIG_IGB is not set # CONFIG_IGBVF is not set # CONFIG_IXGBE is not set # CONFIG_IXGBEVF is not set # CONFIG_I40E is not set # CONFIG_I40EVF is not set # CONFIG_ICE is not set # CONFIG_FM10K is not set # CONFIG_IGC is not set # CONFIG_IDPF is not set # CONFIG_JME is not set # CONFIG_NET_VENDOR_ADI is not set CONFIG_NET_VENDOR_LITEX=y # CONFIG_LITEX_LITEETH is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_NET_VENDOR_MELLANOX=y # CONFIG_MLX4_EN is not set CONFIG_MLX4_CORE=y # CONFIG_MLX4_DEBUG is not set # CONFIG_MLX4_CORE_GEN2 is not set # CONFIG_MLX5_CORE is not set # CONFIG_MLXSW_CORE is not set # CONFIG_MLXFW is not set CONFIG_NET_VENDOR_META=y # CONFIG_FBNIC is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set CONFIG_NET_VENDOR_MICROSOFT=y CONFIG_NET_VENDOR_MUCSE=y # CONFIG_MGBE is not set # CONFIG_NET_VENDOR_MYRI is not set # CONFIG_FEALNX is not set # CONFIG_NET_VENDOR_NI is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NETRONOME is not set # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_ETHOC is not set # CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_BROCADE is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set # CONFIG_NET_VENDOR_REALTEK is not set # CONFIG_NET_VENDOR_RENESAS is not set # CONFIG_NET_VENDOR_ROCKER is not set # CONFIG_NET_VENDOR_SAMSUNG is not set # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SILAN is not set # CONFIG_NET_VENDOR_SIS is not set # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_SUN is not set # CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_TEHUTI is not set # CONFIG_NET_VENDOR_TI is not set CONFIG_NET_VENDOR_VERTEXCOM=y # CONFIG_MSE102X is not set # CONFIG_NET_VENDOR_VIA is not set CONFIG_NET_VENDOR_WANGXUN=y # CONFIG_NGBE is not set # CONFIG_TXGBE is not set # CONFIG_TXGBEVF is not set # CONFIG_NGBEVF is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_NET_VENDOR_XILINX is not set # CONFIG_NET_VENDOR_XIRCOM is not set CONFIG_FDDI=y # CONFIG_DEFXX is not set # CONFIG_SKFP is not set CONFIG_PHYLINK=y CONFIG_PHYLIB=y CONFIG_SWPHY=y CONFIG_PHY_PACKAGE=y # CONFIG_LED_TRIGGER_PHY is not set CONFIG_PHYLIB_LEDS=y CONFIG_FIXED_PHY=y # CONFIG_SFP is not set # # MII PHY device drivers # # CONFIG_AS21XXX_PHY is not set # CONFIG_AIR_EN8811H_PHY is not set # CONFIG_AMD_PHY is not set # CONFIG_ADIN_PHY is not set # CONFIG_ADIN1100_PHY is not set # CONFIG_AQUANTIA_PHY is not set CONFIG_AX88796B_PHY=y # CONFIG_BROADCOM_PHY is not set # CONFIG_BCM54140_PHY is not set # CONFIG_BCM7XXX_PHY is not set # CONFIG_BCM84881_PHY is not set # CONFIG_BCM87XX_PHY is not set # CONFIG_CICADA_PHY is not set # CONFIG_CORTINA_PHY is not set # CONFIG_DAVICOM_PHY is not set # CONFIG_ICPLUS_PHY is not set # CONFIG_LXT_PHY is not set # CONFIG_INTEL_XWAY_PHY is not set # CONFIG_LSI_ET1011C_PHY is not set # CONFIG_MARVELL_PHY is not set # CONFIG_MARVELL_10G_PHY is not set # CONFIG_MARVELL_88Q2XXX_PHY is not set # CONFIG_MARVELL_88X2222_PHY is not set # CONFIG_MAXLINEAR_GPHY is not set # CONFIG_MAXLINEAR_86110_PHY is not set # CONFIG_MEDIATEK_GE_PHY is not set # CONFIG_MICREL_PHY is not set # CONFIG_MICROCHIP_T1S_PHY is not set CONFIG_MICROCHIP_PHY=y # CONFIG_MICROCHIP_T1_PHY is not set # CONFIG_MICROSEMI_PHY is not set # CONFIG_MOTORCOMM_PHY is not set # CONFIG_NATIONAL_PHY is not set # CONFIG_NXP_CBTX_PHY is not set # CONFIG_NXP_C45_TJA11XX_PHY is not set # CONFIG_NXP_TJA11XX_PHY is not set # CONFIG_NCN26000_PHY is not set # CONFIG_AT803X_PHY is not set # CONFIG_QCA83XX_PHY is not set # CONFIG_QCA808X_PHY is not set # CONFIG_QCA807X_PHY is not set # CONFIG_QSEMI_PHY is not set CONFIG_REALTEK_PHY=y # CONFIG_REALTEK_PHY_HWMON is not set # CONFIG_RENESAS_PHY is not set # CONFIG_ROCKCHIP_PHY is not set CONFIG_SMSC_PHY=y # CONFIG_STE10XP is not set # CONFIG_TERANETICS_PHY is not set # CONFIG_DP83822_PHY is not set # CONFIG_DP83TC811_PHY is not set # CONFIG_DP83848_PHY is not set # CONFIG_DP83867_PHY is not set # CONFIG_DP83869_PHY is not set # CONFIG_DP83TD510_PHY is not set # CONFIG_DP83TG720_PHY is not set # CONFIG_VITESSE_PHY is not set # CONFIG_XILINX_GMII2RGMII is not set # CONFIG_PSE_CONTROLLER is not set CONFIG_CAN_DEV=y CONFIG_CAN_VCAN=y CONFIG_CAN_VXCAN=y CONFIG_CAN_NETLINK=y CONFIG_CAN_CALC_BITTIMING=y CONFIG_CAN_RX_OFFLOAD=y # CONFIG_CAN_CAN327 is not set # CONFIG_CAN_DUMMY is not set # CONFIG_CAN_FLEXCAN is not set # CONFIG_CAN_GRCAN is not set # CONFIG_CAN_KVASER_PCIEFD is not set CONFIG_CAN_SLCAN=y # CONFIG_CAN_C_CAN is not set # CONFIG_CAN_CC770 is not set # CONFIG_CAN_CTUCANFD_PCI is not set # CONFIG_CAN_CTUCANFD_PLATFORM is not set # CONFIG_CAN_ESD_402_PCI is not set CONFIG_CAN_IFI_CANFD=y # CONFIG_CAN_M_CAN is not set # CONFIG_CAN_PEAK_PCIEFD is not set # CONFIG_CAN_SJA1000 is not set # CONFIG_CAN_SOFTING is not set # # CAN SPI interfaces # # CONFIG_CAN_HI311X is not set # CONFIG_CAN_MCP251X is not set # CONFIG_CAN_MCP251XFD is not set # end of CAN SPI interfaces # # CAN USB interfaces # CONFIG_CAN_8DEV_USB=y CONFIG_CAN_EMS_USB=y CONFIG_CAN_ESD_USB=y CONFIG_CAN_ETAS_ES58X=y CONFIG_CAN_F81604=y CONFIG_CAN_GS_USB=y CONFIG_CAN_KVASER_USB=y CONFIG_CAN_MCBA_USB=y CONFIG_CAN_PEAK_USB=y CONFIG_CAN_UCAN=y # end of CAN USB interfaces # CONFIG_CAN_DEBUG_DEVICES is not set # # MCTP Device Drivers # # CONFIG_MCTP_SERIAL is not set # CONFIG_MCTP_TRANSPORT_USB is not set # end of MCTP Device Drivers CONFIG_FWNODE_MDIO=y CONFIG_OF_MDIO=y CONFIG_ACPI_MDIO=y # CONFIG_MDIO_BITBANG is not set # CONFIG_MDIO_BCM_UNIMAC is not set # CONFIG_MDIO_HISI_FEMAC is not set CONFIG_MDIO_MVUSB=y # CONFIG_MDIO_MSCC_MIIM is not set # CONFIG_MDIO_OCTEON is not set # CONFIG_MDIO_IPQ4019 is not set # CONFIG_MDIO_IPQ8064 is not set # CONFIG_MDIO_THUNDER is not set # # MDIO Multiplexers # # CONFIG_MDIO_BUS_MUX_GPIO is not set # CONFIG_MDIO_BUS_MUX_MULTIPLEXER is not set # CONFIG_MDIO_BUS_MUX_MMIOREG is not set # # PCS device drivers # # CONFIG_PCS_XPCS is not set # end of PCS device drivers # CONFIG_PLIP is not set CONFIG_PPP=y CONFIG_PPP_BSDCOMP=y CONFIG_PPP_DEFLATE=y CONFIG_PPP_FILTER=y CONFIG_PPP_MPPE=y CONFIG_PPP_MULTILINK=y CONFIG_PPPOATM=y CONFIG_PPPOE=y CONFIG_PPPOE_HASH_BITS_1=y # CONFIG_PPPOE_HASH_BITS_2 is not set # CONFIG_PPPOE_HASH_BITS_4 is not set # CONFIG_PPPOE_HASH_BITS_8 is not set CONFIG_PPPOE_HASH_BITS=1 CONFIG_PPTP=y CONFIG_PPPOL2TP=y CONFIG_PPP_ASYNC=y CONFIG_PPP_SYNC_TTY=y CONFIG_SLIP=y CONFIG_SLHC=y CONFIG_SLIP_COMPRESSED=y CONFIG_SLIP_SMART=y CONFIG_SLIP_MODE_SLIP6=y CONFIG_USB_NET_DRIVERS=y CONFIG_USB_CATC=y CONFIG_USB_KAWETH=y CONFIG_USB_PEGASUS=y CONFIG_USB_RTL8150=y CONFIG_USB_RTL8152=y CONFIG_USB_LAN78XX=y CONFIG_USB_USBNET=y CONFIG_USB_NET_AX8817X=y CONFIG_USB_NET_AX88179_178A=y CONFIG_USB_NET_CDCETHER=y CONFIG_USB_NET_CDC_EEM=y CONFIG_USB_NET_CDC_NCM=y CONFIG_USB_NET_HUAWEI_CDC_NCM=y CONFIG_USB_NET_CDC_MBIM=y CONFIG_USB_NET_DM9601=y CONFIG_USB_NET_SR9700=y CONFIG_USB_NET_SR9800=y CONFIG_USB_NET_SMSC75XX=y CONFIG_USB_NET_SMSC95XX=y CONFIG_USB_NET_GL620A=y CONFIG_USB_NET_NET1080=y CONFIG_USB_NET_PLUSB=y CONFIG_USB_NET_MCS7830=y CONFIG_USB_NET_RNDIS_HOST=y CONFIG_USB_NET_CDC_SUBSET_ENABLE=y CONFIG_USB_NET_CDC_SUBSET=y CONFIG_USB_ALI_M5632=y CONFIG_USB_AN2720=y CONFIG_USB_BELKIN=y CONFIG_USB_ARMLINUX=y CONFIG_USB_EPSON2888=y CONFIG_USB_KC2190=y CONFIG_USB_NET_ZAURUS=y CONFIG_USB_NET_CX82310_ETH=y CONFIG_USB_NET_KALMIA=y CONFIG_USB_NET_QMI_WWAN=y CONFIG_USB_HSO=y CONFIG_USB_NET_INT51X1=y CONFIG_USB_CDC_PHONET=y CONFIG_USB_IPHETH=y CONFIG_USB_SIERRA_NET=y CONFIG_USB_VL600=y CONFIG_USB_NET_CH9200=y CONFIG_USB_NET_AQC111=y CONFIG_USB_RTL8153_ECM=y CONFIG_WLAN=y CONFIG_WLAN_VENDOR_ADMTEK=y # CONFIG_ADM8211 is not set CONFIG_ATH_COMMON=y CONFIG_WLAN_VENDOR_ATH=y # CONFIG_ATH_DEBUG is not set # CONFIG_ATH5K is not set # CONFIG_ATH5K_PCI is not set CONFIG_ATH9K_HW=y CONFIG_ATH9K_COMMON=y CONFIG_ATH9K_COMMON_DEBUG=y CONFIG_ATH9K_BTCOEX_SUPPORT=y CONFIG_ATH9K=y # CONFIG_ATH9K_PCI is not set # CONFIG_ATH9K_AHB is not set CONFIG_ATH9K_DEBUGFS=y # CONFIG_ATH9K_STATION_STATISTICS is not set # CONFIG_ATH9K_DYNACK is not set # CONFIG_ATH9K_WOW is not set # CONFIG_ATH9K_RFKILL is not set # CONFIG_ATH9K_CHANNEL_CONTEXT is not set # CONFIG_ATH9K_PCOEM is not set CONFIG_ATH9K_HTC=y CONFIG_ATH9K_HTC_DEBUGFS=y # CONFIG_ATH9K_HWRNG is not set CONFIG_ATH9K_COMMON_SPECTRAL=y CONFIG_CARL9170=y CONFIG_CARL9170_LEDS=y # CONFIG_CARL9170_DEBUGFS is not set CONFIG_CARL9170_WPC=y CONFIG_CARL9170_HWRNG=y CONFIG_ATH6KL=y # CONFIG_ATH6KL_SDIO is not set CONFIG_ATH6KL_USB=y # CONFIG_ATH6KL_DEBUG is not set # CONFIG_ATH6KL_TRACING is not set CONFIG_AR5523=y # CONFIG_WIL6210 is not set CONFIG_ATH10K=y CONFIG_ATH10K_CE=y # CONFIG_ATH10K_PCI is not set # CONFIG_ATH10K_SDIO is not set CONFIG_ATH10K_USB=y # CONFIG_ATH10K_DEBUG is not set # CONFIG_ATH10K_DEBUGFS is not set CONFIG_ATH10K_LEDS=y # CONFIG_ATH10K_TRACING is not set # CONFIG_WCN36XX is not set # CONFIG_ATH11K is not set # CONFIG_ATH12K is not set CONFIG_WLAN_VENDOR_ATMEL=y CONFIG_AT76C50X_USB=y CONFIG_WLAN_VENDOR_BROADCOM=y # CONFIG_B43 is not set # CONFIG_B43LEGACY is not set CONFIG_BRCMUTIL=y # CONFIG_BRCMSMAC is not set CONFIG_BRCMFMAC=y CONFIG_BRCMFMAC_PROTO_BCDC=y # CONFIG_BRCMFMAC_SDIO is not set CONFIG_BRCMFMAC_USB=y # CONFIG_BRCMFMAC_PCIE is not set # CONFIG_BRCM_TRACING is not set # CONFIG_BRCMDBG is not set CONFIG_WLAN_VENDOR_INTEL=y # CONFIG_IPW2100 is not set # CONFIG_IPW2200 is not set # CONFIG_IWL4965 is not set # CONFIG_IWL3945 is not set # CONFIG_IWLWIFI is not set CONFIG_WLAN_VENDOR_INTERSIL=y CONFIG_P54_COMMON=y CONFIG_P54_USB=y # CONFIG_P54_PCI is not set # CONFIG_P54_SPI is not set CONFIG_P54_LEDS=y CONFIG_WLAN_VENDOR_MARVELL=y CONFIG_LIBERTAS=y CONFIG_LIBERTAS_USB=y CONFIG_LIBERTAS_SDIO=y CONFIG_LIBERTAS_SPI=y # CONFIG_LIBERTAS_DEBUG is not set CONFIG_LIBERTAS_MESH=y CONFIG_LIBERTAS_THINFIRM=y # CONFIG_LIBERTAS_THINFIRM_DEBUG is not set CONFIG_LIBERTAS_THINFIRM_USB=y CONFIG_MWIFIEX=y # CONFIG_MWIFIEX_SDIO is not set # CONFIG_MWIFIEX_PCIE is not set CONFIG_MWIFIEX_USB=y # CONFIG_MWL8K is not set CONFIG_WLAN_VENDOR_MEDIATEK=y CONFIG_MT7601U=y CONFIG_MT76_CORE=y CONFIG_MT76_LEDS=y CONFIG_MT76_USB=y CONFIG_MT76x02_LIB=y CONFIG_MT76x02_USB=y CONFIG_MT76_CONNAC_LIB=y CONFIG_MT792x_LIB=y CONFIG_MT792x_USB=y CONFIG_MT76x0_COMMON=y CONFIG_MT76x0U=y # CONFIG_MT76x0E is not set CONFIG_MT76x2_COMMON=y # CONFIG_MT76x2E is not set CONFIG_MT76x2U=y # CONFIG_MT7603E is not set CONFIG_MT7615_COMMON=y # CONFIG_MT7615E is not set CONFIG_MT7663_USB_SDIO_COMMON=y CONFIG_MT7663U=y # CONFIG_MT7663S is not set # CONFIG_MT7915E is not set CONFIG_MT7921_COMMON=y # CONFIG_MT7921E is not set # CONFIG_MT7921S is not set CONFIG_MT7921U=y # CONFIG_MT7996E is not set CONFIG_MT7925_COMMON=y # CONFIG_MT7925E is not set CONFIG_MT7925U=y CONFIG_WLAN_VENDOR_MICROCHIP=y CONFIG_WILC1000=y CONFIG_WILC1000_SDIO=y # CONFIG_WILC1000_SPI is not set # CONFIG_WILC1000_HW_OOB_INTR is not set CONFIG_WLAN_VENDOR_PURELIFI=y CONFIG_PLFXLC=y CONFIG_WLAN_VENDOR_RALINK=y CONFIG_RT2X00=y # CONFIG_RT2400PCI is not set # CONFIG_RT2500PCI is not set # CONFIG_RT61PCI is not set # CONFIG_RT2800PCI is not set CONFIG_RT2500USB=y CONFIG_RT73USB=y CONFIG_RT2800USB=y CONFIG_RT2800USB_RT33XX=y CONFIG_RT2800USB_RT35XX=y CONFIG_RT2800USB_RT3573=y CONFIG_RT2800USB_RT53XX=y CONFIG_RT2800USB_RT55XX=y CONFIG_RT2800USB_UNKNOWN=y CONFIG_RT2800_LIB=y CONFIG_RT2X00_LIB_USB=y CONFIG_RT2X00_LIB=y CONFIG_RT2X00_LIB_FIRMWARE=y CONFIG_RT2X00_LIB_CRYPTO=y CONFIG_RT2X00_LIB_LEDS=y # CONFIG_RT2X00_LIB_DEBUGFS is not set # CONFIG_RT2X00_DEBUG is not set CONFIG_WLAN_VENDOR_REALTEK=y # CONFIG_RTL8180 is not set CONFIG_RTL8187=y CONFIG_RTL8187_LEDS=y CONFIG_RTL_CARDS=y CONFIG_RTL8192CE=y CONFIG_RTL8192SE=y CONFIG_RTL8192DE=y CONFIG_RTL8723AE=y CONFIG_RTL8723BE=y CONFIG_RTL8188EE=y CONFIG_RTL8192EE=y CONFIG_RTL8821AE=y CONFIG_RTL8192CU=y # CONFIG_RTL8192DU is not set CONFIG_RTLWIFI=y CONFIG_RTLWIFI_PCI=y CONFIG_RTLWIFI_USB=y # CONFIG_RTLWIFI_DEBUG is not set CONFIG_RTL8192C_COMMON=y CONFIG_RTL8192D_COMMON=y CONFIG_RTL8723_COMMON=y CONFIG_RTLBTCOEXIST=y CONFIG_RTL8XXXU=y CONFIG_RTL8XXXU_UNTESTED=y CONFIG_RTW88=y CONFIG_RTW88_CORE=y CONFIG_RTW88_USB=y CONFIG_RTW88_8822B=y CONFIG_RTW88_8822C=y CONFIG_RTW88_8723X=y CONFIG_RTW88_8723D=y CONFIG_RTW88_8821C=y # CONFIG_RTW88_8822BE is not set # CONFIG_RTW88_8822BS is not set CONFIG_RTW88_8822BU=y # CONFIG_RTW88_8822CE is not set # CONFIG_RTW88_8822CS is not set CONFIG_RTW88_8822CU=y # CONFIG_RTW88_8723DE is not set # CONFIG_RTW88_8723DS is not set # CONFIG_RTW88_8723CS is not set CONFIG_RTW88_8723DU=y # CONFIG_RTW88_8821CE is not set # CONFIG_RTW88_8821CS is not set CONFIG_RTW88_8821CU=y # CONFIG_RTW88_8821AU is not set # CONFIG_RTW88_8812AU is not set # CONFIG_RTW88_8814AE is not set # CONFIG_RTW88_8814AU is not set # CONFIG_RTW88_DEBUG is not set # CONFIG_RTW88_DEBUGFS is not set CONFIG_RTW88_LEDS=y CONFIG_RTW89=y # CONFIG_RTW89_8851BE is not set # CONFIG_RTW89_8851BU is not set # CONFIG_RTW89_8852AE is not set # CONFIG_RTW89_8852AU is not set # CONFIG_RTW89_8852BE is not set # CONFIG_RTW89_8852BU is not set # CONFIG_RTW89_8852BTE is not set # CONFIG_RTW89_8852CE is not set # CONFIG_RTW89_8852CU is not set # CONFIG_RTW89_8922AE is not set CONFIG_WLAN_VENDOR_RSI=y CONFIG_RSI_91X=y # CONFIG_RSI_DEBUGFS is not set # CONFIG_RSI_SDIO is not set CONFIG_RSI_USB=y # CONFIG_RSI_COEX is not set CONFIG_WLAN_VENDOR_SILABS=y # CONFIG_WFX is not set CONFIG_WLAN_VENDOR_ST=y # CONFIG_CW1200 is not set CONFIG_WLAN_VENDOR_TI=y # CONFIG_WL1251 is not set # CONFIG_WL12XX is not set # CONFIG_WL18XX is not set # CONFIG_WLCORE is not set CONFIG_WLAN_VENDOR_ZYDAS=y CONFIG_ZD1211RW=y # CONFIG_ZD1211RW_DEBUG is not set CONFIG_WLAN_VENDOR_QUANTENNA=y # CONFIG_QTNFMAC_PCIE is not set # CONFIG_MAC80211_HWSIM is not set # CONFIG_VIRT_WIFI is not set CONFIG_WAN=y CONFIG_HDLC=y CONFIG_HDLC_RAW=y CONFIG_HDLC_RAW_ETH=y CONFIG_HDLC_CISCO=y CONFIG_HDLC_FR=y CONFIG_HDLC_PPP=y CONFIG_HDLC_X25=y # CONFIG_FRAMER is not set # CONFIG_PCI200SYN is not set # CONFIG_WANXL is not set # CONFIG_PC300TOO is not set # CONFIG_FARSYNC is not set CONFIG_LAPBETHER=y CONFIG_IEEE802154_DRIVERS=y # CONFIG_IEEE802154_FAKELB is not set # CONFIG_IEEE802154_AT86RF230 is not set # CONFIG_IEEE802154_MRF24J40 is not set # CONFIG_IEEE802154_CC2520 is not set CONFIG_IEEE802154_ATUSB=y # CONFIG_IEEE802154_ADF7242 is not set # CONFIG_IEEE802154_CA8210 is not set # CONFIG_IEEE802154_MCR20A is not set CONFIG_IEEE802154_HWSIM=y # # Wireless WAN # # CONFIG_WWAN is not set # end of Wireless WAN CONFIG_VMXNET3=y # CONFIG_FUJITSU_ES is not set CONFIG_USB4_NET=y CONFIG_NETDEVSIM=y CONFIG_NET_FAILOVER=y # # Input device support # CONFIG_INPUT=y CONFIG_INPUT_LEDS=y CONFIG_INPUT_FF_MEMLESS=y CONFIG_INPUT_SPARSEKMAP=y # CONFIG_INPUT_MATRIXKMAP is not set CONFIG_INPUT_VIVALDIFMAP=y # # Userland interfaces # # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_JOYDEV is not set CONFIG_INPUT_EVDEV=y # # Input Device Drivers # CONFIG_INPUT_KEYBOARD=y # CONFIG_KEYBOARD_ADC is not set # CONFIG_KEYBOARD_ADP5588 is not set CONFIG_KEYBOARD_ATKBD=y # CONFIG_KEYBOARD_QT1050 is not set # CONFIG_KEYBOARD_QT1070 is not set # CONFIG_KEYBOARD_QT2160 is not set # CONFIG_KEYBOARD_DLINK_DIR685 is not set # CONFIG_KEYBOARD_LKKBD is not set # CONFIG_KEYBOARD_GPIO is not set # CONFIG_KEYBOARD_GPIO_POLLED is not set # CONFIG_KEYBOARD_TCA8418 is not set # CONFIG_KEYBOARD_MATRIX is not set # CONFIG_KEYBOARD_CHARLIEPLEX is not set # CONFIG_KEYBOARD_LM8323 is not set # CONFIG_KEYBOARD_LM8333 is not set # CONFIG_KEYBOARD_MAX7359 is not set # CONFIG_KEYBOARD_MPR121 is not set # CONFIG_KEYBOARD_NEWTON is not set # CONFIG_KEYBOARD_OPENCORES is not set # CONFIG_KEYBOARD_PINEPHONE is not set # CONFIG_KEYBOARD_SAMSUNG is not set # CONFIG_KEYBOARD_STOWAWAY is not set # CONFIG_KEYBOARD_SUNKBD is not set # CONFIG_KEYBOARD_OMAP4 is not set # CONFIG_KEYBOARD_TM2_TOUCHKEY is not set # CONFIG_KEYBOARD_TWL4030 is not set # CONFIG_KEYBOARD_XTKBD is not set # CONFIG_KEYBOARD_CROS_EC is not set # CONFIG_KEYBOARD_CAP11XX is not set # CONFIG_KEYBOARD_BCM is not set # CONFIG_KEYBOARD_CYPRESS_SF is not set CONFIG_INPUT_MOUSE=y CONFIG_MOUSE_PS2=y CONFIG_MOUSE_PS2_ALPS=y CONFIG_MOUSE_PS2_BYD=y CONFIG_MOUSE_PS2_LOGIPS2PP=y CONFIG_MOUSE_PS2_SYNAPTICS=y CONFIG_MOUSE_PS2_SYNAPTICS_SMBUS=y CONFIG_MOUSE_PS2_CYPRESS=y CONFIG_MOUSE_PS2_LIFEBOOK=y CONFIG_MOUSE_PS2_TRACKPOINT=y # CONFIG_MOUSE_PS2_ELANTECH is not set # CONFIG_MOUSE_PS2_SENTELIC is not set # CONFIG_MOUSE_PS2_TOUCHKIT is not set CONFIG_MOUSE_PS2_FOCALTECH=y # CONFIG_MOUSE_PS2_VMMOUSE is not set CONFIG_MOUSE_PS2_SMBUS=y # CONFIG_MOUSE_SERIAL is not set CONFIG_MOUSE_APPLETOUCH=y CONFIG_MOUSE_BCM5974=y # CONFIG_MOUSE_CYAPA is not set # CONFIG_MOUSE_ELAN_I2C is not set # CONFIG_MOUSE_VSXXXAA is not set # CONFIG_MOUSE_GPIO is not set # CONFIG_MOUSE_SYNAPTICS_I2C is not set CONFIG_MOUSE_SYNAPTICS_USB=y CONFIG_INPUT_JOYSTICK=y # CONFIG_JOYSTICK_ANALOG is not set # CONFIG_JOYSTICK_A3D is not set # CONFIG_JOYSTICK_ADC is not set # CONFIG_JOYSTICK_ADI is not set # CONFIG_JOYSTICK_COBRA is not set # CONFIG_JOYSTICK_GF2K is not set # CONFIG_JOYSTICK_GRIP is not set # CONFIG_JOYSTICK_GRIP_MP is not set # CONFIG_JOYSTICK_GUILLEMOT is not set # CONFIG_JOYSTICK_INTERACT is not set # CONFIG_JOYSTICK_SIDEWINDER is not set # CONFIG_JOYSTICK_TMDC is not set CONFIG_JOYSTICK_IFORCE=y CONFIG_JOYSTICK_IFORCE_USB=y # CONFIG_JOYSTICK_IFORCE_232 is not set # CONFIG_JOYSTICK_WARRIOR is not set # CONFIG_JOYSTICK_MAGELLAN is not set # CONFIG_JOYSTICK_SPACEORB is not set # CONFIG_JOYSTICK_SPACEBALL is not set # CONFIG_JOYSTICK_STINGER is not set # CONFIG_JOYSTICK_TWIDJOY is not set # CONFIG_JOYSTICK_ZHENHUA is not set # CONFIG_JOYSTICK_DB9 is not set # CONFIG_JOYSTICK_GAMECON is not set # CONFIG_JOYSTICK_TURBOGRAFX is not set # CONFIG_JOYSTICK_AS5011 is not set # CONFIG_JOYSTICK_JOYDUMP is not set CONFIG_JOYSTICK_XPAD=y CONFIG_JOYSTICK_XPAD_FF=y CONFIG_JOYSTICK_XPAD_LEDS=y # CONFIG_JOYSTICK_WALKERA0701 is not set # CONFIG_JOYSTICK_PSXPAD_SPI is not set CONFIG_JOYSTICK_PXRC=y # CONFIG_JOYSTICK_QWIIC is not set # CONFIG_JOYSTICK_FSIA6B is not set # CONFIG_JOYSTICK_SENSEHAT is not set # CONFIG_JOYSTICK_SEESAW is not set CONFIG_INPUT_TABLET=y CONFIG_TABLET_USB_ACECAD=y CONFIG_TABLET_USB_AIPTEK=y CONFIG_TABLET_USB_HANWANG=y CONFIG_TABLET_USB_KBTAB=y CONFIG_TABLET_USB_PEGASUS=y # CONFIG_TABLET_SERIAL_WACOM4 is not set CONFIG_INPUT_TOUCHSCREEN=y # CONFIG_TOUCHSCREEN_ADS7846 is not set # CONFIG_TOUCHSCREEN_AD7877 is not set # CONFIG_TOUCHSCREEN_AD7879 is not set # CONFIG_TOUCHSCREEN_ADC is not set # CONFIG_TOUCHSCREEN_AR1021_I2C is not set # CONFIG_TOUCHSCREEN_ATMEL_MXT is not set # CONFIG_TOUCHSCREEN_AUO_PIXCIR is not set # CONFIG_TOUCHSCREEN_BU21013 is not set # CONFIG_TOUCHSCREEN_BU21029 is not set # CONFIG_TOUCHSCREEN_CHIPONE_ICN8318 is not set # CONFIG_TOUCHSCREEN_CHIPONE_ICN8505 is not set # CONFIG_TOUCHSCREEN_CY8CTMA140 is not set # CONFIG_TOUCHSCREEN_CY8CTMG110 is not set # CONFIG_TOUCHSCREEN_CYTTSP_CORE is not set # CONFIG_TOUCHSCREEN_CYTTSP5 is not set # CONFIG_TOUCHSCREEN_DYNAPRO is not set # CONFIG_TOUCHSCREEN_HAMPSHIRE is not set # CONFIG_TOUCHSCREEN_EETI is not set # CONFIG_TOUCHSCREEN_EGALAX is not set # CONFIG_TOUCHSCREEN_EGALAX_SERIAL is not set # CONFIG_TOUCHSCREEN_EXC3000 is not set # CONFIG_TOUCHSCREEN_FUJITSU is not set # CONFIG_TOUCHSCREEN_GOODIX is not set # CONFIG_TOUCHSCREEN_GOODIX_BERLIN_I2C is not set # CONFIG_TOUCHSCREEN_GOODIX_BERLIN_SPI is not set # CONFIG_TOUCHSCREEN_HIDEEP is not set # CONFIG_TOUCHSCREEN_HIMAX_HX852X is not set # CONFIG_TOUCHSCREEN_HYCON_HY46XX is not set # CONFIG_TOUCHSCREEN_HYNITRON_CSTXXX is not set # CONFIG_TOUCHSCREEN_HYNITRON_CST816X is not set # CONFIG_TOUCHSCREEN_ILI210X is not set # CONFIG_TOUCHSCREEN_ILITEK is not set # CONFIG_TOUCHSCREEN_S6SY761 is not set # CONFIG_TOUCHSCREEN_GUNZE is not set # CONFIG_TOUCHSCREEN_EKTF2127 is not set # CONFIG_TOUCHSCREEN_ELAN is not set # CONFIG_TOUCHSCREEN_ELO is not set # CONFIG_TOUCHSCREEN_WACOM_W8001 is not set # CONFIG_TOUCHSCREEN_WACOM_I2C is not set # CONFIG_TOUCHSCREEN_MAX11801 is not set # CONFIG_TOUCHSCREEN_MMS114 is not set # CONFIG_TOUCHSCREEN_MELFAS_MIP4 is not set # CONFIG_TOUCHSCREEN_MSG2638 is not set # CONFIG_TOUCHSCREEN_MTOUCH is not set # CONFIG_TOUCHSCREEN_NOVATEK_NVT_TS is not set # CONFIG_TOUCHSCREEN_IMAGIS is not set # CONFIG_TOUCHSCREEN_IMX6UL_TSC is not set # CONFIG_TOUCHSCREEN_INEXIO is not set # CONFIG_TOUCHSCREEN_PENMOUNT is not set # CONFIG_TOUCHSCREEN_EDT_FT5X06 is not set # CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set # CONFIG_TOUCHSCREEN_TOUCHWIN is not set # CONFIG_TOUCHSCREEN_PIXCIR is not set # CONFIG_TOUCHSCREEN_WDT87XX_I2C is not set CONFIG_TOUCHSCREEN_USB_COMPOSITE=y CONFIG_TOUCHSCREEN_USB_EGALAX=y CONFIG_TOUCHSCREEN_USB_PANJIT=y CONFIG_TOUCHSCREEN_USB_3M=y CONFIG_TOUCHSCREEN_USB_ITM=y CONFIG_TOUCHSCREEN_USB_ETURBO=y CONFIG_TOUCHSCREEN_USB_GUNZE=y CONFIG_TOUCHSCREEN_USB_DMC_TSC10=y CONFIG_TOUCHSCREEN_USB_IRTOUCH=y CONFIG_TOUCHSCREEN_USB_IDEALTEK=y CONFIG_TOUCHSCREEN_USB_GENERAL_TOUCH=y CONFIG_TOUCHSCREEN_USB_GOTOP=y CONFIG_TOUCHSCREEN_USB_JASTEC=y CONFIG_TOUCHSCREEN_USB_ELO=y CONFIG_TOUCHSCREEN_USB_E2I=y CONFIG_TOUCHSCREEN_USB_ZYTRONIC=y CONFIG_TOUCHSCREEN_USB_ETT_TC45USB=y CONFIG_TOUCHSCREEN_USB_NEXIO=y CONFIG_TOUCHSCREEN_USB_EASYTOUCH=y # CONFIG_TOUCHSCREEN_TOUCHIT213 is not set # CONFIG_TOUCHSCREEN_TSC_SERIO is not set # CONFIG_TOUCHSCREEN_TSC2004 is not set # CONFIG_TOUCHSCREEN_TSC2005 is not set # CONFIG_TOUCHSCREEN_TSC2007 is not set # CONFIG_TOUCHSCREEN_RM_TS is not set # CONFIG_TOUCHSCREEN_SILEAD is not set # CONFIG_TOUCHSCREEN_SIS_I2C is not set # CONFIG_TOUCHSCREEN_ST1232 is not set # CONFIG_TOUCHSCREEN_STMFTS is not set CONFIG_TOUCHSCREEN_SUR40=y # CONFIG_TOUCHSCREEN_SURFACE3_SPI is not set # CONFIG_TOUCHSCREEN_SX8654 is not set # CONFIG_TOUCHSCREEN_TPS6507X is not set # CONFIG_TOUCHSCREEN_ZET6223 is not set # CONFIG_TOUCHSCREEN_ZFORCE is not set # CONFIG_TOUCHSCREEN_COLIBRI_VF50 is not set # CONFIG_TOUCHSCREEN_ROHM_BU21023 is not set # CONFIG_TOUCHSCREEN_IQS5XX is not set # CONFIG_TOUCHSCREEN_IQS7211 is not set # CONFIG_TOUCHSCREEN_ZINITIX is not set # CONFIG_TOUCHSCREEN_HIMAX_HX83112B is not set CONFIG_INPUT_MISC=y # CONFIG_INPUT_AD714X is not set # CONFIG_INPUT_ATMEL_CAPTOUCH is not set # CONFIG_INPUT_AW86927 is not set # CONFIG_INPUT_BMA150 is not set # CONFIG_INPUT_E3X0_BUTTON is not set # CONFIG_INPUT_PCSPKR is not set # CONFIG_INPUT_MMA8450 is not set # CONFIG_INPUT_APANEL is not set # CONFIG_INPUT_GPIO_BEEPER is not set # CONFIG_INPUT_GPIO_DECODER is not set # CONFIG_INPUT_GPIO_VIBRA is not set # CONFIG_INPUT_ATLAS_BTNS is not set CONFIG_INPUT_ATI_REMOTE2=y CONFIG_INPUT_KEYSPAN_REMOTE=y # CONFIG_INPUT_KXTJ9 is not set CONFIG_INPUT_POWERMATE=y CONFIG_INPUT_YEALINK=y CONFIG_INPUT_CM109=y # CONFIG_INPUT_REGULATOR_HAPTIC is not set # CONFIG_INPUT_RETU_PWRBUTTON is not set # CONFIG_INPUT_TWL4030_PWRBUTTON is not set # CONFIG_INPUT_TWL4030_VIBRA is not set # CONFIG_INPUT_UINPUT is not set # CONFIG_INPUT_PCF8574 is not set # CONFIG_INPUT_GPIO_ROTARY_ENCODER is not set # CONFIG_INPUT_DA7280_HAPTICS is not set # CONFIG_INPUT_ADXL34X is not set CONFIG_INPUT_IMS_PCU=y # CONFIG_INPUT_IQS269A is not set # CONFIG_INPUT_IQS626A is not set # CONFIG_INPUT_IQS7222 is not set # CONFIG_INPUT_CMA3000 is not set # CONFIG_INPUT_IDEAPAD_SLIDEBAR is not set # CONFIG_INPUT_DRV260X_HAPTICS is not set # CONFIG_INPUT_DRV2665_HAPTICS is not set # CONFIG_INPUT_DRV2667_HAPTICS is not set CONFIG_RMI4_CORE=y # CONFIG_RMI4_I2C is not set # CONFIG_RMI4_SPI is not set # CONFIG_RMI4_SMB is not set CONFIG_RMI4_F03=y CONFIG_RMI4_F03_SERIO=y CONFIG_RMI4_2D_SENSOR=y CONFIG_RMI4_F11=y CONFIG_RMI4_F12=y # CONFIG_RMI4_F1A is not set # CONFIG_RMI4_F21 is not set CONFIG_RMI4_F30=y # CONFIG_RMI4_F34 is not set CONFIG_RMI4_F3A=y # CONFIG_RMI4_F54 is not set # CONFIG_RMI4_F55 is not set # # Hardware I/O ports # CONFIG_SERIO=y CONFIG_ARCH_MIGHT_HAVE_PC_SERIO=y CONFIG_SERIO_I8042=y CONFIG_SERIO_SERPORT=y # CONFIG_SERIO_PARKBD is not set # CONFIG_SERIO_PCIPS2 is not set CONFIG_SERIO_LIBPS2=y # CONFIG_SERIO_RAW is not set # CONFIG_SERIO_ALTERA_PS2 is not set # CONFIG_SERIO_PS2MULT is not set # CONFIG_SERIO_ARC_PS2 is not set # CONFIG_SERIO_APBPS2 is not set # CONFIG_SERIO_GPIO_PS2 is not set # CONFIG_USERIO is not set # CONFIG_GAMEPORT is not set # end of Hardware I/O ports # end of Input device support # # Character devices # CONFIG_TTY=y CONFIG_VT=y CONFIG_CONSOLE_TRANSLATIONS=y CONFIG_VT_CONSOLE=y CONFIG_VT_CONSOLE_SLEEP=y # CONFIG_VT_HW_CONSOLE_BINDING is not set CONFIG_UNIX98_PTYS=y # CONFIG_LEGACY_PTYS is not set CONFIG_LEGACY_TIOCSTI=y CONFIG_LDISC_AUTOLOAD=y # # Serial drivers # CONFIG_SERIAL_EARLYCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_PNP=y # CONFIG_SERIAL_8250_16550A_VARIANTS is not set # CONFIG_SERIAL_8250_FINTEK is not set CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DMA=y CONFIG_SERIAL_8250_PCILIB=y CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_EXAR=y # CONFIG_SERIAL_8250_CS is not set CONFIG_SERIAL_8250_NR_UARTS=32 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y CONFIG_SERIAL_8250_MANY_PORTS=y # CONFIG_SERIAL_8250_PCI1XXXX is not set # CONFIG_SERIAL_8250_DW is not set # CONFIG_SERIAL_8250_RT288X is not set CONFIG_SERIAL_8250_LPSS=y CONFIG_SERIAL_8250_MID=y CONFIG_SERIAL_8250_PERICOM=y # CONFIG_SERIAL_8250_NI is not set # CONFIG_SERIAL_OF_PLATFORM is not set CONFIG_SERIAL_8250_DWLIB=y # # Non-8250 serial port support # # CONFIG_SERIAL_MAX3100 is not set # CONFIG_SERIAL_MAX310X is not set # CONFIG_SERIAL_UARTLITE is not set CONFIG_SERIAL_CORE=y CONFIG_SERIAL_CORE_CONSOLE=y # CONFIG_SERIAL_JSM is not set # CONFIG_SERIAL_SIFIVE is not set # CONFIG_SERIAL_LANTIQ is not set # CONFIG_SERIAL_SCCNXP is not set # CONFIG_SERIAL_SC16IS7XX is not set # CONFIG_SERIAL_ALTERA_JTAGUART is not set # CONFIG_SERIAL_ALTERA_UART is not set # CONFIG_SERIAL_XILINX_PS_UART is not set # CONFIG_SERIAL_ARC is not set # CONFIG_SERIAL_RP2 is not set # CONFIG_SERIAL_FSL_LPUART is not set # CONFIG_SERIAL_FSL_LINFLEXUART is not set # CONFIG_SERIAL_CONEXANT_DIGICOLOR is not set # CONFIG_SERIAL_SPRD is not set # end of Serial drivers CONFIG_SERIAL_MCTRL_GPIO=y CONFIG_SERIAL_NONSTANDARD=y # CONFIG_MOXA_INTELLIO is not set # CONFIG_MOXA_SMARTIO is not set # CONFIG_N_HDLC is not set # CONFIG_IPWIRELESS is not set # CONFIG_N_GSM is not set # CONFIG_NOZOMI is not set # CONFIG_NULL_TTY is not set CONFIG_HVC_DRIVER=y CONFIG_SERIAL_DEV_BUS=y # CONFIG_SERIAL_DEV_CTRL_TTYPORT is not set # CONFIG_TTY_PRINTK is not set # CONFIG_PRINTER is not set # CONFIG_PPDEV is not set CONFIG_VIRTIO_CONSOLE=y # CONFIG_IPMI_HANDLER is not set CONFIG_HW_RANDOM=y # CONFIG_HW_RANDOM_TIMERIOMEM is not set # CONFIG_HW_RANDOM_INTEL is not set # CONFIG_HW_RANDOM_AMD is not set # CONFIG_HW_RANDOM_BA431 is not set # CONFIG_HW_RANDOM_VIA is not set CONFIG_HW_RANDOM_VIRTIO=y # CONFIG_HW_RANDOM_CCTRNG is not set # CONFIG_HW_RANDOM_XIPHERA is not set # CONFIG_APPLICOM is not set # CONFIG_DEVMEM is not set CONFIG_NVRAM=y # CONFIG_DEVPORT is not set CONFIG_HPET=y # CONFIG_HPET_MMAP is not set # CONFIG_HANGCHECK_TIMER is not set # CONFIG_TCG_TPM is not set # CONFIG_TELCLOCK is not set CONFIG_XILLYBUS_CLASS=y # CONFIG_XILLYBUS is not set CONFIG_XILLYUSB=y # end of Character devices # # I2C support # CONFIG_I2C=y CONFIG_ACPI_I2C_OPREGION=y CONFIG_I2C_BOARDINFO=y # CONFIG_I2C_CHARDEV is not set CONFIG_I2C_MUX=y # # Multiplexer I2C Chip support # # CONFIG_I2C_ARB_GPIO_CHALLENGE is not set # CONFIG_I2C_MUX_GPIO is not set # CONFIG_I2C_MUX_GPMUX is not set # CONFIG_I2C_MUX_LTC4306 is not set # CONFIG_I2C_MUX_PCA9541 is not set # CONFIG_I2C_MUX_PCA954x is not set # CONFIG_I2C_MUX_REG is not set # CONFIG_I2C_MUX_MLXCPLD is not set # end of Multiplexer I2C Chip support CONFIG_I2C_HELPER_AUTO=y CONFIG_I2C_SMBUS=y CONFIG_I2C_ALGOBIT=y # # I2C Hardware Bus support # # # PC SMBus host controller drivers # # CONFIG_I2C_ALI1535 is not set # CONFIG_I2C_ALI1563 is not set # CONFIG_I2C_ALI15X3 is not set # CONFIG_I2C_AMD756 is not set # CONFIG_I2C_AMD8111 is not set # CONFIG_I2C_AMD_MP2 is not set CONFIG_I2C_I801=y # CONFIG_I2C_ISCH is not set # CONFIG_I2C_ISMT is not set # CONFIG_I2C_PIIX4 is not set # CONFIG_I2C_CHT_WC is not set # CONFIG_I2C_NFORCE2 is not set # CONFIG_I2C_NVIDIA_GPU is not set # CONFIG_I2C_SIS5595 is not set # CONFIG_I2C_SIS630 is not set # CONFIG_I2C_SIS96X is not set # CONFIG_I2C_VIA is not set # CONFIG_I2C_VIAPRO is not set # CONFIG_I2C_ZHAOXIN is not set # # ACPI drivers # # CONFIG_I2C_SCMI is not set # # I2C system bus drivers (mostly embedded / system-on-chip) # # CONFIG_I2C_CBUS_GPIO is not set CONFIG_I2C_DESIGNWARE_CORE=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_I2C_DESIGNWARE_AMDPSP is not set # CONFIG_I2C_DESIGNWARE_BAYTRAIL is not set # CONFIG_I2C_DESIGNWARE_PCI is not set # CONFIG_I2C_EMEV2 is not set # CONFIG_I2C_GPIO is not set # CONFIG_I2C_OCORES is not set # CONFIG_I2C_PCA_PLATFORM is not set # CONFIG_I2C_RK3X is not set # CONFIG_I2C_SIMTEC is not set # CONFIG_I2C_XILINX is not set # # External I2C/SMBus adapter drivers # CONFIG_I2C_DIOLAN_U2C=y CONFIG_I2C_DLN2=y CONFIG_I2C_LJCA=y CONFIG_I2C_CP2615=y # CONFIG_I2C_PARPORT is not set # CONFIG_I2C_PCI1XXXX is not set CONFIG_I2C_ROBOTFUZZ_OSIF=y # CONFIG_I2C_TAOS_EVM is not set CONFIG_I2C_TINY_USB=y CONFIG_I2C_VIPERBOARD=y # # Other I2C/SMBus bus drivers # # CONFIG_I2C_MLXCPLD is not set # CONFIG_I2C_CROS_EC_TUNNEL is not set # CONFIG_I2C_VIRTIO is not set # end of I2C Hardware Bus support # CONFIG_I2C_STUB is not set # CONFIG_I2C_SLAVE is not set # CONFIG_I2C_DEBUG_CORE is not set # CONFIG_I2C_DEBUG_ALGO is not set # CONFIG_I2C_DEBUG_BUS is not set # end of I2C support # CONFIG_I3C is not set CONFIG_I3C_OR_I2C=y CONFIG_SPI=y # CONFIG_SPI_DEBUG is not set CONFIG_SPI_MASTER=y # CONFIG_SPI_MEM is not set # # SPI Master Controller Drivers # # CONFIG_SPI_ALTERA is not set # CONFIG_SPI_AXI_SPI_ENGINE is not set # CONFIG_SPI_BITBANG is not set # CONFIG_SPI_BUTTERFLY is not set # CONFIG_SPI_CADENCE is not set # CONFIG_SPI_CADENCE_QUADSPI is not set # CONFIG_SPI_CH341 is not set # CONFIG_SPI_DESIGNWARE is not set CONFIG_SPI_DLN2=y # CONFIG_SPI_GPIO is not set # CONFIG_SPI_LM70_LLP is not set # CONFIG_SPI_FSL_SPI is not set CONFIG_SPI_LJCA=y # CONFIG_SPI_MICROCHIP_CORE_QSPI is not set # CONFIG_SPI_MICROCHIP_CORE_SPI is not set # CONFIG_SPI_LANTIQ_SSC is not set # CONFIG_SPI_OC_TINY is not set # CONFIG_SPI_PCI1XXXX is not set # CONFIG_SPI_PXA2XX is not set # CONFIG_SPI_SC18IS602 is not set # CONFIG_SPI_SIFIVE is not set # CONFIG_SPI_MXIC is not set # CONFIG_SPI_VIRTIO is not set # CONFIG_SPI_XCOMM is not set # CONFIG_SPI_XILINX is not set # # SPI Multiplexer support # # CONFIG_SPI_MUX is not set # # SPI Protocol Masters # # CONFIG_SPI_SPIDEV is not set # CONFIG_SPI_LOOPBACK_TEST is not set # CONFIG_SPI_TLE62X0 is not set # CONFIG_SPI_SLAVE is not set CONFIG_SPI_DYNAMIC=y # CONFIG_SPMI is not set # CONFIG_HSI is not set CONFIG_PPS=y # CONFIG_PPS_DEBUG is not set # # PPS clients support # # CONFIG_PPS_CLIENT_KTIMER is not set # CONFIG_PPS_CLIENT_LDISC is not set # CONFIG_PPS_CLIENT_PARPORT is not set # CONFIG_PPS_CLIENT_GPIO is not set # CONFIG_PPS_GENERATOR is not set # # PTP clock support # CONFIG_PTP_1588_CLOCK=y CONFIG_PTP_1588_CLOCK_OPTIONAL=y # # Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks. # CONFIG_PTP_1588_CLOCK_KVM=y CONFIG_PTP_1588_CLOCK_VMCLOCK=y # CONFIG_PTP_1588_CLOCK_IDT82P33 is not set # CONFIG_PTP_1588_CLOCK_IDTCM is not set # CONFIG_PTP_1588_CLOCK_FC3W is not set # CONFIG_PTP_1588_CLOCK_MOCK is not set # CONFIG_PTP_1588_CLOCK_VMW is not set # CONFIG_PTP_NETC_V4_TIMER is not set # end of PTP clock support # # DPLL device support # # CONFIG_ZL3073X_I2C is not set # CONFIG_ZL3073X_SPI is not set # end of DPLL device support # CONFIG_PINCTRL is not set CONFIG_GPIOLIB_LEGACY=y CONFIG_GPIOLIB=y CONFIG_GPIOLIB_FASTPATH_LIMIT=512 CONFIG_OF_GPIO=y CONFIG_GPIO_ACPI=y CONFIG_GPIOLIB_IRQCHIP=y # CONFIG_DEBUG_GPIO is not set # CONFIG_GPIO_SYSFS is not set # CONFIG_GPIO_CDEV is not set # # Memory mapped GPIO drivers # # CONFIG_GPIO_74XX_MMIO is not set # CONFIG_GPIO_ALTERA is not set # CONFIG_GPIO_AMDPT is not set # CONFIG_GPIO_BY_PINCTRL is not set # CONFIG_GPIO_CADENCE is not set # CONFIG_GPIO_DWAPB is not set # CONFIG_GPIO_EXAR is not set # CONFIG_GPIO_FTGPIO010 is not set # CONFIG_GPIO_GENERIC_PLATFORM is not set # CONFIG_GPIO_GRANITERAPIDS is not set # CONFIG_GPIO_GRGPIO is not set # CONFIG_GPIO_HLWD is not set # CONFIG_GPIO_LOGICVC is not set # CONFIG_GPIO_MB86S7X is not set # CONFIG_GPIO_POLARFIRE_SOC is not set # CONFIG_GPIO_SIFIVE is not set # CONFIG_GPIO_SYSCON is not set # CONFIG_GPIO_XILINX is not set # CONFIG_GPIO_AMD_FCH is not set # end of Memory mapped GPIO drivers # # Port-mapped I/O GPIO drivers # # CONFIG_GPIO_VX855 is not set # CONFIG_GPIO_F7188X is not set # CONFIG_GPIO_IT87 is not set # CONFIG_GPIO_NOVALAKE is not set # CONFIG_GPIO_SCH311X is not set # CONFIG_GPIO_WINBOND is not set # CONFIG_GPIO_WS16C48 is not set # end of Port-mapped I/O GPIO drivers # # I2C GPIO expanders # # CONFIG_GPIO_ADNP is not set # CONFIG_GPIO_FXL6408 is not set # CONFIG_GPIO_DS4520 is not set # CONFIG_GPIO_GW_PLD is not set # CONFIG_GPIO_MAX7300 is not set # CONFIG_GPIO_MAX732X is not set # CONFIG_GPIO_PCA953X is not set # CONFIG_GPIO_PCA9570 is not set # CONFIG_GPIO_PCF857X is not set # CONFIG_GPIO_TPIC2810 is not set # end of I2C GPIO expanders # # MFD GPIO expanders # # CONFIG_GPIO_CROS_EC is not set CONFIG_GPIO_DLN2=y CONFIG_GPIO_LJCA=y # CONFIG_GPIO_TWL4030 is not set # CONFIG_GPIO_WHISKEY_COVE is not set # end of MFD GPIO expanders # # PCI GPIO expanders # # CONFIG_GPIO_AMD8111 is not set # CONFIG_GPIO_BT8XX is not set # CONFIG_GPIO_ML_IOH is not set # CONFIG_GPIO_PCI_IDIO_16 is not set # CONFIG_GPIO_PCIE_IDIO_24 is not set # CONFIG_GPIO_RDC321X is not set # CONFIG_GPIO_SODAVILLE is not set # end of PCI GPIO expanders # # SPI GPIO expanders # # CONFIG_GPIO_74X164 is not set # CONFIG_GPIO_MAX3191X is not set # CONFIG_GPIO_MAX7301 is not set # CONFIG_GPIO_MC33880 is not set # CONFIG_GPIO_PISOSR is not set # CONFIG_GPIO_XRA1403 is not set # end of SPI GPIO expanders # # USB GPIO expanders # CONFIG_GPIO_VIPERBOARD=y # CONFIG_GPIO_MPSSE is not set # end of USB GPIO expanders # # Virtual GPIO drivers # # CONFIG_GPIO_AGGREGATOR is not set # CONFIG_GPIO_LATCH is not set # CONFIG_GPIO_LINE_MUX is not set # CONFIG_GPIO_MOCKUP is not set # CONFIG_GPIO_VIRTIO is not set # CONFIG_GPIO_SIM is not set # end of Virtual GPIO drivers # # GPIO Debugging utilities # # CONFIG_GPIO_SLOPPY_LOGIC_ANALYZER is not set # CONFIG_GPIO_VIRTUSER is not set # end of GPIO Debugging utilities CONFIG_W1=y # CONFIG_W1_CON is not set # # 1-wire Bus Masters # # CONFIG_W1_MASTER_AMD_AXI is not set # CONFIG_W1_MASTER_MATROX is not set CONFIG_W1_MASTER_DS2490=y # CONFIG_W1_MASTER_DS2482 is not set # CONFIG_W1_MASTER_GPIO is not set # CONFIG_W1_MASTER_SGI is not set # CONFIG_W1_MASTER_UART is not set # end of 1-wire Bus Masters # # 1-wire Slaves # # CONFIG_W1_SLAVE_THERM is not set # CONFIG_W1_SLAVE_SMEM is not set # CONFIG_W1_SLAVE_DS2405 is not set # CONFIG_W1_SLAVE_DS2408 is not set # CONFIG_W1_SLAVE_DS2413 is not set # CONFIG_W1_SLAVE_DS2406 is not set # CONFIG_W1_SLAVE_DS2423 is not set # CONFIG_W1_SLAVE_DS2805 is not set # CONFIG_W1_SLAVE_DS2430 is not set # CONFIG_W1_SLAVE_DS2431 is not set # CONFIG_W1_SLAVE_DS2433 is not set # CONFIG_W1_SLAVE_DS2438 is not set # CONFIG_W1_SLAVE_DS250X is not set # CONFIG_W1_SLAVE_DS2780 is not set # CONFIG_W1_SLAVE_DS2781 is not set # CONFIG_W1_SLAVE_DS28E04 is not set # CONFIG_W1_SLAVE_DS28E17 is not set # end of 1-wire Slaves # CONFIG_POWER_RESET is not set # CONFIG_POWER_SEQUENCING is not set CONFIG_POWER_SUPPLY=y # CONFIG_POWER_SUPPLY_DEBUG is not set CONFIG_POWER_SUPPLY_HWMON=y # CONFIG_GENERIC_ADC_BATTERY is not set # CONFIG_IP5XXX_POWER is not set # CONFIG_TEST_POWER is not set # CONFIG_CHARGER_ADP5061 is not set # CONFIG_BATTERY_CHAGALL is not set # CONFIG_BATTERY_CW2015 is not set # CONFIG_BATTERY_DS2760 is not set # CONFIG_BATTERY_DS2780 is not set # CONFIG_BATTERY_DS2781 is not set # CONFIG_BATTERY_DS2782 is not set # CONFIG_BATTERY_SAMSUNG_SDI is not set # CONFIG_BATTERY_S2MU005 is not set # CONFIG_BATTERY_SBS is not set # CONFIG_CHARGER_SBS is not set # CONFIG_MANAGER_SBS is not set # CONFIG_BATTERY_BQ27XXX is not set # CONFIG_BATTERY_MAX17040 is not set # CONFIG_BATTERY_MAX17042 is not set # CONFIG_BATTERY_MAX1720X is not set # CONFIG_BATTERY_MAX1721X is not set CONFIG_CHARGER_ISP1704=y # CONFIG_CHARGER_MAX8903 is not set # CONFIG_CHARGER_TWL4030 is not set # CONFIG_CHARGER_TWL6030 is not set # CONFIG_CHARGER_LP8727 is not set # CONFIG_CHARGER_GPIO is not set # CONFIG_CHARGER_MANAGER is not set # CONFIG_CHARGER_LT3651 is not set # CONFIG_CHARGER_LTC4162L is not set # CONFIG_CHARGER_DETECTOR_MAX14656 is not set # CONFIG_CHARGER_MAX77976 is not set # CONFIG_CHARGER_MAX8971 is not set # CONFIG_CHARGER_MT6360 is not set # CONFIG_CHARGER_MT6370 is not set # CONFIG_CHARGER_BQ2415X is not set CONFIG_CHARGER_BQ24190=y # CONFIG_CHARGER_BQ24257 is not set # CONFIG_CHARGER_BQ24735 is not set # CONFIG_CHARGER_BQ2515X is not set # CONFIG_CHARGER_BQ25890 is not set # CONFIG_CHARGER_BQ25980 is not set # CONFIG_CHARGER_BQ256XX is not set # CONFIG_CHARGER_SMB347 is not set # CONFIG_BATTERY_GAUGE_LTC2941 is not set # CONFIG_BATTERY_GOLDFISH is not set # CONFIG_BATTERY_RT5033 is not set # CONFIG_CHARGER_RT9455 is not set # CONFIG_CHARGER_RT9467 is not set # CONFIG_CHARGER_RT9471 is not set # CONFIG_CHARGER_RT9756 is not set # CONFIG_CHARGER_CROS_USBPD is not set # CONFIG_CHARGER_CROS_PCHG is not set # CONFIG_CHARGER_CROS_CONTROL is not set # CONFIG_FUEL_GAUGE_STC3117 is not set # CONFIG_CHARGER_UCS1002 is not set # CONFIG_CHARGER_BD99954 is not set # CONFIG_BATTERY_SURFACE is not set # CONFIG_CHARGER_SURFACE is not set # CONFIG_BATTERY_UG3105 is not set # CONFIG_FUEL_GAUGE_MM8013 is not set CONFIG_HWMON=y # CONFIG_HWMON_DEBUG_CHIP is not set # # Native drivers # # CONFIG_SENSORS_ABITUGURU is not set # CONFIG_SENSORS_ABITUGURU3 is not set # CONFIG_SENSORS_AD7314 is not set # CONFIG_SENSORS_AD7414 is not set # CONFIG_SENSORS_AD7418 is not set # CONFIG_SENSORS_ADM1025 is not set # CONFIG_SENSORS_ADM1026 is not set # CONFIG_SENSORS_ADM1029 is not set # CONFIG_SENSORS_ADM1031 is not set # CONFIG_SENSORS_ADM1177 is not set # CONFIG_SENSORS_ADM9240 is not set # CONFIG_SENSORS_ADT7310 is not set # CONFIG_SENSORS_ADT7410 is not set # CONFIG_SENSORS_ADT7411 is not set # CONFIG_SENSORS_ADT7462 is not set # CONFIG_SENSORS_ADT7470 is not set # CONFIG_SENSORS_ADT7475 is not set # CONFIG_SENSORS_AHT10 is not set CONFIG_SENSORS_AQUACOMPUTER_D5NEXT=y # CONFIG_SENSORS_AS370 is not set # CONFIG_SENSORS_ASC7621 is not set # CONFIG_SENSORS_ASUS_ROG_RYUJIN is not set # CONFIG_SENSORS_AXI_FAN_CONTROL is not set # CONFIG_SENSORS_K8TEMP is not set # CONFIG_SENSORS_K10TEMP is not set # CONFIG_SENSORS_FAM15H_POWER is not set # CONFIG_SENSORS_APPLESMC is not set # CONFIG_SENSORS_ASB100 is not set # CONFIG_SENSORS_ATXP1 is not set # CONFIG_SENSORS_CHIPCAP2 is not set CONFIG_SENSORS_CORSAIR_CPRO=y CONFIG_SENSORS_CORSAIR_PSU=y # CONFIG_SENSORS_CROS_EC is not set # CONFIG_SENSORS_DRIVETEMP is not set # CONFIG_SENSORS_DS620 is not set # CONFIG_SENSORS_DS1621 is not set # CONFIG_SENSORS_DELL_SMM is not set # CONFIG_SENSORS_I5K_AMB is not set # CONFIG_SENSORS_F71805F is not set # CONFIG_SENSORS_F71882FG is not set # CONFIG_SENSORS_F75375S is not set # CONFIG_SENSORS_FSCHMD is not set # CONFIG_SENSORS_FTSTEUTATES is not set CONFIG_SENSORS_GIGABYTE_WATERFORCE=y # CONFIG_SENSORS_GL518SM is not set # CONFIG_SENSORS_GL520SM is not set # CONFIG_SENSORS_GPD is not set # CONFIG_SENSORS_G760A is not set # CONFIG_SENSORS_G762 is not set # CONFIG_SENSORS_GPIO_FAN is not set # CONFIG_SENSORS_HIH6130 is not set # CONFIG_SENSORS_HS3001 is not set # CONFIG_SENSORS_HTU31 is not set # CONFIG_SENSORS_IIO_HWMON is not set # CONFIG_SENSORS_I5500 is not set # CONFIG_SENSORS_CORETEMP is not set # CONFIG_SENSORS_ISL28022 is not set # CONFIG_SENSORS_IT87 is not set # CONFIG_SENSORS_JC42 is not set CONFIG_SENSORS_POWERZ=y # CONFIG_SENSORS_POWR1220 is not set # CONFIG_SENSORS_LATTEPANDA_SIGMA_EC is not set # CONFIG_SENSORS_LENOVO_EC is not set # CONFIG_SENSORS_LINEAGE is not set # CONFIG_SENSORS_LTC2945 is not set # CONFIG_SENSORS_LTC2947_I2C is not set # CONFIG_SENSORS_LTC2947_SPI is not set # CONFIG_SENSORS_LTC2990 is not set # CONFIG_SENSORS_LTC2991 is not set # CONFIG_SENSORS_LTC2992 is not set # CONFIG_SENSORS_LTC4151 is not set # CONFIG_SENSORS_LTC4215 is not set # CONFIG_SENSORS_LTC4222 is not set # CONFIG_SENSORS_LTC4245 is not set # CONFIG_SENSORS_LTC4260 is not set # CONFIG_SENSORS_LTC4261 is not set # CONFIG_SENSORS_LTC4282 is not set # CONFIG_SENSORS_MAX1111 is not set # CONFIG_SENSORS_MAX127 is not set # CONFIG_SENSORS_MAX16065 is not set # CONFIG_SENSORS_MAX1619 is not set # CONFIG_SENSORS_MAX1668 is not set # CONFIG_SENSORS_MAX197 is not set # CONFIG_SENSORS_MAX31722 is not set # CONFIG_SENSORS_MAX31730 is not set # CONFIG_SENSORS_MAX31760 is not set # CONFIG_MAX31827 is not set # CONFIG_SENSORS_MAX6620 is not set # CONFIG_SENSORS_MAX6621 is not set # CONFIG_SENSORS_MAX6639 is not set # CONFIG_SENSORS_MAX6650 is not set # CONFIG_SENSORS_MAX6697 is not set # CONFIG_SENSORS_MAX31790 is not set # CONFIG_SENSORS_MC34VR500 is not set # CONFIG_SENSORS_MCP3021 is not set # CONFIG_SENSORS_MCP9982 is not set # CONFIG_SENSORS_TC654 is not set # CONFIG_SENSORS_TPS23861 is not set # CONFIG_SENSORS_MR75203 is not set # CONFIG_SENSORS_ADCXX is not set # CONFIG_SENSORS_LM63 is not set # CONFIG_SENSORS_LM70 is not set # CONFIG_SENSORS_LM73 is not set # CONFIG_SENSORS_LM75 is not set # CONFIG_SENSORS_LM77 is not set # CONFIG_SENSORS_LM78 is not set # CONFIG_SENSORS_LM80 is not set # CONFIG_SENSORS_LM83 is not set # CONFIG_SENSORS_LM85 is not set # CONFIG_SENSORS_LM87 is not set # CONFIG_SENSORS_LM90 is not set # CONFIG_SENSORS_LM92 is not set # CONFIG_SENSORS_LM93 is not set # CONFIG_SENSORS_LM95234 is not set # CONFIG_SENSORS_LM95241 is not set # CONFIG_SENSORS_LM95245 is not set # CONFIG_SENSORS_PC87360 is not set # CONFIG_SENSORS_PC87427 is not set # CONFIG_SENSORS_NTC_THERMISTOR is not set # CONFIG_SENSORS_NCT6683 is not set # CONFIG_SENSORS_NCT6775 is not set # CONFIG_SENSORS_NCT6775_I2C is not set # CONFIG_SENSORS_NCT7363 is not set # CONFIG_SENSORS_NCT7802 is not set # CONFIG_SENSORS_NCT7904 is not set # CONFIG_SENSORS_NPCM7XX is not set CONFIG_SENSORS_NZXT_KRAKEN2=y # CONFIG_SENSORS_NZXT_KRAKEN3 is not set CONFIG_SENSORS_NZXT_SMART2=y # CONFIG_SENSORS_OCC_P8_I2C is not set # CONFIG_SENSORS_PCF8591 is not set # CONFIG_PMBUS is not set # CONFIG_SENSORS_PT5161L is not set # CONFIG_SENSORS_SBTSI is not set # CONFIG_SENSORS_SHT15 is not set # CONFIG_SENSORS_SHT21 is not set # CONFIG_SENSORS_SHT3x is not set # CONFIG_SENSORS_SHT4x is not set # CONFIG_SENSORS_SHTC1 is not set # CONFIG_SENSORS_SIS5595 is not set # CONFIG_SENSORS_DME1737 is not set # CONFIG_SENSORS_EMC1403 is not set # CONFIG_SENSORS_EMC2103 is not set # CONFIG_SENSORS_EMC2305 is not set # CONFIG_SENSORS_EMC6W201 is not set # CONFIG_SENSORS_SMSC47M1 is not set # CONFIG_SENSORS_SMSC47M192 is not set # CONFIG_SENSORS_SMSC47B397 is not set # CONFIG_SENSORS_SCH5627 is not set # CONFIG_SENSORS_SCH5636 is not set # CONFIG_SENSORS_STTS751 is not set # CONFIG_SENSORS_SURFACE_FAN is not set # CONFIG_SENSORS_SURFACE_TEMP is not set # CONFIG_SENSORS_ADC128D818 is not set # CONFIG_SENSORS_ADS7828 is not set # CONFIG_SENSORS_ADS7871 is not set # CONFIG_SENSORS_AMC6821 is not set # CONFIG_SENSORS_INA209 is not set # CONFIG_SENSORS_INA2XX is not set # CONFIG_SENSORS_INA238 is not set # CONFIG_SENSORS_INA3221 is not set # CONFIG_SENSORS_SPD5118 is not set # CONFIG_SENSORS_TC74 is not set # CONFIG_SENSORS_THMC50 is not set # CONFIG_SENSORS_TMP102 is not set # CONFIG_SENSORS_TMP103 is not set # CONFIG_SENSORS_TMP108 is not set # CONFIG_SENSORS_TMP401 is not set # CONFIG_SENSORS_TMP421 is not set # CONFIG_SENSORS_TMP464 is not set # CONFIG_SENSORS_TMP513 is not set # CONFIG_SENSORS_TSC1641 is not set # CONFIG_SENSORS_VIA_CPUTEMP is not set # CONFIG_SENSORS_VIA686A is not set # CONFIG_SENSORS_VT1211 is not set # CONFIG_SENSORS_VT8231 is not set # CONFIG_SENSORS_W83773G is not set # CONFIG_SENSORS_W83781D is not set # CONFIG_SENSORS_W83791D is not set # CONFIG_SENSORS_W83792D is not set # CONFIG_SENSORS_W83793 is not set # CONFIG_SENSORS_W83795 is not set # CONFIG_SENSORS_W83L785TS is not set # CONFIG_SENSORS_W83L786NG is not set # CONFIG_SENSORS_W83627HF is not set # CONFIG_SENSORS_W83627EHF is not set # CONFIG_SENSORS_XGENE is not set # CONFIG_SENSORS_YOGAFAN is not set # # ACPI drivers # # CONFIG_SENSORS_ACPI_POWER is not set # CONFIG_SENSORS_ATK0110 is not set # CONFIG_SENSORS_ASUS_WMI is not set # CONFIG_SENSORS_ASUS_EC is not set # CONFIG_SENSORS_HP_WMI is not set CONFIG_THERMAL=y CONFIG_THERMAL_NETLINK=y # CONFIG_THERMAL_STATISTICS is not set # CONFIG_THERMAL_DEBUGFS is not set # CONFIG_THERMAL_CORE_TESTING is not set CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS=0 CONFIG_THERMAL_HWMON=y # CONFIG_THERMAL_OF is not set CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE=y # CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE is not set # CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE is not set # CONFIG_THERMAL_GOV_FAIR_SHARE is not set CONFIG_THERMAL_GOV_STEP_WISE=y # CONFIG_THERMAL_GOV_BANG_BANG is not set # CONFIG_THERMAL_GOV_USER_SPACE is not set # CONFIG_PCIE_THERMAL is not set # CONFIG_THERMAL_EMULATION is not set # CONFIG_THERMAL_MMIO is not set # # Intel thermal drivers # # CONFIG_INTEL_POWERCLAMP is not set CONFIG_X86_THERMAL_VECTOR=y CONFIG_INTEL_TCC=y CONFIG_X86_PKG_TEMP_THERMAL=y # CONFIG_INTEL_SOC_DTS_THERMAL is not set # # ACPI INT340X thermal drivers # # CONFIG_INT340X_THERMAL is not set # end of ACPI INT340X thermal drivers # CONFIG_INTEL_BXT_PMIC_THERMAL is not set # CONFIG_INTEL_PCH_THERMAL is not set # CONFIG_INTEL_TCC_COOLING is not set # CONFIG_INTEL_HFI_THERMAL is not set # end of Intel thermal drivers # CONFIG_GENERIC_ADC_THERMAL is not set CONFIG_WATCHDOG=y # CONFIG_WATCHDOG_CORE is not set # CONFIG_WATCHDOG_NOWAYOUT is not set CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED=y CONFIG_WATCHDOG_OPEN_TIMEOUT=0 # CONFIG_WATCHDOG_SYSFS is not set # CONFIG_WATCHDOG_HRTIMER_PRETIMEOUT is not set # # Watchdog Pretimeout Governors # # # Watchdog Device Drivers # # CONFIG_SOFT_WATCHDOG is not set # CONFIG_CROS_EC_WATCHDOG is not set # CONFIG_GPIO_WATCHDOG is not set # CONFIG_LENOVO_SE10_WDT is not set # CONFIG_LENOVO_SE30_WDT is not set # CONFIG_WDAT_WDT is not set # CONFIG_XILINX_WATCHDOG is not set # CONFIG_ZIIRAVE_WATCHDOG is not set # CONFIG_CADENCE_WATCHDOG is not set # CONFIG_DW_WATCHDOG is not set # CONFIG_TWL4030_WATCHDOG is not set # CONFIG_MAX63XX_WATCHDOG is not set # CONFIG_RETU_WATCHDOG is not set # CONFIG_ACQUIRE_WDT is not set # CONFIG_ADVANTECH_WDT is not set # CONFIG_ADVANTECH_EC_WDT is not set # CONFIG_ALIM1535_WDT is not set # CONFIG_ALIM7101_WDT is not set # CONFIG_EBC_C384_WDT is not set # CONFIG_EXAR_WDT is not set # CONFIG_F71808E_WDT is not set # CONFIG_SP5100_TCO is not set # CONFIG_SBC_FITPC2_WATCHDOG is not set # CONFIG_EUROTECH_WDT is not set # CONFIG_IB700_WDT is not set # CONFIG_IBMASR is not set # CONFIG_WAFER_WDT is not set # CONFIG_I6300ESB_WDT is not set # CONFIG_IE6XX_WDT is not set # CONFIG_INTEL_OC_WATCHDOG is not set # CONFIG_ITCO_WDT is not set # CONFIG_IT8712F_WDT is not set # CONFIG_IT87_WDT is not set # CONFIG_HP_WATCHDOG is not set # CONFIG_SC1200_WDT is not set # CONFIG_PC87413_WDT is not set # CONFIG_NV_TCO is not set # CONFIG_60XX_WDT is not set # CONFIG_SMSC_SCH311X_WDT is not set # CONFIG_SMSC37B787_WDT is not set # CONFIG_TQMX86_WDT is not set # CONFIG_VIA_WDT is not set # CONFIG_W83627HF_WDT is not set # CONFIG_W83877F_WDT is not set # CONFIG_W83977F_WDT is not set # CONFIG_MACHZ_WDT is not set # CONFIG_SBC_EPX_C3_WATCHDOG is not set # CONFIG_INTEL_MEI_WDT is not set # CONFIG_NI903X_WDT is not set # CONFIG_NIC7018_WDT is not set # CONFIG_MEN_A21_WDT is not set # # PCI-based Watchdog Cards # # CONFIG_PCIPCWATCHDOG is not set # CONFIG_WDTPCI is not set # # USB-based Watchdog Cards # CONFIG_USBPCWATCHDOG=y CONFIG_SSB_POSSIBLE=y CONFIG_SSB=y CONFIG_SSB_PCIHOST_POSSIBLE=y # CONFIG_SSB_PCIHOST is not set CONFIG_SSB_PCMCIAHOST_POSSIBLE=y # CONFIG_SSB_PCMCIAHOST is not set CONFIG_SSB_SDIOHOST_POSSIBLE=y # CONFIG_SSB_SDIOHOST is not set # CONFIG_SSB_DRIVER_GPIO is not set CONFIG_BCMA_POSSIBLE=y CONFIG_BCMA=y CONFIG_BCMA_HOST_PCI_POSSIBLE=y # CONFIG_BCMA_HOST_PCI is not set # CONFIG_BCMA_HOST_SOC is not set # CONFIG_BCMA_DRIVER_PCI is not set # CONFIG_BCMA_DRIVER_GMAC_CMN is not set # CONFIG_BCMA_DRIVER_GPIO is not set # CONFIG_BCMA_DEBUG is not set # # Multifunction device drivers # CONFIG_MFD_CORE=y # CONFIG_MFD_ADP5585 is not set # CONFIG_MFD_ACT8945A is not set # CONFIG_MFD_AS3711 is not set # CONFIG_MFD_SMPRO is not set # CONFIG_MFD_AS3722 is not set # CONFIG_PMIC_ADP5520 is not set # CONFIG_MFD_AAT2870_CORE is not set # CONFIG_MFD_ATMEL_FLEXCOM is not set # CONFIG_MFD_ATMEL_HLCDC is not set # CONFIG_MFD_BCM590XX is not set # CONFIG_MFD_BD9571MWV is not set # CONFIG_MFD_AXP20X_I2C is not set # CONFIG_MFD_CGBC is not set CONFIG_MFD_CROS_EC_DEV=y # CONFIG_MFD_CS40L50_I2C is not set # CONFIG_MFD_CS40L50_SPI is not set # CONFIG_MFD_CS42L43_I2C is not set # CONFIG_MFD_CS42L43_SDW is not set # CONFIG_MFD_LOCHNAGAR is not set # CONFIG_MFD_MADERA is not set # CONFIG_PMIC_DA903X is not set # CONFIG_MFD_DA9052_SPI is not set # CONFIG_MFD_DA9052_I2C is not set # CONFIG_MFD_DA9055 is not set # CONFIG_MFD_DA9062 is not set # CONFIG_MFD_DA9063 is not set # CONFIG_MFD_DA9150 is not set CONFIG_MFD_DLN2=y # CONFIG_MFD_GATEWORKS_GSC is not set # CONFIG_MFD_MC13XXX_SPI is not set # CONFIG_MFD_MC13XXX_I2C is not set # CONFIG_MFD_MP2629 is not set # CONFIG_MFD_PF1550 is not set # CONFIG_MFD_HI6421_PMIC is not set # CONFIG_MFD_INTEL_QUARK_I2C_GPIO is not set # CONFIG_LPC_ICH is not set # CONFIG_LPC_SCH is not set # CONFIG_INTEL_SOC_PMIC is not set CONFIG_INTEL_SOC_PMIC_BXTWC=y CONFIG_INTEL_SOC_PMIC_CHTWC=y # CONFIG_INTEL_SOC_PMIC_CHTDC_TI is not set # CONFIG_MFD_INTEL_LPSS_ACPI is not set # CONFIG_MFD_INTEL_LPSS_PCI is not set CONFIG_MFD_INTEL_PMC_BXT=y # CONFIG_MFD_IQS62X is not set # CONFIG_MFD_JANZ_CMODIO is not set # CONFIG_MFD_KEMPLD is not set # CONFIG_MFD_88PM800 is not set # CONFIG_MFD_88PM805 is not set # CONFIG_MFD_88PM860X is not set # CONFIG_MFD_88PM886_PMIC is not set # CONFIG_MFD_MAX5970 is not set # CONFIG_MFD_MAX14577 is not set # CONFIG_MFD_MAX77541 is not set # CONFIG_MFD_MAX77620 is not set # CONFIG_MFD_MAX77650 is not set # CONFIG_MFD_MAX77686 is not set # CONFIG_MFD_MAX77693 is not set # CONFIG_MFD_MAX77705 is not set # CONFIG_MFD_MAX77714 is not set # CONFIG_MFD_MAX77759 is not set # CONFIG_MFD_MAX77843 is not set # CONFIG_MFD_MAX8907 is not set # CONFIG_MFD_MAX8925 is not set # CONFIG_MFD_MAX8997 is not set # CONFIG_MFD_MAX8998 is not set CONFIG_MFD_MT6360=y CONFIG_MFD_MT6370=y # CONFIG_MFD_MT6397 is not set # CONFIG_MFD_MENF21BMC is not set # CONFIG_MFD_NCT6694 is not set # CONFIG_MFD_OCELOT is not set # CONFIG_EZX_PCAP is not set # CONFIG_MFD_CPCAP is not set CONFIG_MFD_VIPERBOARD=y # CONFIG_MFD_NTXEC is not set CONFIG_MFD_RETU=y # CONFIG_MFD_SY7636A is not set # CONFIG_MFD_RDC321X is not set # CONFIG_MFD_RT4831 is not set # CONFIG_MFD_RT5033 is not set # CONFIG_MFD_RT5120 is not set # CONFIG_MFD_RC5T583 is not set # CONFIG_MFD_RK8XX_I2C is not set # CONFIG_MFD_RK8XX_SPI is not set # CONFIG_MFD_RN5T618 is not set # CONFIG_MFD_SEC_I2C is not set # CONFIG_MFD_SI476X_CORE is not set # CONFIG_MFD_SM501 is not set # CONFIG_MFD_SKY81452 is not set # CONFIG_MFD_STMPE is not set CONFIG_MFD_SYSCON=y # CONFIG_MFD_LP3943 is not set # CONFIG_MFD_LP8788 is not set # CONFIG_MFD_TI_LMU is not set # CONFIG_MFD_BQ257XX is not set # CONFIG_MFD_PALMAS is not set # CONFIG_TPS6105X is not set # CONFIG_TPS65010 is not set # CONFIG_TPS6507X is not set # CONFIG_MFD_TPS65086 is not set # CONFIG_MFD_TPS65090 is not set # CONFIG_MFD_TPS65217 is not set # CONFIG_MFD_TI_LP873X is not set # CONFIG_MFD_TI_LP87565 is not set # CONFIG_MFD_TPS65218 is not set # CONFIG_MFD_TPS65219 is not set # CONFIG_MFD_TPS6586X is not set # CONFIG_MFD_TPS65910 is not set # CONFIG_MFD_TPS65912_I2C is not set # CONFIG_MFD_TPS65912_SPI is not set # CONFIG_MFD_TPS6594_I2C is not set # CONFIG_MFD_TPS6594_SPI is not set CONFIG_TWL4030_CORE=y # CONFIG_MFD_TWL4030_AUDIO is not set # CONFIG_TWL6040_CORE is not set # CONFIG_MFD_LM3533 is not set # CONFIG_MFD_TC3589X is not set # CONFIG_MFD_TQMX86 is not set # CONFIG_MFD_VX855 is not set # CONFIG_MFD_ARIZONA_I2C is not set # CONFIG_MFD_ARIZONA_SPI is not set # CONFIG_MFD_WM8400 is not set # CONFIG_MFD_WM831X_I2C is not set # CONFIG_MFD_WM831X_SPI is not set # CONFIG_MFD_WM8350_I2C is not set # CONFIG_MFD_WM8994 is not set # CONFIG_MFD_ROHM_BD718XX is not set # CONFIG_MFD_ROHM_BD71828 is not set # CONFIG_MFD_ROHM_BD957XMUF is not set # CONFIG_MFD_ROHM_BD96801 is not set # CONFIG_MFD_STPMIC1 is not set # CONFIG_MFD_STMFX is not set # CONFIG_MFD_ATC260X_I2C is not set # CONFIG_MFD_QCOM_PM8008 is not set # CONFIG_RAVE_SP_CORE is not set # CONFIG_MFD_INTEL_M10_BMC_SPI is not set # CONFIG_MFD_QNAP_MCU is not set # CONFIG_MFD_RSMU_I2C is not set # CONFIG_MFD_RSMU_SPI is not set # CONFIG_MFD_UPBOARD_FPGA is not set # CONFIG_MFD_MAX7360 is not set # end of Multifunction device drivers CONFIG_REGULATOR=y # CONFIG_REGULATOR_DEBUG is not set CONFIG_REGULATOR_FIXED_VOLTAGE=y # CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set # CONFIG_REGULATOR_USERSPACE_CONSUMER is not set # CONFIG_REGULATOR_NETLINK_EVENTS is not set # CONFIG_REGULATOR_88PG86X is not set # CONFIG_REGULATOR_ACT8865 is not set # CONFIG_REGULATOR_AD5398 is not set # CONFIG_REGULATOR_ADP5055 is not set # CONFIG_REGULATOR_AW37503 is not set # CONFIG_REGULATOR_CROS_EC is not set # CONFIG_REGULATOR_DA9121 is not set # CONFIG_REGULATOR_DA9210 is not set # CONFIG_REGULATOR_DA9211 is not set # CONFIG_REGULATOR_FAN53555 is not set # CONFIG_REGULATOR_FAN53880 is not set # CONFIG_REGULATOR_GPIO is not set # CONFIG_REGULATOR_ISL9305 is not set # CONFIG_REGULATOR_ISL6271A is not set # CONFIG_REGULATOR_FP9931 is not set # CONFIG_REGULATOR_LP3971 is not set # CONFIG_REGULATOR_LP3972 is not set # CONFIG_REGULATOR_LP872X is not set # CONFIG_REGULATOR_LP8755 is not set # CONFIG_REGULATOR_LTC3589 is not set # CONFIG_REGULATOR_LTC3676 is not set # CONFIG_REGULATOR_MAX1586 is not set # CONFIG_REGULATOR_MAX77503 is not set # CONFIG_REGULATOR_MAX77675 is not set # CONFIG_REGULATOR_MAX77857 is not set # CONFIG_REGULATOR_MAX8649 is not set # CONFIG_REGULATOR_MAX8660 is not set # CONFIG_REGULATOR_MAX8893 is not set # CONFIG_REGULATOR_MAX8952 is not set # CONFIG_REGULATOR_MAX20086 is not set # CONFIG_REGULATOR_MAX20411 is not set # CONFIG_REGULATOR_MAX77826 is not set # CONFIG_REGULATOR_MAX77838 is not set # CONFIG_REGULATOR_MCP16502 is not set # CONFIG_REGULATOR_MP5416 is not set # CONFIG_REGULATOR_MP8859 is not set # CONFIG_REGULATOR_MP886X is not set # CONFIG_REGULATOR_MPQ7920 is not set # CONFIG_REGULATOR_MT6311 is not set # CONFIG_REGULATOR_MT6360 is not set # CONFIG_REGULATOR_MT6370 is not set # CONFIG_REGULATOR_PCA9450 is not set # CONFIG_REGULATOR_PF9453 is not set # CONFIG_REGULATOR_PF0900 is not set # CONFIG_REGULATOR_PF530X is not set # CONFIG_REGULATOR_PF8X00 is not set # CONFIG_REGULATOR_PFUZE100 is not set # CONFIG_REGULATOR_PV88060 is not set # CONFIG_REGULATOR_PV88080 is not set # CONFIG_REGULATOR_PV88090 is not set # CONFIG_REGULATOR_RAA215300 is not set # CONFIG_REGULATOR_RT4801 is not set # CONFIG_REGULATOR_RT4803 is not set # CONFIG_REGULATOR_RT5133 is not set # CONFIG_REGULATOR_RT5190A is not set # CONFIG_REGULATOR_RT5739 is not set # CONFIG_REGULATOR_RT5759 is not set # CONFIG_REGULATOR_RT6160 is not set # CONFIG_REGULATOR_RT6190 is not set # CONFIG_REGULATOR_RT6245 is not set # CONFIG_REGULATOR_RT8092 is not set # CONFIG_REGULATOR_RTQ2134 is not set # CONFIG_REGULATOR_RTMV20 is not set # CONFIG_REGULATOR_RTQ6752 is not set # CONFIG_REGULATOR_RTQ2208 is not set # CONFIG_REGULATOR_SLG51000 is not set # CONFIG_REGULATOR_SY8106A is not set # CONFIG_REGULATOR_SY8824X is not set # CONFIG_REGULATOR_SY8827N is not set # CONFIG_REGULATOR_TPS51632 is not set # CONFIG_REGULATOR_TPS62360 is not set # CONFIG_REGULATOR_TPS6286X is not set # CONFIG_REGULATOR_TPS6287X is not set # CONFIG_REGULATOR_TPS65023 is not set # CONFIG_REGULATOR_TPS6507X is not set # CONFIG_REGULATOR_TPS65132 is not set # CONFIG_REGULATOR_TPS65185 is not set # CONFIG_REGULATOR_TPS6524X is not set CONFIG_REGULATOR_TWL4030=y # CONFIG_REGULATOR_VCTRL is not set CONFIG_RC_CORE=y # CONFIG_LIRC is not set # CONFIG_RC_MAP is not set # CONFIG_RC_DECODERS is not set CONFIG_RC_DEVICES=y # CONFIG_IR_ENE is not set # CONFIG_IR_FINTEK is not set # CONFIG_IR_GPIO_CIR is not set # CONFIG_IR_HIX5HD2 is not set CONFIG_IR_IGORPLUGUSB=y CONFIG_IR_IGUANA=y CONFIG_IR_IMON=y CONFIG_IR_IMON_RAW=y # CONFIG_IR_ITE_CIR is not set CONFIG_IR_MCEUSB=y # CONFIG_IR_NUVOTON is not set CONFIG_IR_REDRAT3=y # CONFIG_IR_SERIAL is not set CONFIG_IR_STREAMZAP=y CONFIG_IR_TOY=y CONFIG_IR_TTUSBIR=y # CONFIG_IR_WINBOND_CIR is not set CONFIG_RC_ATI_REMOTE=y # CONFIG_RC_LOOPBACK is not set CONFIG_RC_XBOX_DVD=y CONFIG_CEC_CORE=y # # CEC support # # CONFIG_MEDIA_CEC_RC is not set CONFIG_MEDIA_CEC_SUPPORT=y # CONFIG_CEC_CH7322 is not set # CONFIG_CEC_NXP_TDA9950 is not set # CONFIG_CEC_CROS_EC is not set # CONFIG_CEC_GPIO is not set # CONFIG_CEC_SECO is not set # CONFIG_USB_EXTRON_DA_HD_4K_PLUS_CEC is not set CONFIG_USB_PULSE8_CEC=y CONFIG_USB_RAINSHADOW_CEC=y # end of CEC support CONFIG_MEDIA_SUPPORT=y # CONFIG_MEDIA_SUPPORT_FILTER is not set # CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set # # Media device types # CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_MEDIA_ANALOG_TV_SUPPORT=y CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y CONFIG_MEDIA_RADIO_SUPPORT=y CONFIG_MEDIA_SDR_SUPPORT=y CONFIG_MEDIA_PLATFORM_SUPPORT=y CONFIG_MEDIA_TEST_SUPPORT=y # end of Media device types # # Media core support # CONFIG_VIDEO_DEV=y CONFIG_MEDIA_CONTROLLER=y CONFIG_DVB_CORE=y # end of Media core support # # Video4Linux options # CONFIG_VIDEO_V4L2_I2C=y # CONFIG_VIDEO_ADV_DEBUG is not set # CONFIG_VIDEO_FIXED_MINOR_RANGES is not set CONFIG_VIDEO_TUNER=y # end of Video4Linux options # # Media controller options # CONFIG_MEDIA_CONTROLLER_DVB=y # end of Media controller options # # Digital TV options # # CONFIG_DVB_MMAP is not set # CONFIG_DVB_NET is not set CONFIG_DVB_MAX_ADAPTERS=16 # CONFIG_DVB_DYNAMIC_MINORS is not set # CONFIG_DVB_DEMUX_SECTION_LOSS_LOG is not set # CONFIG_DVB_ULE_DEBUG is not set # end of Digital TV options # # Media drivers # # # Media drivers # CONFIG_MEDIA_USB_SUPPORT=y # # Webcam devices # CONFIG_USB_GSPCA=y CONFIG_USB_GSPCA_BENQ=y CONFIG_USB_GSPCA_CONEX=y CONFIG_USB_GSPCA_CPIA1=y CONFIG_USB_GSPCA_DTCS033=y CONFIG_USB_GSPCA_ETOMS=y CONFIG_USB_GSPCA_FINEPIX=y CONFIG_USB_GSPCA_JEILINJ=y CONFIG_USB_GSPCA_JL2005BCD=y CONFIG_USB_GSPCA_KINECT=y CONFIG_USB_GSPCA_KONICA=y CONFIG_USB_GSPCA_MARS=y CONFIG_USB_GSPCA_MR97310A=y CONFIG_USB_GSPCA_NW80X=y CONFIG_USB_GSPCA_OV519=y CONFIG_USB_GSPCA_OV534=y CONFIG_USB_GSPCA_OV534_9=y CONFIG_USB_GSPCA_PAC207=y CONFIG_USB_GSPCA_PAC7302=y CONFIG_USB_GSPCA_PAC7311=y CONFIG_USB_GSPCA_SE401=y CONFIG_USB_GSPCA_SN9C2028=y CONFIG_USB_GSPCA_SN9C20X=y CONFIG_USB_GSPCA_SONIXB=y CONFIG_USB_GSPCA_SONIXJ=y CONFIG_USB_GSPCA_SPCA1528=y CONFIG_USB_GSPCA_SPCA500=y CONFIG_USB_GSPCA_SPCA501=y CONFIG_USB_GSPCA_SPCA505=y CONFIG_USB_GSPCA_SPCA506=y CONFIG_USB_GSPCA_SPCA508=y CONFIG_USB_GSPCA_SPCA561=y CONFIG_USB_GSPCA_SQ905=y CONFIG_USB_GSPCA_SQ905C=y CONFIG_USB_GSPCA_SQ930X=y CONFIG_USB_GSPCA_STK014=y CONFIG_USB_GSPCA_STK1135=y CONFIG_USB_GSPCA_STV0680=y CONFIG_USB_GSPCA_SUNPLUS=y CONFIG_USB_GSPCA_T613=y CONFIG_USB_GSPCA_TOPRO=y CONFIG_USB_GSPCA_TOUPTEK=y CONFIG_USB_GSPCA_TV8532=y CONFIG_USB_GSPCA_VC032X=y CONFIG_USB_GSPCA_VICAM=y CONFIG_USB_GSPCA_XIRLINK_CIT=y CONFIG_USB_GSPCA_ZC3XX=y CONFIG_USB_GL860=y CONFIG_USB_M5602=y CONFIG_USB_STV06XX=y CONFIG_USB_PWC=y # CONFIG_USB_PWC_DEBUG is not set CONFIG_USB_PWC_INPUT_EVDEV=y CONFIG_USB_S2255=y CONFIG_VIDEO_USBTV=y CONFIG_USB_VIDEO_CLASS=y CONFIG_USB_VIDEO_CLASS_INPUT_EVDEV=y # # Analog TV USB devices # CONFIG_VIDEO_GO7007=y CONFIG_VIDEO_GO7007_USB=y CONFIG_VIDEO_GO7007_LOADER=y CONFIG_VIDEO_GO7007_USB_S2250_BOARD=y CONFIG_VIDEO_HDPVR=y CONFIG_VIDEO_PVRUSB2=y CONFIG_VIDEO_PVRUSB2_SYSFS=y CONFIG_VIDEO_PVRUSB2_DVB=y # CONFIG_VIDEO_PVRUSB2_DEBUGIFC is not set CONFIG_VIDEO_STK1160=y # # Analog/digital TV USB devices # CONFIG_VIDEO_AU0828=y CONFIG_VIDEO_AU0828_V4L2=y CONFIG_VIDEO_AU0828_RC=y CONFIG_VIDEO_CX231XX=y CONFIG_VIDEO_CX231XX_RC=y CONFIG_VIDEO_CX231XX_ALSA=y CONFIG_VIDEO_CX231XX_DVB=y # # Digital TV USB devices # CONFIG_DVB_AS102=y CONFIG_DVB_B2C2_FLEXCOP_USB=y # CONFIG_DVB_B2C2_FLEXCOP_USB_DEBUG is not set CONFIG_DVB_USB_V2=y CONFIG_DVB_USB_AF9015=y CONFIG_DVB_USB_AF9035=y CONFIG_DVB_USB_ANYSEE=y CONFIG_DVB_USB_AU6610=y CONFIG_DVB_USB_AZ6007=y CONFIG_DVB_USB_CE6230=y CONFIG_DVB_USB_DVBSKY=y CONFIG_DVB_USB_EC168=y CONFIG_DVB_USB_GL861=y CONFIG_DVB_USB_LME2510=y CONFIG_DVB_USB_MXL111SF=y CONFIG_DVB_USB_RTL28XXU=y CONFIG_DVB_USB_ZD1301=y CONFIG_DVB_USB=y # CONFIG_DVB_USB_DEBUG is not set CONFIG_DVB_USB_A800=y CONFIG_DVB_USB_AF9005=y CONFIG_DVB_USB_AF9005_REMOTE=y CONFIG_DVB_USB_AZ6027=y CONFIG_DVB_USB_CINERGY_T2=y CONFIG_DVB_USB_CXUSB=y CONFIG_DVB_USB_CXUSB_ANALOG=y CONFIG_DVB_USB_DIB0700=y CONFIG_DVB_USB_DIB3000MC=y CONFIG_DVB_USB_DIBUSB_MB=y # CONFIG_DVB_USB_DIBUSB_MB_FAULTY is not set CONFIG_DVB_USB_DIBUSB_MC=y CONFIG_DVB_USB_DIGITV=y CONFIG_DVB_USB_DTT200U=y CONFIG_DVB_USB_DTV5100=y CONFIG_DVB_USB_DW2102=y CONFIG_DVB_USB_GP8PSK=y CONFIG_DVB_USB_M920X=y CONFIG_DVB_USB_NOVA_T_USB2=y CONFIG_DVB_USB_OPERA1=y CONFIG_DVB_USB_PCTV452E=y CONFIG_DVB_USB_TECHNISAT_USB2=y CONFIG_DVB_USB_TTUSB2=y CONFIG_DVB_USB_UMT_010=y CONFIG_DVB_USB_VP702X=y CONFIG_DVB_USB_VP7045=y CONFIG_SMS_USB_DRV=y CONFIG_DVB_TTUSB_BUDGET=y CONFIG_DVB_TTUSB_DEC=y # # Webcam, TV (analog/digital) USB devices # CONFIG_VIDEO_EM28XX=y CONFIG_VIDEO_EM28XX_V4L2=y CONFIG_VIDEO_EM28XX_ALSA=y CONFIG_VIDEO_EM28XX_DVB=y CONFIG_VIDEO_EM28XX_RC=y # # Software defined radio USB devices # CONFIG_USB_AIRSPY=y CONFIG_USB_HACKRF=y CONFIG_USB_MSI2500=y CONFIG_MEDIA_PCI_SUPPORT=y # # Media capture support # # CONFIG_VIDEO_SOLO6X10 is not set # CONFIG_VIDEO_TW5864 is not set # CONFIG_VIDEO_TW68 is not set # CONFIG_VIDEO_TW686X is not set # CONFIG_VIDEO_ZORAN is not set # # Media capture/analog TV support # # CONFIG_VIDEO_DT3155 is not set # CONFIG_VIDEO_IVTV is not set # CONFIG_VIDEO_HEXIUM_GEMINI is not set # CONFIG_VIDEO_HEXIUM_ORION is not set # CONFIG_VIDEO_MXB is not set # # Media capture/analog/hybrid TV support # # CONFIG_VIDEO_BT848 is not set # CONFIG_VIDEO_CX18 is not set # CONFIG_VIDEO_CX23885 is not set # CONFIG_VIDEO_CX25821 is not set # CONFIG_VIDEO_CX88 is not set CONFIG_VIDEO_SAA7134=y # CONFIG_VIDEO_SAA7134_ALSA is not set # CONFIG_VIDEO_SAA7134_RC is not set # CONFIG_VIDEO_SAA7134_DVB is not set CONFIG_VIDEO_SAA7134_GO7007=y # CONFIG_VIDEO_SAA7164 is not set # # Media digital TV PCI Adapters # CONFIG_DVB_B2C2_FLEXCOP_PCI=y # CONFIG_DVB_B2C2_FLEXCOP_PCI_DEBUG is not set # CONFIG_DVB_DDBRIDGE is not set # CONFIG_DVB_DM1105 is not set # CONFIG_MANTIS_CORE is not set # CONFIG_DVB_NETUP_UNIDVB is not set # CONFIG_DVB_NGENE is not set # CONFIG_DVB_PLUTO2 is not set # CONFIG_DVB_PT1 is not set # CONFIG_DVB_PT3 is not set # CONFIG_DVB_SMIPCIE is not set # CONFIG_DVB_BUDGET_CORE is not set # CONFIG_VIDEO_IPU3_CIO2 is not set # CONFIG_VIDEO_INTEL_IPU6 is not set # CONFIG_INTEL_VSC is not set # CONFIG_IPU_BRIDGE is not set CONFIG_RADIO_ADAPTERS=y # CONFIG_RADIO_MAXIRADIO is not set # CONFIG_RADIO_SAA7706H is not set CONFIG_RADIO_SHARK=y CONFIG_RADIO_SHARK2=y CONFIG_RADIO_SI4713=y CONFIG_RADIO_TEA575X=y # CONFIG_RADIO_TEA5764 is not set # CONFIG_RADIO_TEF6862 is not set CONFIG_USB_DSBR=y CONFIG_USB_KEENE=y CONFIG_USB_MA901=y CONFIG_USB_MR800=y CONFIG_USB_RAREMONO=y CONFIG_RADIO_SI470X=y CONFIG_USB_SI470X=y # CONFIG_I2C_SI470X is not set CONFIG_USB_SI4713=y # CONFIG_PLATFORM_SI4713 is not set CONFIG_I2C_SI4713=y # CONFIG_MEDIA_PLATFORM_DRIVERS is not set # # MMC/SDIO DVB adapters # CONFIG_SMS_SDIO_DRV=y # CONFIG_V4L_TEST_DRIVERS is not set # CONFIG_DVB_TEST_DRIVERS is not set CONFIG_MEDIA_COMMON_OPTIONS=y # # common driver options # CONFIG_CYPRESS_FIRMWARE=y CONFIG_TTPCI_EEPROM=y CONFIG_UVC_COMMON=y CONFIG_VIDEO_CX2341X=y CONFIG_VIDEO_TVEEPROM=y CONFIG_DVB_B2C2_FLEXCOP=y CONFIG_SMS_SIANO_MDTV=y CONFIG_SMS_SIANO_RC=y CONFIG_SMS_SIANO_DEBUGFS=y CONFIG_VIDEOBUF2_CORE=y CONFIG_VIDEOBUF2_V4L2=y CONFIG_VIDEOBUF2_MEMOPS=y CONFIG_VIDEOBUF2_VMALLOC=y CONFIG_VIDEOBUF2_DMA_SG=y # end of Media drivers # # Media ancillary drivers # CONFIG_MEDIA_ATTACH=y # CONFIG_VIDEO_IR_I2C is not set # CONFIG_VIDEO_CAMERA_SENSOR is not set # # Camera ISPs # # CONFIG_VIDEO_THP7312 is not set # end of Camera ISPs # CONFIG_VIDEO_CAMERA_LENS is not set # # Flash devices # # CONFIG_VIDEO_ADP1653 is not set # CONFIG_VIDEO_LM3560 is not set # CONFIG_VIDEO_LM3646 is not set # end of Flash devices # # Audio decoders, processors and mixers # # CONFIG_VIDEO_CS3308 is not set # CONFIG_VIDEO_CS5345 is not set CONFIG_VIDEO_CS53L32A=y CONFIG_VIDEO_MSP3400=y # CONFIG_VIDEO_SONY_BTF_MPX is not set # CONFIG_VIDEO_TDA1997X is not set # CONFIG_VIDEO_TDA7432 is not set # CONFIG_VIDEO_TDA9840 is not set # CONFIG_VIDEO_TEA6415C is not set # CONFIG_VIDEO_TEA6420 is not set # CONFIG_VIDEO_TLV320AIC23B is not set # CONFIG_VIDEO_TVAUDIO is not set # CONFIG_VIDEO_UDA1342 is not set # CONFIG_VIDEO_VP27SMPX is not set # CONFIG_VIDEO_WM8739 is not set CONFIG_VIDEO_WM8775=y # end of Audio decoders, processors and mixers # # RDS decoders # # CONFIG_VIDEO_SAA6588 is not set # end of RDS decoders # # Video decoders # # CONFIG_VIDEO_ADV7180 is not set # CONFIG_VIDEO_ADV7183 is not set # CONFIG_VIDEO_ADV748X is not set # CONFIG_VIDEO_ADV7604 is not set # CONFIG_VIDEO_ADV7842 is not set # CONFIG_VIDEO_BT819 is not set # CONFIG_VIDEO_BT856 is not set # CONFIG_VIDEO_BT866 is not set # CONFIG_VIDEO_ISL7998X is not set # CONFIG_VIDEO_LT6911UXE is not set # CONFIG_VIDEO_KS0127 is not set # CONFIG_VIDEO_MAX9286 is not set # CONFIG_VIDEO_ML86V7667 is not set # CONFIG_VIDEO_SAA7110 is not set CONFIG_VIDEO_SAA711X=y # CONFIG_VIDEO_TC358743 is not set # CONFIG_VIDEO_TC358746 is not set # CONFIG_VIDEO_TVP514X is not set # CONFIG_VIDEO_TVP5150 is not set # CONFIG_VIDEO_TVP7002 is not set # CONFIG_VIDEO_TW2804 is not set # CONFIG_VIDEO_TW9900 is not set # CONFIG_VIDEO_TW9903 is not set # CONFIG_VIDEO_TW9906 is not set # CONFIG_VIDEO_TW9910 is not set # CONFIG_VIDEO_VPX3220 is not set # # Video and audio decoders # # CONFIG_VIDEO_SAA717X is not set CONFIG_VIDEO_CX25840=y # end of Video decoders # # Video encoders # # CONFIG_VIDEO_ADV7170 is not set # CONFIG_VIDEO_ADV7175 is not set # CONFIG_VIDEO_ADV7343 is not set # CONFIG_VIDEO_ADV7393 is not set # CONFIG_VIDEO_ADV7511 is not set # CONFIG_VIDEO_AK881X is not set # CONFIG_VIDEO_SAA7127 is not set # CONFIG_VIDEO_SAA7185 is not set # CONFIG_VIDEO_THS8200 is not set # end of Video encoders # # Video improvement chips # # CONFIG_VIDEO_UPD64031A is not set # CONFIG_VIDEO_UPD64083 is not set # end of Video improvement chips # # Audio/Video compression chips # # CONFIG_VIDEO_SAA6752HS is not set # end of Audio/Video compression chips # # SDR tuner chips # # CONFIG_SDR_MAX2175 is not set # end of SDR tuner chips # # Miscellaneous helper chips # # CONFIG_VIDEO_I2C is not set # CONFIG_VIDEO_M52790 is not set # CONFIG_VIDEO_ST_MIPID02 is not set # CONFIG_VIDEO_THS7303 is not set # end of Miscellaneous helper chips # # Video serializers and deserializers # # CONFIG_VIDEO_DS90UB913 is not set # CONFIG_VIDEO_DS90UB953 is not set # CONFIG_VIDEO_DS90UB960 is not set # CONFIG_VIDEO_MAX96714 is not set # CONFIG_VIDEO_MAX96717 is not set # end of Video serializers and deserializers # # Media SPI Adapters # # CONFIG_CXD2880_SPI_DRV is not set # CONFIG_VIDEO_GS1662 is not set # end of Media SPI Adapters CONFIG_MEDIA_TUNER=y # # Customize TV tuners # # CONFIG_MEDIA_TUNER_E4000 is not set # CONFIG_MEDIA_TUNER_FC0011 is not set # CONFIG_MEDIA_TUNER_FC0012 is not set # CONFIG_MEDIA_TUNER_FC0013 is not set # CONFIG_MEDIA_TUNER_FC2580 is not set # CONFIG_MEDIA_TUNER_IT913X is not set # CONFIG_MEDIA_TUNER_M88RS6000T is not set # CONFIG_MEDIA_TUNER_MAX2165 is not set # CONFIG_MEDIA_TUNER_MC44S803 is not set CONFIG_MEDIA_TUNER_MSI001=y # CONFIG_MEDIA_TUNER_MT2060 is not set # CONFIG_MEDIA_TUNER_MT2063 is not set # CONFIG_MEDIA_TUNER_MT20XX is not set # CONFIG_MEDIA_TUNER_MT2131 is not set # CONFIG_MEDIA_TUNER_MT2266 is not set # CONFIG_MEDIA_TUNER_MXL301RF is not set # CONFIG_MEDIA_TUNER_MXL5005S is not set # CONFIG_MEDIA_TUNER_MXL5007T is not set # CONFIG_MEDIA_TUNER_QM1D1B0004 is not set # CONFIG_MEDIA_TUNER_QM1D1C0042 is not set # CONFIG_MEDIA_TUNER_QT1010 is not set # CONFIG_MEDIA_TUNER_R820T is not set # CONFIG_MEDIA_TUNER_SI2157 is not set # CONFIG_MEDIA_TUNER_SIMPLE is not set # CONFIG_MEDIA_TUNER_TDA18212 is not set # CONFIG_MEDIA_TUNER_TDA18218 is not set # CONFIG_MEDIA_TUNER_TDA18250 is not set # CONFIG_MEDIA_TUNER_TDA18271 is not set # CONFIG_MEDIA_TUNER_TDA827X is not set # CONFIG_MEDIA_TUNER_TDA8290 is not set # CONFIG_MEDIA_TUNER_TDA9887 is not set # CONFIG_MEDIA_TUNER_TEA5761 is not set # CONFIG_MEDIA_TUNER_TEA5767 is not set # CONFIG_MEDIA_TUNER_TUA9001 is not set # CONFIG_MEDIA_TUNER_XC2028 is not set # CONFIG_MEDIA_TUNER_XC4000 is not set # CONFIG_MEDIA_TUNER_XC5000 is not set # end of Customize TV tuners # # Customise DVB Frontends # # # Multistandard (satellite) frontends # # CONFIG_DVB_M88DS3103 is not set # CONFIG_DVB_MXL5XX is not set # CONFIG_DVB_STB0899 is not set # CONFIG_DVB_STB6100 is not set # CONFIG_DVB_STV090x is not set # CONFIG_DVB_STV0910 is not set # CONFIG_DVB_STV6110x is not set # CONFIG_DVB_STV6111 is not set # # Multistandard (cable + terrestrial) frontends # # CONFIG_DVB_DRXK is not set # CONFIG_DVB_MN88472 is not set # CONFIG_DVB_MN88473 is not set # CONFIG_DVB_SI2165 is not set # CONFIG_DVB_TDA18271C2DD is not set # # DVB-S (satellite) frontends # # CONFIG_DVB_CX24110 is not set # CONFIG_DVB_CX24116 is not set # CONFIG_DVB_CX24117 is not set # CONFIG_DVB_CX24120 is not set # CONFIG_DVB_CX24123 is not set # CONFIG_DVB_DS3000 is not set # CONFIG_DVB_MB86A16 is not set # CONFIG_DVB_MT312 is not set # CONFIG_DVB_S5H1420 is not set # CONFIG_DVB_SI21XX is not set # CONFIG_DVB_STB6000 is not set # CONFIG_DVB_STV0288 is not set # CONFIG_DVB_STV0299 is not set # CONFIG_DVB_STV0900 is not set # CONFIG_DVB_STV6110 is not set # CONFIG_DVB_TDA10071 is not set # CONFIG_DVB_TDA10086 is not set # CONFIG_DVB_TDA8083 is not set # CONFIG_DVB_TDA8261 is not set # CONFIG_DVB_TDA826X is not set # CONFIG_DVB_TS2020 is not set # CONFIG_DVB_TUA6100 is not set # CONFIG_DVB_TUNER_CX24113 is not set # CONFIG_DVB_TUNER_ITD1000 is not set # CONFIG_DVB_VES1X93 is not set # CONFIG_DVB_ZL10036 is not set # CONFIG_DVB_ZL10039 is not set # # DVB-T (terrestrial) frontends # CONFIG_DVB_AF9013=y CONFIG_DVB_AS102_FE=y # CONFIG_DVB_CX22700 is not set # CONFIG_DVB_CX22702 is not set # CONFIG_DVB_CXD2820R is not set # CONFIG_DVB_CXD2841ER is not set CONFIG_DVB_DIB3000MB=y CONFIG_DVB_DIB3000MC=y # CONFIG_DVB_DIB7000M is not set # CONFIG_DVB_DIB7000P is not set # CONFIG_DVB_DIB9000 is not set # CONFIG_DVB_DRXD is not set CONFIG_DVB_EC100=y CONFIG_DVB_GP8PSK_FE=y # CONFIG_DVB_L64781 is not set # CONFIG_DVB_MT352 is not set # CONFIG_DVB_NXT6000 is not set CONFIG_DVB_RTL2830=y CONFIG_DVB_RTL2832=y CONFIG_DVB_RTL2832_SDR=y # CONFIG_DVB_S5H1432 is not set # CONFIG_DVB_SI2168 is not set # CONFIG_DVB_SP887X is not set # CONFIG_DVB_STV0367 is not set # CONFIG_DVB_TDA10048 is not set # CONFIG_DVB_TDA1004X is not set # CONFIG_DVB_ZD1301_DEMOD is not set CONFIG_DVB_ZL10353=y # CONFIG_DVB_CXD2880 is not set # # DVB-C (cable) frontends # # CONFIG_DVB_STV0297 is not set # CONFIG_DVB_TDA10021 is not set # CONFIG_DVB_TDA10023 is not set # CONFIG_DVB_VES1820 is not set # # ATSC (North American/Korean Terrestrial/Cable DTV) frontends # # CONFIG_DVB_AU8522_DTV is not set # CONFIG_DVB_AU8522_V4L is not set # CONFIG_DVB_BCM3510 is not set # CONFIG_DVB_LG2160 is not set # CONFIG_DVB_LGDT3305 is not set # CONFIG_DVB_LGDT3306A is not set # CONFIG_DVB_LGDT330X is not set # CONFIG_DVB_MXL692 is not set # CONFIG_DVB_NXT200X is not set # CONFIG_DVB_OR51132 is not set # CONFIG_DVB_OR51211 is not set # CONFIG_DVB_S5H1409 is not set # CONFIG_DVB_S5H1411 is not set # # ISDB-T (terrestrial) frontends # # CONFIG_DVB_DIB8000 is not set # CONFIG_DVB_MB86A20S is not set # CONFIG_DVB_S921 is not set # # ISDB-S (satellite) & ISDB-T (terrestrial) frontends # # CONFIG_DVB_MN88443X is not set # CONFIG_DVB_TC90522 is not set # # Digital terrestrial only tuners/PLL # # CONFIG_DVB_PLL is not set # CONFIG_DVB_TUNER_DIB0070 is not set # CONFIG_DVB_TUNER_DIB0090 is not set # # SEC control devices for DVB-S # # CONFIG_DVB_A8293 is not set CONFIG_DVB_AF9033=y # CONFIG_DVB_ASCOT2E is not set # CONFIG_DVB_ATBM8830 is not set # CONFIG_DVB_HELENE is not set # CONFIG_DVB_HORUS3A is not set # CONFIG_DVB_ISL6405 is not set # CONFIG_DVB_ISL6421 is not set # CONFIG_DVB_ISL6423 is not set # CONFIG_DVB_IX2505V is not set # CONFIG_DVB_LGS8GL5 is not set # CONFIG_DVB_LGS8GXX is not set # CONFIG_DVB_LNBH25 is not set # CONFIG_DVB_LNBH29 is not set # CONFIG_DVB_LNBP21 is not set # CONFIG_DVB_LNBP22 is not set # CONFIG_DVB_M88RS2000 is not set # CONFIG_DVB_TDA665x is not set # CONFIG_DVB_DRX39XYJ is not set # # Common Interface (EN50221) controller drivers # # CONFIG_DVB_CXD2099 is not set # CONFIG_DVB_SP2 is not set # end of Customise DVB Frontends # # Tools to develop new frontends # # CONFIG_DVB_DUMMY_FE is not set # end of Media ancillary drivers # # Graphics support # CONFIG_APERTURE_HELPERS=y CONFIG_SCREEN_INFO=y CONFIG_VIDEO=y # CONFIG_AUXDISPLAY is not set # CONFIG_PANEL is not set CONFIG_AGP=y CONFIG_AGP_AMD64=y CONFIG_AGP_INTEL=y # CONFIG_AGP_SIS is not set # CONFIG_AGP_VIA is not set CONFIG_INTEL_GTT=y # CONFIG_VGA_SWITCHEROO is not set CONFIG_GPU_BUDDY=y CONFIG_DRM=y # # DRM debugging options # # CONFIG_DRM_WERROR is not set # CONFIG_DRM_DEBUG_MM is not set # end of DRM debugging options CONFIG_DRM_MIPI_DSI=y CONFIG_DRM_KMS_HELPER=y # CONFIG_DRM_PANIC is not set # CONFIG_DRM_RAS is not set # CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS is not set # CONFIG_DRM_DEBUG_MODESET_LOCK is not set CONFIG_DRM_CLIENT_SELECTION=y # # Supported DRM clients # # CONFIG_DRM_FBDEV_EMULATION is not set # CONFIG_DRM_CLIENT_LOG is not set # end of Supported DRM clients # CONFIG_DRM_LOAD_EDID_FIRMWARE is not set CONFIG_DRM_DISPLAY_HELPER=y # CONFIG_DRM_DISPLAY_DP_AUX_CEC is not set # CONFIG_DRM_DISPLAY_DP_AUX_CHARDEV is not set CONFIG_DRM_DISPLAY_DP_HELPER=y CONFIG_DRM_DISPLAY_DSC_HELPER=y CONFIG_DRM_DISPLAY_HDCP_HELPER=y CONFIG_DRM_DISPLAY_HDMI_HELPER=y CONFIG_DRM_TTM=y CONFIG_DRM_BUDDY=y CONFIG_DRM_GEM_SHMEM_HELPER=y # CONFIG_DRM_AMDGPU is not set # # ARM devices # # CONFIG_DRM_KOMEDA is not set # end of ARM devices # CONFIG_DRM_AST is not set CONFIG_DRM_BRIDGE=y CONFIG_DRM_PANEL_BRIDGE=y CONFIG_DRM_AUX_BRIDGE=y CONFIG_DRM_AUX_HPD_BRIDGE=y # # Display Interface Bridges # # CONFIG_DRM_CHIPONE_ICN6211 is not set # CONFIG_DRM_CHRONTEL_CH7033 is not set # CONFIG_DRM_DISPLAY_CONNECTOR is not set # CONFIG_DRM_I2C_NXP_TDA998X is not set # CONFIG_DRM_ITE_IT6263 is not set # CONFIG_DRM_ITE_IT6505 is not set # CONFIG_DRM_LONTIUM_LT8912B is not set # CONFIG_DRM_LONTIUM_LT9211 is not set # CONFIG_DRM_LONTIUM_LT9611 is not set # CONFIG_DRM_LONTIUM_LT9611UXC is not set # CONFIG_DRM_LONTIUM_LT8713SX is not set # CONFIG_DRM_ITE_IT66121 is not set # CONFIG_DRM_LVDS_CODEC is not set # CONFIG_DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW is not set # CONFIG_DRM_NWL_MIPI_DSI is not set # CONFIG_DRM_NXP_PTN3460 is not set # CONFIG_DRM_PARADE_PS8622 is not set # CONFIG_DRM_PARADE_PS8640 is not set # CONFIG_DRM_SAMSUNG_DSIM is not set # CONFIG_DRM_SIL_SII8620 is not set # CONFIG_DRM_SII902X is not set # CONFIG_DRM_SII9234 is not set # CONFIG_DRM_SIMPLE_BRIDGE is not set # CONFIG_DRM_SOLOMON_SSD2825 is not set # CONFIG_DRM_THINE_THC63LVD1024 is not set # CONFIG_DRM_TOSHIBA_TC358762 is not set # CONFIG_DRM_TOSHIBA_TC358764 is not set # CONFIG_DRM_TOSHIBA_TC358767 is not set # CONFIG_DRM_TOSHIBA_TC358768 is not set # CONFIG_DRM_TOSHIBA_TC358775 is not set # CONFIG_DRM_TI_DLPC3433 is not set # CONFIG_DRM_TI_TDP158 is not set # CONFIG_DRM_TI_TFP410 is not set # CONFIG_DRM_TI_SN65DSI83 is not set # CONFIG_DRM_TI_SN65DSI86 is not set # CONFIG_DRM_TI_TPD12S015 is not set # CONFIG_DRM_WAVESHARE_BRIDGE is not set # CONFIG_DRM_ANALOGIX_ANX6345 is not set # CONFIG_DRM_ANALOGIX_ANX78XX is not set # CONFIG_DRM_ANALOGIX_ANX7625 is not set # CONFIG_DRM_I2C_ADV7511 is not set # CONFIG_DRM_CDNS_DSI is not set # CONFIG_DRM_CDNS_MHDP8546 is not set # end of Display Interface Bridges # CONFIG_DRM_ETNAVIV is not set # CONFIG_DRM_GMA500 is not set CONFIG_DRM_GUD=y # CONFIG_DRM_HISI_HIBMC is not set CONFIG_DRM_I915=y CONFIG_DRM_I915_FORCE_PROBE="" CONFIG_DRM_I915_CAPTURE_ERROR=y CONFIG_DRM_I915_COMPRESS_ERROR=y CONFIG_DRM_I915_USERPTR=y # CONFIG_DRM_I915_DP_TUNNEL is not set # # drm/i915 Debugging # # CONFIG_DRM_I915_WERROR is not set # CONFIG_DRM_I915_REPLAY_GPU_HANGS_API is not set # CONFIG_DRM_I915_DEBUG is not set # CONFIG_DRM_I915_DEBUG_MMIO is not set # CONFIG_DRM_I915_SW_FENCE_DEBUG_OBJECTS is not set # CONFIG_DRM_I915_SW_FENCE_CHECK_DAG is not set # CONFIG_DRM_I915_DEBUG_GUC is not set # CONFIG_DRM_I915_SELFTEST is not set # CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS is not set # CONFIG_DRM_I915_DEBUG_VBLANK_EVADE is not set # CONFIG_DRM_I915_DEBUG_RUNTIME_PM is not set # CONFIG_DRM_I915_DEBUG_WAKEREF is not set # end of drm/i915 Debugging # # drm/i915 Profile Guided Optimisation # CONFIG_DRM_I915_REQUEST_TIMEOUT=20000 CONFIG_DRM_I915_FENCE_TIMEOUT=10000 CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND=250 CONFIG_DRM_I915_HEARTBEAT_INTERVAL=2500 CONFIG_DRM_I915_PREEMPT_TIMEOUT=640 CONFIG_DRM_I915_PREEMPT_TIMEOUT_COMPUTE=7500 CONFIG_DRM_I915_MAX_REQUEST_BUSYWAIT=8000 CONFIG_DRM_I915_STOP_TIMEOUT=100 CONFIG_DRM_I915_TIMESLICE_DURATION=1 # end of drm/i915 Profile Guided Optimisation # CONFIG_DRM_LOGICVC is not set # CONFIG_DRM_MGAG200 is not set # CONFIG_DRM_NOUVEAU is not set CONFIG_DRM_PANEL=y # # Display Panels # # CONFIG_DRM_PANEL_ABT_Y030XX067A is not set # CONFIG_DRM_PANEL_ARM_VERSATILE is not set # CONFIG_DRM_PANEL_ASUS_Z00T_TM5P5_NT35596 is not set # CONFIG_DRM_PANEL_AUO_A030JTN01 is not set # CONFIG_DRM_PANEL_BOE_BF060Y8M_AJ0 is not set # CONFIG_DRM_PANEL_BOE_HIMAX8279D is not set # CONFIG_DRM_PANEL_BOE_TD4320 is not set # CONFIG_DRM_PANEL_BOE_TH101MB31UIG002_28A is not set # CONFIG_DRM_PANEL_BOE_TV101WUM_NL6 is not set # CONFIG_DRM_PANEL_BOE_TV101WUM_LL2 is not set # CONFIG_DRM_PANEL_EBBG_FT8719 is not set # CONFIG_DRM_PANEL_ELIDA_KD35T133 is not set # CONFIG_DRM_PANEL_FEIXIN_K101_IM2BA02 is not set # CONFIG_DRM_PANEL_FEIYANG_FY07024DI26A30D is not set # CONFIG_DRM_PANEL_DSI_CM is not set # CONFIG_DRM_PANEL_LVDS is not set # CONFIG_DRM_PANEL_HIMAX_HX8279 is not set # CONFIG_DRM_PANEL_HIMAX_HX83102 is not set # CONFIG_DRM_PANEL_HIMAX_HX83112A is not set # CONFIG_DRM_PANEL_HIMAX_HX83112B is not set # CONFIG_DRM_PANEL_HIMAX_HX83121A is not set # CONFIG_DRM_PANEL_HIMAX_HX8394 is not set # CONFIG_DRM_PANEL_HYDIS_HV101HD1 is not set # CONFIG_DRM_PANEL_ILITEK_IL9322 is not set # CONFIG_DRM_PANEL_ILITEK_ILI9341 is not set # CONFIG_DRM_PANEL_ILITEK_ILI9805 is not set # CONFIG_DRM_PANEL_ILITEK_ILI9806E_DSI is not set # CONFIG_DRM_PANEL_ILITEK_ILI9806E_SPI is not set # CONFIG_DRM_PANEL_ILITEK_ILI9881C is not set # CONFIG_DRM_PANEL_ILITEK_ILI9882T is not set # CONFIG_DRM_PANEL_INNOLUX_EJ030NA is not set # CONFIG_DRM_PANEL_INNOLUX_P079ZCA is not set # CONFIG_DRM_PANEL_JADARD_JD9365DA_H3 is not set # CONFIG_DRM_PANEL_JDI_LPM102A188A is not set # CONFIG_DRM_PANEL_JDI_LT070ME05000 is not set # CONFIG_DRM_PANEL_JDI_R63452 is not set # CONFIG_DRM_PANEL_KHADAS_TS050 is not set # CONFIG_DRM_PANEL_KINGDISPLAY_KD097D04 is not set # CONFIG_DRM_PANEL_LEADTEK_LTK050H3146W is not set # CONFIG_DRM_PANEL_LEADTEK_LTK500HD1829 is not set # CONFIG_DRM_PANEL_LINCOLNTECH_LCD197 is not set # CONFIG_DRM_PANEL_LG_LB035Q02 is not set # CONFIG_DRM_PANEL_LG_LD070WX3 is not set # CONFIG_DRM_PANEL_LG_LG4573 is not set # CONFIG_DRM_PANEL_LG_SW43408 is not set # CONFIG_DRM_PANEL_LXD_M9189A is not set # CONFIG_DRM_PANEL_MAGNACHIP_D53E6EA8966 is not set # CONFIG_DRM_PANEL_MANTIX_MLAF057WE51 is not set # CONFIG_DRM_PANEL_MOTOROLA_MOT is not set # CONFIG_DRM_PANEL_NEC_NL8048HL11 is not set # CONFIG_DRM_PANEL_NEWVISION_NV3051D is not set # CONFIG_DRM_PANEL_NEWVISION_NV3052C is not set # CONFIG_DRM_PANEL_NOVATEK_NT35510 is not set # CONFIG_DRM_PANEL_NOVATEK_NT35560 is not set # CONFIG_DRM_PANEL_NOVATEK_NT35950 is not set # CONFIG_DRM_PANEL_NOVATEK_NT36523 is not set # CONFIG_DRM_PANEL_NOVATEK_NT36672A is not set # CONFIG_DRM_PANEL_NOVATEK_NT36672E is not set # CONFIG_DRM_PANEL_NOVATEK_NT37700F is not set # CONFIG_DRM_PANEL_NOVATEK_NT37801 is not set # CONFIG_DRM_PANEL_NOVATEK_NT39016 is not set # CONFIG_DRM_PANEL_OLIMEX_LCD_OLINUXINO is not set # CONFIG_DRM_PANEL_ORISETECH_OTA5601A is not set # CONFIG_DRM_PANEL_ORISETECH_OTM8009A is not set # CONFIG_DRM_PANEL_OSD_OSD101T2587_53TS is not set # CONFIG_DRM_PANEL_PANASONIC_VVX10F034N00 is not set # CONFIG_DRM_PANEL_RASPBERRYPI_TOUCHSCREEN is not set # CONFIG_DRM_PANEL_RAYDIUM_RM67191 is not set # CONFIG_DRM_PANEL_RAYDIUM_RM67200 is not set # CONFIG_DRM_PANEL_RAYDIUM_RM68200 is not set # CONFIG_DRM_PANEL_RAYDIUM_RM692E5 is not set # CONFIG_DRM_PANEL_RAYDIUM_RM69380 is not set # CONFIG_DRM_PANEL_RENESAS_R61307 is not set # CONFIG_DRM_PANEL_RENESAS_R69328 is not set # CONFIG_DRM_PANEL_RONBO_RB070D30 is not set # CONFIG_DRM_PANEL_SAMSUNG_AMS581VF01 is not set # CONFIG_DRM_PANEL_SAMSUNG_AMS639RQ08 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E88A0_AMS427AP24 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E88A0_AMS452EF01 is not set # CONFIG_DRM_PANEL_SAMSUNG_ATNA33XC20 is not set # CONFIG_DRM_PANEL_SAMSUNG_DB7430 is not set # CONFIG_DRM_PANEL_SAMSUNG_LD9040 is not set # CONFIG_DRM_PANEL_SAMSUNG_LTL106HL02 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E3FA7 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6D16D0 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6D27A1 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6D7AA0 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E3FC2X01 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E3HA2 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E3HA8 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E63J0X03 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E63M0 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E8AA0 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E8AA5X01_AMS561RA01 is not set # CONFIG_DRM_PANEL_SAMSUNG_S6E8FC0 is not set # CONFIG_DRM_PANEL_SAMSUNG_SOFEF00 is not set # CONFIG_DRM_PANEL_SEIKO_43WVF1G is not set # CONFIG_DRM_PANEL_SHARP_LQ079L1SX01 is not set # CONFIG_DRM_PANEL_SHARP_LQ101R1SX01 is not set # CONFIG_DRM_PANEL_SHARP_LS037V7DW01 is not set # CONFIG_DRM_PANEL_SHARP_LS043T1LE01 is not set # CONFIG_DRM_PANEL_SHARP_LS060T1SX01 is not set # CONFIG_DRM_PANEL_SITRONIX_ST7701 is not set # CONFIG_DRM_PANEL_SITRONIX_ST7703 is not set # CONFIG_DRM_PANEL_SITRONIX_ST7789V is not set # CONFIG_DRM_PANEL_SONY_ACX565AKM is not set # CONFIG_DRM_PANEL_SONY_TD4353_JDI is not set # CONFIG_DRM_PANEL_SONY_TULIP_TRULY_NT35521 is not set # CONFIG_DRM_PANEL_STARTEK_KD070FHFID015 is not set # CONFIG_DRM_PANEL_EDP is not set # CONFIG_DRM_PANEL_SIMPLE is not set # CONFIG_DRM_PANEL_SUMMIT is not set # CONFIG_DRM_PANEL_SYNAPTICS_R63353 is not set # CONFIG_DRM_PANEL_SYNAPTICS_TDDI is not set # CONFIG_DRM_PANEL_TDO_TL070WSH30 is not set # CONFIG_DRM_PANEL_TPO_TD028TTEC1 is not set # CONFIG_DRM_PANEL_TPO_TD043MTEA1 is not set # CONFIG_DRM_PANEL_TPO_TPG110 is not set # CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA is not set # CONFIG_DRM_PANEL_VISIONOX_G2647FB105 is not set # CONFIG_DRM_PANEL_VISIONOX_R66451 is not set # CONFIG_DRM_PANEL_VISIONOX_RM69299 is not set # CONFIG_DRM_PANEL_VISIONOX_RM692E5 is not set # CONFIG_DRM_PANEL_VISIONOX_VTDR6130 is not set # CONFIG_DRM_PANEL_WIDECHIPS_WS2401 is not set # CONFIG_DRM_PANEL_XINPENG_XPP055C272 is not set # end of Display Panels # CONFIG_DRM_QXL is not set # CONFIG_DRM_RADEON is not set # CONFIG_DRM_ST7571 is not set # CONFIG_DRM_ST7586 is not set # CONFIG_DRM_ST7735R is not set # CONFIG_DRM_ST7920 is not set # CONFIG_DRM_SSD130X is not set # # Drivers for system framebuffers # # CONFIG_DRM_SIMPLEDRM is not set # CONFIG_DRM_VESADRM is not set # end of Drivers for system framebuffers # CONFIG_DRM_APPLETBDRM is not set # CONFIG_DRM_ARCPGU is not set # CONFIG_DRM_BOCHS is not set # CONFIG_DRM_CIRRUS_QEMU is not set CONFIG_DRM_GM12U320=y # CONFIG_DRM_PANEL_MIPI_DBI is not set # CONFIG_DRM_PIXPAPER is not set # CONFIG_TINYDRM_HX8357D is not set # CONFIG_TINYDRM_ILI9163 is not set # CONFIG_TINYDRM_ILI9225 is not set # CONFIG_TINYDRM_ILI9341 is not set # CONFIG_TINYDRM_ILI9486 is not set # CONFIG_TINYDRM_MI0283QT is not set # CONFIG_TINYDRM_REPAPER is not set # CONFIG_TINYDRM_SHARP_MEMORY is not set CONFIG_DRM_UDL=y # CONFIG_DRM_VBOXVIDEO is not set # CONFIG_DRM_VGEM is not set CONFIG_DRM_VIRTIO_GPU=y CONFIG_DRM_VIRTIO_GPU_KMS=y # CONFIG_DRM_VKMS is not set # CONFIG_DRM_VMWGFX is not set # CONFIG_DRM_XE is not set CONFIG_DRM_PANEL_ORIENTATION_QUIRKS=y # # Frame buffer Devices # CONFIG_FB=y # CONFIG_FB_CIRRUS is not set # CONFIG_FB_PM2 is not set # CONFIG_FB_CYBER2000 is not set # CONFIG_FB_ARC is not set # CONFIG_FB_ASILIANT is not set # CONFIG_FB_IMSTT is not set # CONFIG_FB_VGA16 is not set # CONFIG_FB_UVESA is not set # CONFIG_FB_VESA is not set # CONFIG_FB_N411 is not set # CONFIG_FB_HGA is not set # CONFIG_FB_OPENCORES is not set # CONFIG_FB_S1D13XXX is not set # CONFIG_FB_NVIDIA is not set # CONFIG_FB_RIVA is not set # CONFIG_FB_I740 is not set # CONFIG_FB_RADEON is not set # CONFIG_FB_ATY128 is not set # CONFIG_FB_ATY is not set # CONFIG_FB_SAVAGE is not set # CONFIG_FB_SIS is not set # CONFIG_FB_VIA is not set # CONFIG_FB_NEOMAGIC is not set # CONFIG_FB_KYRO is not set # CONFIG_FB_3DFX is not set # CONFIG_FB_VOODOO1 is not set # CONFIG_FB_TRIDENT is not set # CONFIG_FB_PM3 is not set # CONFIG_FB_CARMINE is not set CONFIG_FB_SMSCUFX=y CONFIG_FB_UDL=y # CONFIG_FB_IBM_GXT4500 is not set # CONFIG_FB_VIRTUAL is not set # CONFIG_FB_METRONOME is not set # CONFIG_FB_MB862XX is not set # CONFIG_FB_SIMPLE is not set # CONFIG_FB_SSD1307 is not set # CONFIG_FB_SM712 is not set CONFIG_FB_CORE=y CONFIG_FB_NOTIFY=y CONFIG_FB_DEVICE=y CONFIG_FB_SYS_FILLRECT=y CONFIG_FB_SYS_COPYAREA=y CONFIG_FB_SYS_IMAGEBLIT=y # CONFIG_FB_FOREIGN_ENDIAN is not set CONFIG_FB_SYSMEM_FOPS=y CONFIG_FB_DEFERRED_IO=y CONFIG_FB_SYSMEM_HELPERS=y CONFIG_FB_SYSMEM_HELPERS_DEFERRED=y CONFIG_FB_MODE_HELPERS=y # CONFIG_FB_TILEBLITTING is not set # end of Frame buffer Devices # # Backlight & LCD device support # CONFIG_LCD_CLASS_DEVICE=y # CONFIG_LCD_L4F00242T03 is not set # CONFIG_LCD_LMS283GF05 is not set # CONFIG_LCD_LTV350QV is not set # CONFIG_LCD_ILI922X is not set # CONFIG_LCD_ILI9320 is not set # CONFIG_LCD_TDO24M is not set # CONFIG_LCD_VGG2432A4 is not set # CONFIG_LCD_PLATFORM is not set # CONFIG_LCD_AMS369FG06 is not set # CONFIG_LCD_LMS501KF03 is not set # CONFIG_LCD_HX8357 is not set # CONFIG_LCD_OTM3225A is not set CONFIG_BACKLIGHT_CLASS_DEVICE=y # CONFIG_BACKLIGHT_AW99706 is not set # CONFIG_BACKLIGHT_KTD253 is not set # CONFIG_BACKLIGHT_KTD2801 is not set # CONFIG_BACKLIGHT_KTZ8866 is not set # CONFIG_BACKLIGHT_MT6370 is not set # CONFIG_BACKLIGHT_APPLE is not set # CONFIG_BACKLIGHT_QCOM_WLED is not set # CONFIG_BACKLIGHT_SAHARA is not set # CONFIG_BACKLIGHT_ADP8860 is not set # CONFIG_BACKLIGHT_ADP8870 is not set # CONFIG_BACKLIGHT_LM3509 is not set # CONFIG_BACKLIGHT_LM3639 is not set # CONFIG_BACKLIGHT_PANDORA is not set # CONFIG_BACKLIGHT_GPIO is not set # CONFIG_BACKLIGHT_LV5207LP is not set # CONFIG_BACKLIGHT_BD6107 is not set # CONFIG_BACKLIGHT_ARCXCNN is not set # CONFIG_BACKLIGHT_LED is not set # end of Backlight & LCD device support CONFIG_HDMI=y # CONFIG_FIRMWARE_EDID is not set # # Console display driver support # CONFIG_VGA_CONSOLE=y CONFIG_DUMMY_CONSOLE=y CONFIG_DUMMY_CONSOLE_COLUMNS=80 CONFIG_DUMMY_CONSOLE_ROWS=25 # CONFIG_FRAMEBUFFER_CONSOLE is not set # end of Console display driver support # CONFIG_LOGO is not set # CONFIG_TRACE_GPU_MEM is not set # end of Graphics support # CONFIG_DRM_ACCEL is not set CONFIG_SOUND=y CONFIG_SND=y CONFIG_SND_TIMER=y CONFIG_SND_PCM=y CONFIG_SND_HWDEP=y CONFIG_SND_SEQ_DEVICE=y CONFIG_SND_RAWMIDI=y CONFIG_SND_UMP=y CONFIG_SND_UMP_LEGACY_RAWMIDI=y CONFIG_SND_JACK=y CONFIG_SND_JACK_INPUT_DEV=y # CONFIG_SND_OSSEMUL is not set CONFIG_SND_PCM_TIMER=y CONFIG_SND_HRTIMER=y # CONFIG_SND_DYNAMIC_MINORS is not set # CONFIG_SND_SUPPORT_OLD_API is not set CONFIG_SND_PROC_FS=y CONFIG_SND_VERBOSE_PROCFS=y CONFIG_SND_CTL_FAST_LOOKUP=y # CONFIG_SND_DEBUG is not set # CONFIG_SND_CTL_INPUT_VALIDATION is not set # CONFIG_SND_UTIMER is not set CONFIG_SND_VMASTER=y CONFIG_SND_DMA_SGBUF=y CONFIG_SND_SEQUENCER=y CONFIG_SND_SEQ_DUMMY=y CONFIG_SND_SEQ_HRTIMER_DEFAULT=y CONFIG_SND_SEQ_MIDI_EVENT=y CONFIG_SND_SEQ_MIDI=y # CONFIG_SND_SEQ_UMP is not set CONFIG_SND_DRIVERS=y # CONFIG_SND_PCSP is not set # CONFIG_SND_DUMMY is not set # CONFIG_SND_ALOOP is not set # CONFIG_SND_PCMTEST is not set # CONFIG_SND_VIRMIDI is not set # CONFIG_SND_MTPAV is not set # CONFIG_SND_MTS64 is not set # CONFIG_SND_SERIAL_U16550 is not set # CONFIG_SND_SERIAL_GENERIC is not set # CONFIG_SND_MPU401 is not set # CONFIG_SND_PORTMAN2X4 is not set CONFIG_SND_PCI=y # CONFIG_SND_AD1889 is not set # CONFIG_SND_ALS300 is not set # CONFIG_SND_ALS4000 is not set # CONFIG_SND_ALI5451 is not set # CONFIG_SND_ASIHPI is not set # CONFIG_SND_ATIIXP is not set # CONFIG_SND_ATIIXP_MODEM is not set # CONFIG_SND_AU8810 is not set # CONFIG_SND_AU8820 is not set # CONFIG_SND_AU8830 is not set # CONFIG_SND_AW2 is not set # CONFIG_SND_AZT3328 is not set # CONFIG_SND_BT87X is not set # CONFIG_SND_CA0106 is not set # CONFIG_SND_CMIPCI is not set # CONFIG_SND_OXYGEN is not set # CONFIG_SND_CS4281 is not set # CONFIG_SND_CS46XX is not set # CONFIG_SND_CTXFI is not set # CONFIG_SND_DARLA20 is not set # CONFIG_SND_GINA20 is not set # CONFIG_SND_LAYLA20 is not set # CONFIG_SND_DARLA24 is not set # CONFIG_SND_GINA24 is not set # CONFIG_SND_LAYLA24 is not set # CONFIG_SND_MONA is not set # CONFIG_SND_MIA is not set # CONFIG_SND_ECHO3G is not set # CONFIG_SND_INDIGO is not set # CONFIG_SND_INDIGOIO is not set # CONFIG_SND_INDIGODJ is not set # CONFIG_SND_INDIGOIOX is not set # CONFIG_SND_INDIGODJX is not set # CONFIG_SND_EMU10K1 is not set # CONFIG_SND_EMU10K1X is not set # CONFIG_SND_ENS1370 is not set # CONFIG_SND_ENS1371 is not set # CONFIG_SND_ES1938 is not set # CONFIG_SND_ES1968 is not set # CONFIG_SND_FM801 is not set # CONFIG_SND_HDSP is not set # CONFIG_SND_HDSPM is not set # CONFIG_SND_ICE1712 is not set # CONFIG_SND_ICE1724 is not set # CONFIG_SND_INTEL8X0 is not set # CONFIG_SND_INTEL8X0M is not set # CONFIG_SND_KORG1212 is not set # CONFIG_SND_LOLA is not set # CONFIG_SND_LX6464ES is not set # CONFIG_SND_MAESTRO3 is not set # CONFIG_SND_MIXART is not set # CONFIG_SND_NM256 is not set # CONFIG_SND_PCXHR is not set # CONFIG_SND_RIPTIDE is not set # CONFIG_SND_RME32 is not set # CONFIG_SND_RME96 is not set # CONFIG_SND_RME9652 is not set # CONFIG_SND_SE6X is not set # CONFIG_SND_SONICVIBES is not set # CONFIG_SND_TRIDENT is not set # CONFIG_SND_VIA82XX is not set # CONFIG_SND_VIA82XX_MODEM is not set # CONFIG_SND_VIRTUOSO is not set # CONFIG_SND_VX222 is not set # CONFIG_SND_YMFPCI is not set # # HD-Audio # CONFIG_SND_HDA=y CONFIG_SND_HDA_HWDEP=y # CONFIG_SND_HDA_RECONFIG is not set # CONFIG_SND_HDA_INPUT_BEEP is not set # CONFIG_SND_HDA_PATCH_LOADER is not set CONFIG_SND_HDA_POWER_SAVE_DEFAULT=0 # CONFIG_SND_HDA_CTL_DEV_ID is not set CONFIG_SND_HDA_PREALLOC_SIZE=0 CONFIG_SND_HDA_INTEL=y # CONFIG_SND_HDA_ACPI is not set # CONFIG_SND_HDA_CODEC_ANALOG is not set # CONFIG_SND_HDA_CODEC_SIGMATEL is not set # CONFIG_SND_HDA_CODEC_VIA is not set # CONFIG_SND_HDA_CODEC_CONEXANT is not set # CONFIG_SND_HDA_CODEC_SENARYTECH is not set # CONFIG_SND_HDA_CODEC_CA0110 is not set # CONFIG_SND_HDA_CODEC_CA0132 is not set # CONFIG_SND_HDA_CODEC_CMEDIA is not set # CONFIG_SND_HDA_CODEC_CM9825 is not set # CONFIG_SND_HDA_CODEC_SI3054 is not set # CONFIG_SND_HDA_GENERIC is not set # CONFIG_SND_HDA_CODEC_REALTEK is not set # CONFIG_SND_HDA_CODEC_CIRRUS is not set # CONFIG_SND_HDA_CODEC_HDMI is not set # CONFIG_SND_HDA_SCODEC_CS35L56_I2C is not set # CONFIG_SND_HDA_SCODEC_CS35L56_SPI is not set CONFIG_SND_HDA_CORE=y CONFIG_SND_HDA_COMPONENT=y CONFIG_SND_HDA_I915=y CONFIG_SND_INTEL_NHLT=y CONFIG_SND_INTEL_DSP_CONFIG=y CONFIG_SND_INTEL_SOUNDWIRE_ACPI=y # end of HD-Audio # CONFIG_SND_SPI is not set CONFIG_SND_USB=y CONFIG_SND_USB_AUDIO=y CONFIG_SND_USB_AUDIO_MIDI_V2=y CONFIG_SND_USB_AUDIO_USE_MEDIA_CONTROLLER=y CONFIG_SND_USB_UA101=y CONFIG_SND_USB_USX2Y=y CONFIG_SND_USB_CAIAQ=y CONFIG_SND_USB_CAIAQ_INPUT=y CONFIG_SND_USB_US122L=y # CONFIG_SND_USB_US144MKII is not set CONFIG_SND_USB_6FIRE=y CONFIG_SND_USB_HIFACE=y CONFIG_SND_BCD2000=y CONFIG_SND_USB_LINE6=y CONFIG_SND_USB_POD=y CONFIG_SND_USB_PODHD=y CONFIG_SND_USB_TONEPORT=y CONFIG_SND_USB_VARIAX=y CONFIG_SND_PCMCIA=y # CONFIG_SND_VXPOCKET is not set # CONFIG_SND_PDAUDIOCF is not set CONFIG_SND_SOC=y # CONFIG_SND_SOC_USB is not set # # Analog Devices # # CONFIG_SND_SOC_ADI_AXI_I2S is not set # CONFIG_SND_SOC_ADI_AXI_SPDIF is not set # end of Analog Devices # # AMD # # CONFIG_SND_SOC_AMD_ACP is not set # CONFIG_SND_SOC_AMD_ACP3x is not set # CONFIG_SND_SOC_AMD_RENOIR is not set # CONFIG_SND_SOC_AMD_ACP5x is not set # CONFIG_SND_SOC_AMD_ACP6x is not set # CONFIG_SND_AMD_ACP_CONFIG is not set # CONFIG_SND_SOC_AMD_ACP_COMMON is not set # end of AMD # # Apple # # end of Apple # # Atmel # # CONFIG_SND_SOC_MIKROE_PROTO is not set # end of Atmel # # Au1x # # end of Au1x # # Broadcom # # CONFIG_SND_BCM63XX_I2S_WHISTLER is not set # end of Broadcom # # Cirrus Logic # # end of Cirrus Logic # # DesignWare # # CONFIG_SND_DESIGNWARE_I2S is not set # end of DesignWare # # Freescale # # # Common SoC Audio options for Freescale CPUs: # # CONFIG_SND_SOC_FSL_ASRC is not set # CONFIG_SND_SOC_FSL_SAI is not set # CONFIG_SND_SOC_FSL_AUDMIX is not set # CONFIG_SND_SOC_FSL_SSI is not set # CONFIG_SND_SOC_FSL_SPDIF is not set # CONFIG_SND_SOC_FSL_ESAI is not set # CONFIG_SND_SOC_FSL_MICFIL is not set # CONFIG_SND_SOC_FSL_XCVR is not set # CONFIG_SND_SOC_IMX_AUDMUX is not set # end of Freescale # # Google # # CONFIG_SND_SOC_CHV3_I2S is not set # end of Google # # Hisilicon # # CONFIG_SND_I2S_HI6210_I2S is not set # end of Hisilicon # # JZ4740 # # end of JZ4740 # # Kirkwood # # end of Kirkwood # # Loongson # # end of Loongson # # Intel # # CONFIG_SND_SOC_INTEL_SST_TOPLEVEL is not set # CONFIG_SND_SOC_INTEL_AVS is not set # end of Intel # # Mediatek # # CONFIG_SND_SOC_MTK_BTCVSD is not set # end of Mediatek # # PXA # # end of PXA # # SoundWire (SDCA) # CONFIG_SND_SOC_SDCA_OPTIONAL=y # end of SoundWire (SDCA) # # ST SPEAr # # end of ST SPEAr # # Spreadtrum # # end of Spreadtrum # # STMicroelectronics STM32 # # end of STMicroelectronics STM32 # # Tegra # # end of Tegra # # Xilinx # # CONFIG_SND_SOC_XILINX_I2S is not set # CONFIG_SND_SOC_XILINX_AUDIO_FORMATTER is not set # CONFIG_SND_SOC_XILINX_SPDIF is not set # end of Xilinx # # Xtensa # # CONFIG_SND_SOC_XTFPGA_I2S is not set # end of Xtensa # CONFIG_SND_SOC_SOF_TOPLEVEL is not set CONFIG_SND_SOC_I2C_AND_SPI=y # # CODEC drivers # # CONFIG_SND_SOC_AC97_CODEC is not set # CONFIG_SND_SOC_ADAU1372_I2C is not set # CONFIG_SND_SOC_ADAU1372_SPI is not set # CONFIG_SND_SOC_ADAU1373 is not set # CONFIG_SND_SOC_ADAU1701 is not set # CONFIG_SND_SOC_ADAU1761_I2C is not set # CONFIG_SND_SOC_ADAU1761_SPI is not set # CONFIG_SND_SOC_ADAU7002 is not set # CONFIG_SND_SOC_ADAU7118_HW is not set # CONFIG_SND_SOC_ADAU7118_I2C is not set # CONFIG_SND_SOC_AK4104 is not set # CONFIG_SND_SOC_AK4118 is not set # CONFIG_SND_SOC_AK4375 is not set # CONFIG_SND_SOC_AK4458 is not set # CONFIG_SND_SOC_AK4554 is not set # CONFIG_SND_SOC_AK4613 is not set # CONFIG_SND_SOC_AK4619 is not set # CONFIG_SND_SOC_AK4642 is not set # CONFIG_SND_SOC_AK5386 is not set # CONFIG_SND_SOC_AK5558 is not set # CONFIG_SND_SOC_ALC5623 is not set # CONFIG_SND_SOC_AUDIO_IIO_AUX is not set # CONFIG_SND_SOC_AW8738 is not set # CONFIG_SND_SOC_AW88395 is not set # CONFIG_SND_SOC_AW88166 is not set # CONFIG_SND_SOC_AW88261 is not set # CONFIG_SND_SOC_AW88081 is not set # CONFIG_SND_SOC_AW87390 is not set # CONFIG_SND_SOC_AW88399 is not set # CONFIG_SND_SOC_BD28623 is not set # CONFIG_SND_SOC_BT_SCO is not set # CONFIG_SND_SOC_CHV3_CODEC is not set # CONFIG_SND_SOC_CROS_EC_CODEC is not set # CONFIG_SND_SOC_CS35L32 is not set # CONFIG_SND_SOC_CS35L33 is not set # CONFIG_SND_SOC_CS35L34 is not set # CONFIG_SND_SOC_CS35L35 is not set # CONFIG_SND_SOC_CS35L36 is not set # CONFIG_SND_SOC_CS35L41_SPI is not set # CONFIG_SND_SOC_CS35L41_I2C is not set # CONFIG_SND_SOC_CS35L45_SPI is not set # CONFIG_SND_SOC_CS35L45_I2C is not set # CONFIG_SND_SOC_CS35L56_I2C is not set # CONFIG_SND_SOC_CS35L56_SPI is not set # CONFIG_SND_SOC_CS35L56_SDW is not set # CONFIG_SND_SOC_CS42L42 is not set # CONFIG_SND_SOC_CS42L42_SDW is not set # CONFIG_SND_SOC_CS42L51_I2C is not set # CONFIG_SND_SOC_CS42L52 is not set # CONFIG_SND_SOC_CS42L56 is not set # CONFIG_SND_SOC_CS42L73 is not set # CONFIG_SND_SOC_CS42L83 is not set # CONFIG_SND_SOC_CS42L84 is not set # CONFIG_SND_SOC_CS4234 is not set # CONFIG_SND_SOC_CS4265 is not set # CONFIG_SND_SOC_CS4270 is not set # CONFIG_SND_SOC_CS4271_I2C is not set # CONFIG_SND_SOC_CS4271_SPI is not set # CONFIG_SND_SOC_CS42XX8_I2C is not set # CONFIG_SND_SOC_CS43130 is not set # CONFIG_SND_SOC_CS4341 is not set # CONFIG_SND_SOC_CS4349 is not set # CONFIG_SND_SOC_CS48L32 is not set # CONFIG_SND_SOC_CS53L30 is not set # CONFIG_SND_SOC_CS530X_I2C is not set # CONFIG_SND_SOC_CS530X_SPI is not set # CONFIG_SND_SOC_CX2072X is not set # CONFIG_SND_SOC_DA7213 is not set # CONFIG_SND_SOC_DMIC is not set # CONFIG_SND_SOC_ES7134 is not set # CONFIG_SND_SOC_ES7241 is not set # CONFIG_SND_SOC_ES8311 is not set # CONFIG_SND_SOC_ES8316 is not set # CONFIG_SND_SOC_ES8323 is not set # CONFIG_SND_SOC_ES8326 is not set # CONFIG_SND_SOC_ES8328_I2C is not set # CONFIG_SND_SOC_ES8328_SPI is not set # CONFIG_SND_SOC_ES8375 is not set # CONFIG_SND_SOC_ES8389 is not set # CONFIG_SND_SOC_FS210X is not set # CONFIG_SND_SOC_GTM601 is not set # CONFIG_SND_SOC_HDA is not set # CONFIG_SND_SOC_ICS43432 is not set # CONFIG_SND_SOC_IDT821034 is not set # CONFIG_SND_SOC_MAX98088 is not set # CONFIG_SND_SOC_MAX98090 is not set # CONFIG_SND_SOC_MAX98357A is not set # CONFIG_SND_SOC_MAX98504 is not set # CONFIG_SND_SOC_MAX9867 is not set # CONFIG_SND_SOC_MAX98927 is not set # CONFIG_SND_SOC_MAX98520 is not set # CONFIG_SND_SOC_MAX98363 is not set # CONFIG_SND_SOC_MAX98373_I2C is not set # CONFIG_SND_SOC_MAX98373_SDW is not set # CONFIG_SND_SOC_MAX98388 is not set # CONFIG_SND_SOC_MAX98390 is not set # CONFIG_SND_SOC_MAX98396 is not set # CONFIG_SND_SOC_MAX9860 is not set # CONFIG_SND_SOC_MSM8916_WCD_DIGITAL is not set # CONFIG_SND_SOC_PCM1681 is not set # CONFIG_SND_SOC_PCM1754 is not set # CONFIG_SND_SOC_PCM1789_I2C is not set # CONFIG_SND_SOC_PCM179X_I2C is not set # CONFIG_SND_SOC_PCM179X_SPI is not set # CONFIG_SND_SOC_PCM186X_I2C is not set # CONFIG_SND_SOC_PCM186X_SPI is not set # CONFIG_SND_SOC_PCM3060_I2C is not set # CONFIG_SND_SOC_PCM3060_SPI is not set # CONFIG_SND_SOC_PCM3168A_I2C is not set # CONFIG_SND_SOC_PCM3168A_SPI is not set # CONFIG_SND_SOC_PCM5102A is not set # CONFIG_SND_SOC_PCM512x_I2C is not set # CONFIG_SND_SOC_PCM512x_SPI is not set # CONFIG_SND_SOC_PCM6240 is not set # CONFIG_SND_SOC_PEB2466 is not set # CONFIG_SND_SOC_PM4125_SDW is not set # CONFIG_SND_SOC_RT1017_SDCA_SDW is not set # CONFIG_SND_SOC_RT1308_SDW is not set # CONFIG_SND_SOC_RT1316_SDW is not set # CONFIG_SND_SOC_RT1318_SDW is not set # CONFIG_SND_SOC_RT1320_SDW is not set # CONFIG_SND_SOC_RT5575 is not set # CONFIG_SND_SOC_RT5616 is not set # CONFIG_SND_SOC_RT5631 is not set # CONFIG_SND_SOC_RT5640 is not set # CONFIG_SND_SOC_RT5659 is not set # CONFIG_SND_SOC_RT5682_SDW is not set # CONFIG_SND_SOC_RT700_SDW is not set # CONFIG_SND_SOC_RT711_SDW is not set # CONFIG_SND_SOC_RT711_SDCA_SDW is not set # CONFIG_SND_SOC_RT712_SDCA_SDW is not set # CONFIG_SND_SOC_RT712_SDCA_DMIC_SDW is not set # CONFIG_SND_SOC_RT721_SDCA_SDW is not set # CONFIG_SND_SOC_RT722_SDCA_SDW is not set # CONFIG_SND_SOC_RT715_SDW is not set # CONFIG_SND_SOC_RT715_SDCA_SDW is not set # CONFIG_SND_SOC_RT9120 is not set # CONFIG_SND_SOC_RT9123 is not set # CONFIG_SND_SOC_RT9123P is not set # CONFIG_SND_SOC_RTQ9124 is not set # CONFIG_SND_SOC_RTQ9128 is not set # CONFIG_SND_SOC_SDW_MOCKUP is not set # CONFIG_SND_SOC_SGTL5000 is not set # CONFIG_SND_SOC_SIMPLE_AMPLIFIER is not set # CONFIG_SND_SOC_SIMPLE_MUX is not set # CONFIG_SND_SOC_SMA1303 is not set # CONFIG_SND_SOC_SMA1307 is not set # CONFIG_SND_SOC_SPDIF is not set # CONFIG_SND_SOC_SRC4XXX_I2C is not set # CONFIG_SND_SOC_SSM2305 is not set # CONFIG_SND_SOC_SSM2518 is not set # CONFIG_SND_SOC_SSM2602_SPI is not set # CONFIG_SND_SOC_SSM2602_I2C is not set # CONFIG_SND_SOC_SSM3515 is not set # CONFIG_SND_SOC_SSM4567 is not set # CONFIG_SND_SOC_STA32X is not set # CONFIG_SND_SOC_STA350 is not set # CONFIG_SND_SOC_STI_SAS is not set # CONFIG_SND_SOC_TAS2552 is not set # CONFIG_SND_SOC_TAS2562 is not set # CONFIG_SND_SOC_TAS2764 is not set # CONFIG_SND_SOC_TAS2770 is not set # CONFIG_SND_SOC_TAS2780 is not set # CONFIG_SND_SOC_TAS2781_I2C is not set # CONFIG_SND_SOC_TAS5086 is not set # CONFIG_SND_SOC_TAS571X is not set # CONFIG_SND_SOC_TAS5720 is not set # CONFIG_SND_SOC_TAS5805M is not set # CONFIG_SND_SOC_TAS6424 is not set # CONFIG_SND_SOC_TDA7419 is not set # CONFIG_SND_SOC_TFA9879 is not set # CONFIG_SND_SOC_TFA989X is not set # CONFIG_SND_SOC_TLV320ADC3XXX is not set # CONFIG_SND_SOC_TLV320AIC23_I2C is not set # CONFIG_SND_SOC_TLV320AIC23_SPI is not set # CONFIG_SND_SOC_TLV320AIC31XX is not set # CONFIG_SND_SOC_TLV320AIC32X4_I2C is not set # CONFIG_SND_SOC_TLV320AIC32X4_SPI is not set # CONFIG_SND_SOC_TLV320AIC3X_I2C is not set # CONFIG_SND_SOC_TLV320AIC3X_SPI is not set # CONFIG_SND_SOC_TLV320ADCX140 is not set # CONFIG_SND_SOC_TS3A227E is not set # CONFIG_SND_SOC_TSCS42XX is not set # CONFIG_SND_SOC_TSCS454 is not set # CONFIG_SND_SOC_UDA1334 is not set # CONFIG_SND_SOC_UDA1342 is not set # CONFIG_SND_SOC_UDA1380 is not set # CONFIG_SND_SOC_WCD937X_SDW is not set # CONFIG_SND_SOC_WCD938X_SDW is not set # CONFIG_SND_SOC_WCD939X_SDW is not set # CONFIG_SND_SOC_WM8510 is not set # CONFIG_SND_SOC_WM8523 is not set # CONFIG_SND_SOC_WM8524 is not set # CONFIG_SND_SOC_WM8580 is not set # CONFIG_SND_SOC_WM8711 is not set # CONFIG_SND_SOC_WM8728 is not set # CONFIG_SND_SOC_WM8731_I2C is not set # CONFIG_SND_SOC_WM8731_SPI is not set # CONFIG_SND_SOC_WM8737 is not set # CONFIG_SND_SOC_WM8741 is not set # CONFIG_SND_SOC_WM8750 is not set # CONFIG_SND_SOC_WM8753 is not set # CONFIG_SND_SOC_WM8770 is not set # CONFIG_SND_SOC_WM8776 is not set # CONFIG_SND_SOC_WM8782 is not set # CONFIG_SND_SOC_WM8804_I2C is not set # CONFIG_SND_SOC_WM8804_SPI is not set # CONFIG_SND_SOC_WM8903 is not set # CONFIG_SND_SOC_WM8904 is not set # CONFIG_SND_SOC_WM8940 is not set # CONFIG_SND_SOC_WM8960 is not set # CONFIG_SND_SOC_WM8961 is not set # CONFIG_SND_SOC_WM8962 is not set # CONFIG_SND_SOC_WM8974 is not set # CONFIG_SND_SOC_WM8978 is not set # CONFIG_SND_SOC_WM8985 is not set # CONFIG_SND_SOC_WSA881X is not set # CONFIG_SND_SOC_WSA883X is not set # CONFIG_SND_SOC_WSA884X is not set # CONFIG_SND_SOC_ZL38060 is not set # CONFIG_SND_SOC_MAX9759 is not set # CONFIG_SND_SOC_MT6351 is not set # CONFIG_SND_SOC_MT6357 is not set # CONFIG_SND_SOC_MT6358 is not set # CONFIG_SND_SOC_MT6660 is not set # CONFIG_SND_SOC_NAU8315 is not set # CONFIG_SND_SOC_NAU8325 is not set # CONFIG_SND_SOC_NAU8540 is not set # CONFIG_SND_SOC_NAU8810 is not set # CONFIG_SND_SOC_NAU8821 is not set # CONFIG_SND_SOC_NAU8822 is not set # CONFIG_SND_SOC_NAU8824 is not set # CONFIG_SND_SOC_NTP8918 is not set # CONFIG_SND_SOC_NTP8835 is not set # CONFIG_SND_SOC_TPA6130A2 is not set # CONFIG_SND_SOC_LPASS_WSA_MACRO is not set # CONFIG_SND_SOC_LPASS_VA_MACRO is not set # CONFIG_SND_SOC_LPASS_RX_MACRO is not set # CONFIG_SND_SOC_LPASS_TX_MACRO is not set # end of CODEC drivers # # Generic drivers # # CONFIG_SND_SIMPLE_CARD is not set # CONFIG_SND_AUDIO_GRAPH_CARD is not set # CONFIG_SND_AUDIO_GRAPH_CARD2 is not set # CONFIG_SND_TEST_COMPONENT is not set # end of Generic drivers CONFIG_SND_X86=y # CONFIG_HDMI_LPE_AUDIO is not set # CONFIG_SND_VIRTIO is not set CONFIG_HID_SUPPORT=y CONFIG_HID=y CONFIG_HID_BATTERY_STRENGTH=y CONFIG_HIDRAW=y CONFIG_UHID=y CONFIG_HID_GENERIC=y # CONFIG_HID_HAPTIC is not set # # Special HID drivers # CONFIG_HID_A4TECH=y CONFIG_HID_ACCUTOUCH=y CONFIG_HID_ACRUX=y CONFIG_HID_ACRUX_FF=y CONFIG_HID_APPLE=y CONFIG_HID_APPLEIR=y # CONFIG_HID_APPLETB_BL is not set # CONFIG_HID_APPLETB_KBD is not set CONFIG_HID_ASUS=y CONFIG_HID_AUREAL=y CONFIG_HID_BELKIN=y CONFIG_HID_BETOP_FF=y CONFIG_HID_BIGBEN_FF=y CONFIG_HID_CHERRY=y CONFIG_HID_CHICONY=y CONFIG_HID_CORSAIR=y CONFIG_HID_COUGAR=y CONFIG_HID_MACALLY=y CONFIG_HID_PRODIKEYS=y CONFIG_HID_CMEDIA=y CONFIG_HID_CP2112=y CONFIG_HID_CREATIVE_SB0540=y CONFIG_HID_CYPRESS=y CONFIG_HID_DRAGONRISE=y CONFIG_DRAGONRISE_FF=y CONFIG_HID_EMS_FF=y CONFIG_HID_ELAN=y CONFIG_HID_ELECOM=y CONFIG_HID_ELO=y CONFIG_HID_EVISION=y CONFIG_HID_EZKEY=y CONFIG_HID_FT260=y CONFIG_HID_GEMBIRD=y CONFIG_HID_GFRM=y CONFIG_HID_GLORIOUS=y CONFIG_HID_HOLTEK=y CONFIG_HOLTEK_FF=y CONFIG_HID_VIVALDI_COMMON=y # CONFIG_HID_GOODIX_SPI is not set CONFIG_HID_GOOGLE_HAMMER=y CONFIG_HID_GOOGLE_STADIA_FF=y CONFIG_HID_VIVALDI=y CONFIG_HID_GT683R=y CONFIG_HID_KEYTOUCH=y CONFIG_HID_KYE=y # CONFIG_HID_KYSONA is not set CONFIG_HID_UCLOGIC=y CONFIG_HID_WALTOP=y CONFIG_HID_VIEWSONIC=y CONFIG_HID_VRC2=y CONFIG_HID_XIAOMI=y CONFIG_HID_GYRATION=y CONFIG_HID_ICADE=y CONFIG_HID_ITE=y CONFIG_HID_JABRA=y CONFIG_HID_TWINHAN=y CONFIG_HID_KENSINGTON=y CONFIG_HID_LCPOWER=y CONFIG_HID_LED=y CONFIG_HID_LENOVO=y # CONFIG_HID_LENOVO_GO is not set # CONFIG_HID_LENOVO_GO_S is not set CONFIG_HID_LETSKETCH=y CONFIG_HID_LOGITECH=y CONFIG_HID_LOGITECH_DJ=y CONFIG_HID_LOGITECH_HIDPP=y CONFIG_LOGITECH_FF=y CONFIG_LOGIRUMBLEPAD2_FF=y CONFIG_LOGIG940_FF=y CONFIG_LOGIWHEELS_FF=y CONFIG_HID_MAGICMOUSE=y CONFIG_HID_MALTRON=y CONFIG_HID_MAYFLASH=y CONFIG_HID_MEGAWORLD_FF=y CONFIG_HID_REDRAGON=y CONFIG_HID_MICROSOFT=y CONFIG_HID_MONTEREY=y CONFIG_HID_MULTITOUCH=y CONFIG_HID_NINTENDO=y CONFIG_NINTENDO_FF=y CONFIG_HID_NTI=y CONFIG_HID_NTRIG=y CONFIG_HID_NVIDIA_SHIELD=y CONFIG_NVIDIA_SHIELD_FF=y CONFIG_HID_ORTEK=y CONFIG_HID_PANTHERLORD=y CONFIG_PANTHERLORD_FF=y CONFIG_HID_PENMOUNT=y CONFIG_HID_PETALYNX=y CONFIG_HID_PICOLCD=y CONFIG_HID_PICOLCD_FB=y CONFIG_HID_PICOLCD_BACKLIGHT=y CONFIG_HID_PICOLCD_LCD=y CONFIG_HID_PICOLCD_LEDS=y CONFIG_HID_PICOLCD_CIR=y CONFIG_HID_PLANTRONICS=y CONFIG_HID_PLAYSTATION=y CONFIG_PLAYSTATION_FF=y CONFIG_HID_PXRC=y # CONFIG_HID_RAPOO is not set CONFIG_HID_RAZER=y CONFIG_HID_PRIMAX=y CONFIG_HID_RETRODE=y CONFIG_HID_ROCCAT=y CONFIG_HID_SAITEK=y CONFIG_HID_SAMSUNG=y CONFIG_HID_SEMITEK=y CONFIG_HID_SIGMAMICRO=y CONFIG_HID_SONY=y CONFIG_SONY_FF=y CONFIG_HID_SPEEDLINK=y CONFIG_HID_STEAM=y CONFIG_STEAM_FF=y CONFIG_HID_STEELSERIES=y CONFIG_HID_SUNPLUS=y CONFIG_HID_RMI=y CONFIG_HID_GREENASIA=y CONFIG_GREENASIA_FF=y CONFIG_HID_SMARTJOYPLUS=y CONFIG_SMARTJOYPLUS_FF=y CONFIG_HID_TIVO=y CONFIG_HID_TOPSEED=y CONFIG_HID_TOPRE=y CONFIG_HID_THINGM=y CONFIG_HID_THRUSTMASTER=y CONFIG_THRUSTMASTER_FF=y CONFIG_HID_UDRAW_PS3=y CONFIG_HID_U2FZERO=y # CONFIG_HID_UNIVERSAL_PIDFF is not set CONFIG_HID_WACOM=y CONFIG_HID_WIIMOTE=y # CONFIG_HID_WINWING is not set CONFIG_HID_XINMO=y CONFIG_HID_ZEROPLUS=y CONFIG_ZEROPLUS_FF=y CONFIG_HID_ZYDACRON=y CONFIG_HID_SENSOR_HUB=y CONFIG_HID_SENSOR_CUSTOM_SENSOR=y CONFIG_HID_ALPS=y CONFIG_HID_MCP2200=y CONFIG_HID_MCP2221=y # CONFIG_HID_HUAWEI is not set # end of Special HID drivers # # HID-BPF support # # end of HID-BPF support CONFIG_I2C_HID=y CONFIG_I2C_HID_ACPI=y CONFIG_I2C_HID_OF=y # CONFIG_I2C_HID_OF_ELAN is not set # CONFIG_I2C_HID_OF_GOODIX is not set CONFIG_I2C_HID_CORE=y # # Intel ISH HID support # CONFIG_INTEL_ISH_HID=y CONFIG_INTEL_ISH_FIRMWARE_DOWNLOADER=y # end of Intel ISH HID support # # AMD SFH HID Support # CONFIG_AMD_SFH_HID=y # end of AMD SFH HID Support # # Surface System Aggregator Module HID support # CONFIG_SURFACE_HID=y CONFIG_SURFACE_KBD=y # end of Surface System Aggregator Module HID support CONFIG_SURFACE_HID_CORE=y # # Intel THC HID Support # # CONFIG_INTEL_THC_HID is not set # end of Intel THC HID Support # # USB HID support # CONFIG_USB_HID=y CONFIG_HID_PID=y CONFIG_USB_HIDDEV=y # end of USB HID support CONFIG_USB_OHCI_LITTLE_ENDIAN=y CONFIG_USB_SUPPORT=y CONFIG_USB_COMMON=y CONFIG_USB_LED_TRIG=y CONFIG_USB_ULPI_BUS=y CONFIG_USB_CONN_GPIO=y CONFIG_USB_ARCH_HAS_HCD=y CONFIG_USB=y CONFIG_USB_PCI=y CONFIG_USB_PCI_AMD=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y # # Miscellaneous USB options # CONFIG_USB_DEFAULT_PERSIST=y # CONFIG_USB_FEW_INIT_RETRIES is not set CONFIG_USB_DYNAMIC_MINORS=y CONFIG_USB_OTG=y # CONFIG_USB_OTG_PRODUCTLIST is not set # CONFIG_USB_OTG_DISABLE_EXTERNAL_HUB is not set CONFIG_USB_OTG_FSM=y CONFIG_USB_LEDS_TRIGGER_USBPORT=y CONFIG_USB_AUTOSUSPEND_DELAY=2 CONFIG_USB_DEFAULT_AUTHORIZATION_MODE=1 CONFIG_USB_MON=y # # USB Host Controller Drivers # CONFIG_USB_C67X00_HCD=y CONFIG_USB_XHCI_HCD=y CONFIG_USB_XHCI_DBGCAP=y CONFIG_USB_XHCI_PCI=y CONFIG_USB_XHCI_PCI_RENESAS=y CONFIG_USB_XHCI_PLATFORM=y # CONFIG_USB_XHCI_SIDEBAND is not set CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_ROOT_HUB_TT=y CONFIG_USB_EHCI_TT_NEWSCHED=y CONFIG_USB_EHCI_PCI=y CONFIG_USB_EHCI_FSL=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OXU210HP_HCD=y CONFIG_USB_ISP116X_HCD=y CONFIG_USB_MAX3421_HCD=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PCI=y # CONFIG_USB_OHCI_HCD_SSB is not set CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_UHCI_HCD=y CONFIG_USB_SL811_HCD=y CONFIG_USB_SL811_HCD_ISO=y CONFIG_USB_SL811_CS=y CONFIG_USB_R8A66597_HCD=y CONFIG_USB_HCD_BCMA=y CONFIG_USB_HCD_SSB=y # CONFIG_USB_HCD_TEST_MODE is not set # # USB Device Class drivers # CONFIG_USB_ACM=y CONFIG_USB_PRINTER=y CONFIG_USB_WDM=y CONFIG_USB_TMC=y # # NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed; see USB_STORAGE Help for more info # CONFIG_USB_STORAGE=y # CONFIG_USB_STORAGE_DEBUG is not set CONFIG_USB_STORAGE_REALTEK=y CONFIG_REALTEK_AUTOPM=y CONFIG_USB_STORAGE_DATAFAB=y CONFIG_USB_STORAGE_FREECOM=y CONFIG_USB_STORAGE_ISD200=y CONFIG_USB_STORAGE_USBAT=y CONFIG_USB_STORAGE_SDDR09=y CONFIG_USB_STORAGE_SDDR55=y CONFIG_USB_STORAGE_JUMPSHOT=y CONFIG_USB_STORAGE_ALAUDA=y CONFIG_USB_STORAGE_ONETOUCH=y CONFIG_USB_STORAGE_KARMA=y CONFIG_USB_STORAGE_CYPRESS_ATACB=y CONFIG_USB_STORAGE_ENE_UB6250=y CONFIG_USB_UAS=y # # USB Imaging devices # CONFIG_USB_MDC800=y CONFIG_USB_MICROTEK=y CONFIG_USBIP_CORE=y CONFIG_USBIP_VHCI_HCD=y CONFIG_USBIP_VHCI_HC_PORTS=8 CONFIG_USBIP_VHCI_NR_HCS=16 CONFIG_USBIP_HOST=y CONFIG_USBIP_VUDC=y # CONFIG_USBIP_DEBUG is not set # # USB dual-mode controller drivers # CONFIG_USB_CDNS_SUPPORT=y CONFIG_USB_CDNS_HOST=y CONFIG_USB_CDNS3=y CONFIG_USB_CDNS3_GADGET=y CONFIG_USB_CDNS3_HOST=y CONFIG_USB_CDNS3_PCI_WRAP=y CONFIG_USB_CDNSP_PCI=y CONFIG_USB_CDNSP_GADGET=y CONFIG_USB_CDNSP_HOST=y CONFIG_USB_MUSB_HDRC=y # CONFIG_USB_MUSB_HOST is not set # CONFIG_USB_MUSB_GADGET is not set CONFIG_USB_MUSB_DUAL_ROLE=y # # Platform Glue Layer # # # MUSB DMA mode # CONFIG_MUSB_PIO_ONLY=y CONFIG_USB_DWC3=y CONFIG_USB_DWC3_ULPI=y # CONFIG_USB_DWC3_HOST is not set # CONFIG_USB_DWC3_GADGET is not set CONFIG_USB_DWC3_DUAL_ROLE=y # # Platform Glue Driver Support # CONFIG_USB_DWC3_PCI=y CONFIG_USB_DWC3_HAPS=y CONFIG_USB_DWC3_OF_SIMPLE=y # CONFIG_USB_DWC3_GENERIC_PLAT is not set # CONFIG_USB_DWC3_GOOGLE is not set CONFIG_USB_DWC2=y CONFIG_USB_DWC2_HOST=y # # Gadget/Dual-role mode requires USB Gadget support to be enabled # # CONFIG_USB_DWC2_PERIPHERAL is not set # CONFIG_USB_DWC2_DUAL_ROLE is not set CONFIG_USB_DWC2_PCI=y # CONFIG_USB_DWC2_DEBUG is not set # CONFIG_USB_DWC2_TRACK_MISSED_SOFS is not set CONFIG_USB_CHIPIDEA=y CONFIG_USB_CHIPIDEA_UDC=y CONFIG_USB_CHIPIDEA_HOST=y CONFIG_USB_CHIPIDEA_PCI=y CONFIG_USB_CHIPIDEA_MSM=y CONFIG_USB_CHIPIDEA_NPCM=y # CONFIG_USB_CHIPIDEA_IMX is not set CONFIG_USB_CHIPIDEA_GENERIC=y # CONFIG_USB_CHIPIDEA_TEGRA is not set CONFIG_USB_ISP1760=y CONFIG_USB_ISP1760_HCD=y CONFIG_USB_ISP1761_UDC=y # CONFIG_USB_ISP1760_HOST_ROLE is not set # CONFIG_USB_ISP1760_GADGET_ROLE is not set CONFIG_USB_ISP1760_DUAL_ROLE=y # # USB port drivers # CONFIG_USB_SERIAL=y CONFIG_USB_SERIAL_CONSOLE=y CONFIG_USB_SERIAL_GENERIC=y CONFIG_USB_SERIAL_SIMPLE=y CONFIG_USB_SERIAL_AIRCABLE=y CONFIG_USB_SERIAL_ARK3116=y CONFIG_USB_SERIAL_BELKIN=y CONFIG_USB_SERIAL_CH341=y CONFIG_USB_SERIAL_WHITEHEAT=y CONFIG_USB_SERIAL_DIGI_ACCELEPORT=y CONFIG_USB_SERIAL_CP210X=y CONFIG_USB_SERIAL_CYPRESS_M8=y CONFIG_USB_SERIAL_EMPEG=y CONFIG_USB_SERIAL_FTDI_SIO=y CONFIG_USB_SERIAL_VISOR=y CONFIG_USB_SERIAL_IPAQ=y CONFIG_USB_SERIAL_IR=y CONFIG_USB_SERIAL_EDGEPORT=y CONFIG_USB_SERIAL_EDGEPORT_TI=y CONFIG_USB_SERIAL_F81232=y CONFIG_USB_SERIAL_F8153X=y CONFIG_USB_SERIAL_GARMIN=y CONFIG_USB_SERIAL_IPW=y CONFIG_USB_SERIAL_IUU=y CONFIG_USB_SERIAL_KEYSPAN_PDA=y CONFIG_USB_SERIAL_KEYSPAN=y CONFIG_USB_SERIAL_KLSI=y CONFIG_USB_SERIAL_KOBIL_SCT=y CONFIG_USB_SERIAL_MCT_U232=y CONFIG_USB_SERIAL_METRO=y CONFIG_USB_SERIAL_MOS7720=y CONFIG_USB_SERIAL_MOS7715_PARPORT=y CONFIG_USB_SERIAL_MOS7840=y CONFIG_USB_SERIAL_MXUPORT=y CONFIG_USB_SERIAL_NAVMAN=y CONFIG_USB_SERIAL_PL2303=y CONFIG_USB_SERIAL_OTI6858=y CONFIG_USB_SERIAL_QCAUX=y CONFIG_USB_SERIAL_QUALCOMM=y CONFIG_USB_SERIAL_SPCP8X5=y CONFIG_USB_SERIAL_SAFE=y # CONFIG_USB_SERIAL_SAFE_PADDED is not set CONFIG_USB_SERIAL_SIERRAWIRELESS=y CONFIG_USB_SERIAL_SYMBOL=y CONFIG_USB_SERIAL_TI=y CONFIG_USB_SERIAL_CYBERJACK=y CONFIG_USB_SERIAL_WWAN=y CONFIG_USB_SERIAL_OPTION=y CONFIG_USB_SERIAL_OMNINET=y CONFIG_USB_SERIAL_OPTICON=y CONFIG_USB_SERIAL_XSENS_MT=y CONFIG_USB_SERIAL_WISHBONE=y CONFIG_USB_SERIAL_SSU100=y CONFIG_USB_SERIAL_QT2=y CONFIG_USB_SERIAL_UPD78F0730=y CONFIG_USB_SERIAL_XR=y CONFIG_USB_SERIAL_DEBUG=y # # USB Miscellaneous drivers # CONFIG_USB_USS720=y CONFIG_USB_EMI62=y CONFIG_USB_EMI26=y CONFIG_USB_ADUTUX=y CONFIG_USB_SEVSEG=y CONFIG_USB_LEGOTOWER=y CONFIG_USB_LCD=y CONFIG_USB_CYPRESS_CY7C63=y CONFIG_USB_CYTHERM=y CONFIG_USB_IDMOUSE=y CONFIG_USB_APPLEDISPLAY=y CONFIG_APPLE_MFI_FASTCHARGE=y CONFIG_USB_LJCA=y # CONFIG_USB_USBIO is not set CONFIG_USB_SISUSBVGA=y CONFIG_USB_LD=y CONFIG_USB_TRANCEVIBRATOR=y CONFIG_USB_IOWARRIOR=y CONFIG_USB_TEST=y CONFIG_USB_EHSET_TEST_FIXTURE=y CONFIG_USB_ISIGHTFW=y CONFIG_USB_YUREX=y CONFIG_USB_EZUSB_FX2=y CONFIG_USB_HUB_USB251XB=y CONFIG_USB_HSIC_USB3503=y CONFIG_USB_HSIC_USB4604=y CONFIG_USB_LINK_LAYER_TEST=y CONFIG_USB_CHAOSKEY=y # CONFIG_USB_ONBOARD_DEV is not set CONFIG_USB_ATM=y CONFIG_USB_SPEEDTOUCH=y CONFIG_USB_CXACRU=y CONFIG_USB_UEAGLEATM=y CONFIG_USB_XUSBATM=y # # USB Physical Layer drivers # CONFIG_USB_PHY=y CONFIG_NOP_USB_XCEIV=y CONFIG_TAHVO_USB=y CONFIG_TAHVO_USB_HOST_BY_DEFAULT=y CONFIG_USB_ISP1301=y # end of USB Physical Layer drivers CONFIG_USB_GADGET=y # CONFIG_USB_GADGET_DEBUG is not set CONFIG_USB_GADGET_DEBUG_FILES=y CONFIG_USB_GADGET_DEBUG_FS=y CONFIG_USB_GADGET_VBUS_DRAW=2 CONFIG_USB_GADGET_STORAGE_NUM_BUFFERS=2 CONFIG_U_SERIAL_CONSOLE=y # # USB Peripheral Controller # CONFIG_USB_GR_UDC=y CONFIG_USB_R8A66597=y CONFIG_USB_PXA27X=y CONFIG_USB_SNP_CORE=y # CONFIG_USB_SNP_UDC_PLAT is not set # CONFIG_USB_M66592 is not set CONFIG_USB_BDC_UDC=y CONFIG_USB_AMD5536UDC=y CONFIG_USB_NET2280=y CONFIG_USB_GOKU=y CONFIG_USB_EG20T=y # CONFIG_USB_GADGET_XILINX is not set CONFIG_USB_MAX3420_UDC=y CONFIG_USB_CDNS2_UDC=y # CONFIG_USB_DUMMY_HCD is not set # end of USB Peripheral Controller CONFIG_USB_LIBCOMPOSITE=y CONFIG_USB_F_ACM=y CONFIG_USB_F_SS_LB=y CONFIG_USB_U_SERIAL=y CONFIG_USB_U_ETHER=y CONFIG_USB_U_AUDIO=y CONFIG_USB_F_SERIAL=y CONFIG_USB_F_OBEX=y CONFIG_USB_F_NCM=y CONFIG_USB_F_ECM=y CONFIG_USB_F_PHONET=y CONFIG_USB_F_EEM=y CONFIG_USB_F_SUBSET=y CONFIG_USB_F_RNDIS=y CONFIG_USB_F_MASS_STORAGE=y CONFIG_USB_F_FS=y CONFIG_USB_F_UAC1=y CONFIG_USB_F_UAC1_LEGACY=y CONFIG_USB_F_UAC2=y CONFIG_USB_F_UVC=y CONFIG_USB_F_MIDI=y CONFIG_USB_F_MIDI2=y CONFIG_USB_F_HID=y CONFIG_USB_F_PRINTER=y CONFIG_USB_F_TCM=y CONFIG_USB_CONFIGFS=y CONFIG_USB_CONFIGFS_SERIAL=y CONFIG_USB_CONFIGFS_ACM=y CONFIG_USB_CONFIGFS_OBEX=y CONFIG_USB_CONFIGFS_NCM=y CONFIG_USB_CONFIGFS_ECM=y CONFIG_USB_CONFIGFS_ECM_SUBSET=y CONFIG_USB_CONFIGFS_RNDIS=y CONFIG_USB_CONFIGFS_EEM=y CONFIG_USB_CONFIGFS_PHONET=y CONFIG_USB_CONFIGFS_MASS_STORAGE=y CONFIG_USB_CONFIGFS_F_LB_SS=y CONFIG_USB_CONFIGFS_F_FS=y CONFIG_USB_CONFIGFS_F_UAC1=y CONFIG_USB_CONFIGFS_F_UAC1_LEGACY=y CONFIG_USB_CONFIGFS_F_UAC2=y CONFIG_USB_CONFIGFS_F_MIDI=y CONFIG_USB_CONFIGFS_F_MIDI2=y CONFIG_USB_CONFIGFS_F_HID=y CONFIG_USB_CONFIGFS_F_UVC=y CONFIG_USB_CONFIGFS_F_PRINTER=y CONFIG_USB_CONFIGFS_F_TCM=y # # USB Gadget precomposed configurations # # CONFIG_USB_ZERO is not set # CONFIG_USB_AUDIO is not set # CONFIG_USB_ETH is not set # CONFIG_USB_G_NCM is not set CONFIG_USB_GADGETFS=y # CONFIG_USB_FUNCTIONFS is not set # CONFIG_USB_MASS_STORAGE is not set # CONFIG_USB_GADGET_TARGET is not set # CONFIG_USB_G_SERIAL is not set # CONFIG_USB_MIDI_GADGET is not set # CONFIG_USB_G_PRINTER is not set # CONFIG_USB_CDC_COMPOSITE is not set # CONFIG_USB_G_NOKIA is not set # CONFIG_USB_G_ACM_MS is not set # CONFIG_USB_G_MULTI is not set # CONFIG_USB_G_HID is not set # CONFIG_USB_G_DBGP is not set # CONFIG_USB_G_WEBCAM is not set CONFIG_USB_RAW_GADGET=y # end of USB Gadget precomposed configurations CONFIG_TYPEC=y CONFIG_TYPEC_TCPM=y CONFIG_TYPEC_TCPCI=y CONFIG_TYPEC_RT1711H=y CONFIG_TYPEC_MT6360=y CONFIG_TYPEC_TCPCI_MT6370=y CONFIG_TYPEC_TCPCI_MAXIM=y CONFIG_TYPEC_FUSB302=y CONFIG_TYPEC_WCOVE=y CONFIG_TYPEC_UCSI=y CONFIG_UCSI_CCG=y CONFIG_UCSI_ACPI=y CONFIG_UCSI_STM32G0=y # CONFIG_CROS_EC_UCSI is not set CONFIG_TYPEC_TPS6598X=y CONFIG_TYPEC_ANX7411=y CONFIG_TYPEC_RT1719=y CONFIG_TYPEC_HD3SS3220=y CONFIG_TYPEC_STUSB160X=y CONFIG_TYPEC_WUSB3801=y # # USB Type-C Multiplexer/DeMultiplexer Switch support # CONFIG_TYPEC_MUX_FSA4480=y CONFIG_TYPEC_MUX_GPIO_SBU=y CONFIG_TYPEC_MUX_PI3USB30532=y CONFIG_TYPEC_MUX_INTEL_PMC=y # CONFIG_TYPEC_MUX_IT5205 is not set CONFIG_TYPEC_MUX_NB7VPQ904M=y # CONFIG_TYPEC_MUX_PS883X is not set CONFIG_TYPEC_MUX_PTN36502=y # CONFIG_TYPEC_MUX_TUSB1046 is not set CONFIG_TYPEC_MUX_WCD939X_USBSS=y # end of USB Type-C Multiplexer/DeMultiplexer Switch support # # USB Type-C Alternate Mode drivers # CONFIG_TYPEC_DP_ALTMODE=y CONFIG_TYPEC_NVIDIA_ALTMODE=y # CONFIG_TYPEC_TBT_ALTMODE is not set # end of USB Type-C Alternate Mode drivers CONFIG_USB_ROLE_SWITCH=y CONFIG_USB_ROLES_INTEL_XHCI=y CONFIG_MMC=y # CONFIG_PWRSEQ_EMMC is not set # CONFIG_PWRSEQ_SD8787 is not set # CONFIG_PWRSEQ_SIMPLE is not set # CONFIG_MMC_BLOCK is not set # CONFIG_SDIO_UART is not set # CONFIG_MMC_TEST is not set # # MMC/SD/SDIO Host Controller Drivers # # CONFIG_MMC_DEBUG is not set # CONFIG_MMC_SDHCI is not set # CONFIG_MMC_WBSD is not set # CONFIG_MMC_TIFM_SD is not set # CONFIG_MMC_SPI is not set # CONFIG_MMC_SDRICOH_CS is not set # CONFIG_MMC_CB710 is not set # CONFIG_MMC_VIA_SDMMC is not set CONFIG_MMC_VUB300=y CONFIG_MMC_USHC=y # CONFIG_MMC_USDHI6ROL0 is not set CONFIG_MMC_REALTEK_USB=y # CONFIG_MMC_CQHCI is not set # CONFIG_MMC_HSQ is not set # CONFIG_MMC_TOSHIBA_PCI is not set # CONFIG_MMC_MTK is not set # CONFIG_SCSI_UFSHCD is not set CONFIG_MEMSTICK=y # CONFIG_MEMSTICK_DEBUG is not set # # MemoryStick drivers # # CONFIG_MEMSTICK_UNSAFE_RESUME is not set # CONFIG_MSPRO_BLOCK is not set # CONFIG_MS_BLOCK is not set # # MemoryStick Host Controller Drivers # # CONFIG_MEMSTICK_TIFM_MS is not set # CONFIG_MEMSTICK_JMICRON_38X is not set # CONFIG_MEMSTICK_R592 is not set CONFIG_MEMSTICK_REALTEK_USB=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y # CONFIG_LEDS_CLASS_FLASH is not set CONFIG_LEDS_CLASS_MULTICOLOR=y # CONFIG_LEDS_BRIGHTNESS_HW_CHANGED is not set # # LED drivers # # CONFIG_LEDS_AN30259A is not set # CONFIG_LEDS_APU is not set # CONFIG_LEDS_OSRAM_AMS_AS3668 is not set # CONFIG_LEDS_AW200XX is not set # CONFIG_LEDS_AW2013 is not set # CONFIG_LEDS_BCM6328 is not set # CONFIG_LEDS_BCM6358 is not set # CONFIG_LEDS_CHT_WCOVE is not set # CONFIG_LEDS_CR0014114 is not set # CONFIG_LEDS_CROS_EC is not set # CONFIG_LEDS_EL15203000 is not set # CONFIG_LEDS_LM3530 is not set # CONFIG_LEDS_LM3532 is not set # CONFIG_LEDS_LM3642 is not set # CONFIG_LEDS_LM3692X is not set # CONFIG_LEDS_PCA9532 is not set # CONFIG_LEDS_GPIO is not set # CONFIG_LEDS_LP3944 is not set # CONFIG_LEDS_LP3952 is not set # CONFIG_LEDS_LP50XX is not set # CONFIG_LEDS_LP55XX_COMMON is not set # CONFIG_LEDS_LP8860 is not set # CONFIG_LEDS_LP8864 is not set # CONFIG_LEDS_PCA955X is not set # CONFIG_LEDS_PCA963X is not set # CONFIG_LEDS_PCA995X is not set # CONFIG_LEDS_DAC124S085 is not set # CONFIG_LEDS_REGULATOR is not set # CONFIG_LEDS_BD2606MVV is not set # CONFIG_LEDS_BD2802 is not set # CONFIG_LEDS_INTEL_SS4200 is not set # CONFIG_LEDS_LT3593 is not set # CONFIG_LEDS_TCA6507 is not set # CONFIG_LEDS_TLC591XX is not set # CONFIG_LEDS_LM355x is not set # CONFIG_LEDS_IS31FL319X is not set # CONFIG_LEDS_IS31FL32XX is not set # # LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM) # # CONFIG_LEDS_BLINKM is not set # CONFIG_LEDS_SYSCON is not set # CONFIG_LEDS_MLXCPLD is not set # CONFIG_LEDS_MLXREG is not set # CONFIG_LEDS_USER is not set # CONFIG_LEDS_NIC78BX is not set # CONFIG_LEDS_SPI_BYTE is not set # CONFIG_LEDS_LM3697 is not set # CONFIG_LEDS_ST1202 is not set # CONFIG_LEDS_LGM is not set # # Flash and Torch LED drivers # # # RGB LED drivers # # CONFIG_LEDS_GROUP_MULTICOLOR is not set # CONFIG_LEDS_KTD202X is not set # CONFIG_LEDS_LP5812 is not set # CONFIG_LEDS_NCP5623 is not set # CONFIG_LEDS_MT6370_RGB is not set # # LED Triggers # CONFIG_LEDS_TRIGGERS=y # CONFIG_LEDS_TRIGGER_TIMER is not set # CONFIG_LEDS_TRIGGER_ONESHOT is not set # CONFIG_LEDS_TRIGGER_DISK is not set # CONFIG_LEDS_TRIGGER_HEARTBEAT is not set # CONFIG_LEDS_TRIGGER_BACKLIGHT is not set # CONFIG_LEDS_TRIGGER_CPU is not set # CONFIG_LEDS_TRIGGER_ACTIVITY is not set # CONFIG_LEDS_TRIGGER_GPIO is not set # CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set # # iptables trigger is under Netfilter config (LED target) # # CONFIG_LEDS_TRIGGER_TRANSIENT is not set # CONFIG_LEDS_TRIGGER_CAMERA is not set # CONFIG_LEDS_TRIGGER_PANIC is not set # CONFIG_LEDS_TRIGGER_NETDEV is not set # CONFIG_LEDS_TRIGGER_PATTERN is not set # CONFIG_LEDS_TRIGGER_TTY is not set # CONFIG_LEDS_TRIGGER_INPUT_EVENTS is not set # # Simatic LED drivers # # CONFIG_ACCESSIBILITY is not set CONFIG_INFINIBAND=y CONFIG_INFINIBAND_USER_MAD=y CONFIG_INFINIBAND_USER_ACCESS=y CONFIG_INFINIBAND_USER_MEM=y CONFIG_INFINIBAND_ON_DEMAND_PAGING=y CONFIG_INFINIBAND_ADDR_TRANS=y CONFIG_INFINIBAND_ADDR_TRANS_CONFIGFS=y CONFIG_INFINIBAND_VIRT_DMA=y # CONFIG_INFINIBAND_EFA is not set # CONFIG_INFINIBAND_ERDMA is not set CONFIG_MLX4_INFINIBAND=y # CONFIG_INFINIBAND_MTHCA is not set # CONFIG_INFINIBAND_OCRDMA is not set # CONFIG_INFINIBAND_USNIC is not set # CONFIG_INFINIBAND_VMWARE_PVRDMA is not set # CONFIG_INFINIBAND_RDMAVT is not set CONFIG_RDMA_RXE=y CONFIG_RDMA_SIW=y CONFIG_INFINIBAND_IPOIB=y CONFIG_INFINIBAND_IPOIB_CM=y CONFIG_INFINIBAND_IPOIB_DEBUG=y # CONFIG_INFINIBAND_IPOIB_DEBUG_DATA is not set CONFIG_INFINIBAND_SRP=y # CONFIG_INFINIBAND_SRPT is not set CONFIG_INFINIBAND_ISER=y CONFIG_INFINIBAND_RTRS=y CONFIG_INFINIBAND_RTRS_CLIENT=y # CONFIG_INFINIBAND_RTRS_SERVER is not set CONFIG_EDAC_ATOMIC_SCRUB=y CONFIG_EDAC_SUPPORT=y CONFIG_EDAC=y # CONFIG_EDAC_DEBUG is not set # CONFIG_EDAC_DECODE_MCE is not set # CONFIG_EDAC_SCRUB is not set # CONFIG_EDAC_ECS is not set # CONFIG_EDAC_MEM_REPAIR is not set # CONFIG_EDAC_E752X is not set # CONFIG_EDAC_I82975X is not set # CONFIG_EDAC_I3000 is not set # CONFIG_EDAC_I3200 is not set # CONFIG_EDAC_IE31200 is not set # CONFIG_EDAC_X38 is not set # CONFIG_EDAC_I5400 is not set # CONFIG_EDAC_I7CORE is not set # CONFIG_EDAC_I5100 is not set # CONFIG_EDAC_I7300 is not set # CONFIG_EDAC_SBRIDGE is not set # CONFIG_EDAC_SKX is not set # CONFIG_EDAC_I10NM is not set # CONFIG_EDAC_IMH is not set # CONFIG_EDAC_PND2 is not set # CONFIG_EDAC_IGEN6 is not set CONFIG_RTC_LIB=y CONFIG_RTC_MC146818_LIB=y CONFIG_RTC_CLASS=y # CONFIG_RTC_HCTOSYS is not set CONFIG_RTC_SYSTOHC=y CONFIG_RTC_SYSTOHC_DEVICE="rtc0" # CONFIG_RTC_DEBUG is not set CONFIG_RTC_NVMEM=y # # RTC interfaces # CONFIG_RTC_INTF_SYSFS=y CONFIG_RTC_INTF_PROC=y CONFIG_RTC_INTF_DEV=y # CONFIG_RTC_INTF_DEV_UIE_EMUL is not set # CONFIG_RTC_DRV_TEST is not set # # I2C RTC drivers # # CONFIG_RTC_DRV_ABB5ZES3 is not set # CONFIG_RTC_DRV_ABEOZ9 is not set # CONFIG_RTC_DRV_ABX80X is not set # CONFIG_RTC_DRV_DS1307 is not set # CONFIG_RTC_DRV_DS1374 is not set # CONFIG_RTC_DRV_DS1672 is not set # CONFIG_RTC_DRV_HYM8563 is not set # CONFIG_RTC_DRV_MAX6900 is not set # CONFIG_RTC_DRV_MAX31335 is not set # CONFIG_RTC_DRV_NCT3018Y is not set # CONFIG_RTC_DRV_RS5C372 is not set # CONFIG_RTC_DRV_ISL1208 is not set # CONFIG_RTC_DRV_ISL12022 is not set # CONFIG_RTC_DRV_ISL12026 is not set # CONFIG_RTC_DRV_X1205 is not set # CONFIG_RTC_DRV_PCF8523 is not set # CONFIG_RTC_DRV_PCF85363 is not set # CONFIG_RTC_DRV_PCF8563 is not set # CONFIG_RTC_DRV_PCF8583 is not set # CONFIG_RTC_DRV_M41T80 is not set # CONFIG_RTC_DRV_BQ32K is not set # CONFIG_RTC_DRV_TWL4030 is not set # CONFIG_RTC_DRV_S35390A is not set # CONFIG_RTC_DRV_FM3130 is not set # CONFIG_RTC_DRV_RX8010 is not set # CONFIG_RTC_DRV_RX8111 is not set # CONFIG_RTC_DRV_RX8581 is not set # CONFIG_RTC_DRV_RX8025 is not set # CONFIG_RTC_DRV_EM3027 is not set # CONFIG_RTC_DRV_RV3028 is not set # CONFIG_RTC_DRV_RV3032 is not set # CONFIG_RTC_DRV_RV8803 is not set # CONFIG_RTC_DRV_SD2405AL is not set # CONFIG_RTC_DRV_SD3078 is not set # # SPI RTC drivers # # CONFIG_RTC_DRV_M41T93 is not set # CONFIG_RTC_DRV_M41T94 is not set # CONFIG_RTC_DRV_DS1302 is not set # CONFIG_RTC_DRV_DS1305 is not set # CONFIG_RTC_DRV_DS1343 is not set # CONFIG_RTC_DRV_DS1347 is not set # CONFIG_RTC_DRV_DS1390 is not set # CONFIG_RTC_DRV_MAX6916 is not set # CONFIG_RTC_DRV_R9701 is not set # CONFIG_RTC_DRV_RX4581 is not set # CONFIG_RTC_DRV_RS5C348 is not set # CONFIG_RTC_DRV_MAX6902 is not set # CONFIG_RTC_DRV_PCF2123 is not set # CONFIG_RTC_DRV_MCP795 is not set CONFIG_RTC_I2C_AND_SPI=y # # SPI and I2C RTC drivers # # CONFIG_RTC_DRV_DS3232 is not set # CONFIG_RTC_DRV_PCF2127 is not set # CONFIG_RTC_DRV_PCF85063 is not set # CONFIG_RTC_DRV_RV3029C2 is not set # CONFIG_RTC_DRV_RX6110 is not set # # Platform RTC drivers # CONFIG_RTC_DRV_CMOS=y # CONFIG_RTC_DRV_DS1286 is not set # CONFIG_RTC_DRV_DS1511 is not set # CONFIG_RTC_DRV_DS1553 is not set # CONFIG_RTC_DRV_DS1685_FAMILY is not set # CONFIG_RTC_DRV_DS1742 is not set # CONFIG_RTC_DRV_DS2404 is not set # CONFIG_RTC_DRV_STK17TA8 is not set # CONFIG_RTC_DRV_M48T86 is not set # CONFIG_RTC_DRV_M48T35 is not set # CONFIG_RTC_DRV_M48T59 is not set # CONFIG_RTC_DRV_MSM6242 is not set # CONFIG_RTC_DRV_RP5C01 is not set # CONFIG_RTC_DRV_ZYNQMP is not set # CONFIG_RTC_DRV_CROS_EC is not set # # on-CPU RTC drivers # # CONFIG_RTC_DRV_CADENCE is not set # CONFIG_RTC_DRV_FTRTC010 is not set # CONFIG_RTC_DRV_R7301 is not set # CONFIG_RTC_DRV_GOLDFISH is not set # # HID Sensor RTC drivers # CONFIG_RTC_DRV_HID_SENSOR_TIME=y CONFIG_DMADEVICES=y # CONFIG_DMADEVICES_DEBUG is not set # # DMA Devices # CONFIG_DMA_ENGINE=y CONFIG_DMA_VIRTUAL_CHANNELS=y CONFIG_DMA_ACPI=y CONFIG_DMA_OF=y # CONFIG_ALTERA_MSGDMA is not set # CONFIG_DW_AXI_DMAC is not set # CONFIG_FSL_EDMA is not set # CONFIG_INTEL_IDMA64 is not set # CONFIG_INTEL_IDXD is not set # CONFIG_INTEL_IDXD_COMPAT is not set # CONFIG_INTEL_IOATDMA is not set # CONFIG_PLX_DMA is not set # CONFIG_SWITCHTEC_DMA is not set # CONFIG_XILINX_DMA is not set # CONFIG_XILINX_XDMA is not set # CONFIG_XILINX_ZYNQMP_DPDMA is not set # CONFIG_AMD_PTDMA is not set # CONFIG_AMD_QDMA is not set # CONFIG_QCOM_HIDMA_MGMT is not set # CONFIG_QCOM_HIDMA is not set CONFIG_DW_DMAC_CORE=y # CONFIG_DW_DMAC is not set # CONFIG_DW_DMAC_PCI is not set # CONFIG_DW_EDMA is not set CONFIG_HSU_DMA=y # CONFIG_SF_PDMA is not set # CONFIG_INTEL_LDMA is not set # # DMA Clients # # CONFIG_ASYNC_TX_DMA is not set # CONFIG_DMATEST is not set # # DMABUF options # CONFIG_SYNC_FILE=y # CONFIG_SW_SYNC is not set # CONFIG_UDMABUF is not set # CONFIG_DMABUF_DEBUG is not set # CONFIG_DMABUF_SELFTESTS is not set # CONFIG_DMABUF_HEAPS is not set # end of DMABUF options # CONFIG_UIO is not set # CONFIG_VFIO is not set # CONFIG_VIRT_DRIVERS is not set CONFIG_TSM=y CONFIG_VIRTIO_ANCHOR=y CONFIG_VIRTIO=y CONFIG_VIRTIO_PCI_LIB=y CONFIG_VIRTIO_PCI_LIB_LEGACY=y CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_PCI_ADMIN_LEGACY=y CONFIG_VIRTIO_PCI_LEGACY=y # CONFIG_VIRTIO_BALLOON is not set CONFIG_VIRTIO_INPUT=y # CONFIG_VIRTIO_MMIO is not set CONFIG_VIRTIO_DMA_SHARED_BUFFER=y # CONFIG_VIRTIO_DEBUG is not set # CONFIG_VIRTIO_RTC is not set # CONFIG_VDPA is not set CONFIG_VHOST_MENU=y # CONFIG_VHOST_NET is not set # CONFIG_VHOST_SCSI is not set # CONFIG_VHOST_VSOCK is not set # CONFIG_VHOST_CROSS_ENDIAN_LEGACY is not set CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y # # Microsoft Hyper-V guest support # # CONFIG_HYPERV is not set # end of Microsoft Hyper-V guest support CONFIG_GREYBUS=y # CONFIG_GREYBUS_BEAGLEPLAY is not set CONFIG_GREYBUS_ES2=y CONFIG_COMEDI=y # CONFIG_COMEDI_DEBUG is not set CONFIG_COMEDI_DEFAULT_BUF_SIZE_KB=2048 CONFIG_COMEDI_DEFAULT_BUF_MAXSIZE_KB=20480 # CONFIG_COMEDI_MISC_DRIVERS is not set # CONFIG_COMEDI_PCI_DRIVERS is not set # CONFIG_COMEDI_PCMCIA_DRIVERS is not set CONFIG_COMEDI_USB_DRIVERS=y CONFIG_COMEDI_DT9812=y CONFIG_COMEDI_NI_USB6501=y CONFIG_COMEDI_USBDUX=y CONFIG_COMEDI_USBDUXFAST=y CONFIG_COMEDI_USBDUXSIGMA=y CONFIG_COMEDI_VMK80XX=y # CONFIG_COMEDI_8255_SA is not set # CONFIG_COMEDI_KCOMEDILIB is not set # CONFIG_COMEDI_TESTS is not set # CONFIG_GPIB is not set CONFIG_STAGING=y # CONFIG_RTL8723BS is not set # # IIO staging drivers # # # Accelerometers # # CONFIG_ADIS16203 is not set # end of Accelerometers # # Analog to digital converters # # CONFIG_AD7816 is not set # end of Analog to digital converters # # Analog digital bi-direction converters # # CONFIG_ADT7316 is not set # end of Analog digital bi-direction converters # # Direct Digital Synthesis # # CONFIG_AD9832 is not set # CONFIG_AD9834 is not set # end of Direct Digital Synthesis # # Network Analyzer, Impedance Converters # # CONFIG_AD5933 is not set # end of Network Analyzer, Impedance Converters # end of IIO staging drivers # CONFIG_FB_SM750 is not set # CONFIG_STAGING_MEDIA is not set # CONFIG_FB_TFT is not set # CONFIG_MOST_COMPONENTS is not set # CONFIG_GREYBUS_AUDIO is not set # CONFIG_GREYBUS_BOOTROM is not set # CONFIG_GREYBUS_FIRMWARE is not set CONFIG_GREYBUS_HID=y # CONFIG_GREYBUS_LOG is not set # CONFIG_GREYBUS_LOOPBACK is not set # CONFIG_GREYBUS_POWER is not set # CONFIG_GREYBUS_RAW is not set # CONFIG_GREYBUS_VIBRATOR is not set CONFIG_GREYBUS_BRIDGED_PHY=y # CONFIG_GREYBUS_GPIO is not set # CONFIG_GREYBUS_I2C is not set # CONFIG_GREYBUS_SDIO is not set # CONFIG_GREYBUS_SPI is not set # CONFIG_GREYBUS_UART is not set CONFIG_GREYBUS_USB=y # CONFIG_XIL_AXIS_FIFO is not set # CONFIG_VME_BUS is not set # CONFIG_GOLDFISH is not set CONFIG_CHROME_PLATFORMS=y # CONFIG_CHROMEOS_ACPI is not set # CONFIG_CHROMEOS_LAPTOP is not set # CONFIG_CHROMEOS_PSTORE is not set # CONFIG_CHROMEOS_TBMC is not set # CONFIG_CHROMEOS_OF_HW_PROBER is not set CONFIG_CROS_EC=y # CONFIG_CROS_EC_I2C is not set CONFIG_CROS_EC_ISHTP=y # CONFIG_CROS_EC_SPI is not set # CONFIG_CROS_EC_UART is not set # CONFIG_CROS_EC_LPC is not set CONFIG_CROS_EC_PROTO=y # CONFIG_CROS_KBD_LED_BACKLIGHT is not set # CONFIG_CROS_EC_CHARDEV is not set # CONFIG_CROS_EC_LIGHTBAR is not set # CONFIG_CROS_EC_VBC is not set # CONFIG_CROS_EC_DEBUGFS is not set # CONFIG_CROS_EC_SENSORHUB is not set # CONFIG_CROS_EC_SYSFS is not set CONFIG_CROS_EC_TYPEC_ALTMODES=y CONFIG_CROS_EC_TYPEC=y CONFIG_CROS_HPS_I2C=y CONFIG_CROS_USBPD_NOTIFY=y # CONFIG_CHROMEOS_PRIVACY_SCREEN is not set CONFIG_CROS_TYPEC_SWITCH=y # CONFIG_MELLANOX_PLATFORM is not set CONFIG_SURFACE_PLATFORMS=y # CONFIG_SURFACE3_WMI is not set # CONFIG_SURFACE_3_POWER_OPREGION is not set # CONFIG_SURFACE_ACPI_NOTIFY is not set # CONFIG_SURFACE_AGGREGATOR_CDEV is not set # CONFIG_SURFACE_AGGREGATOR_HUB is not set CONFIG_SURFACE_AGGREGATOR_REGISTRY=y # CONFIG_SURFACE_AGGREGATOR_TABLET_SWITCH is not set # CONFIG_SURFACE_DTX is not set # CONFIG_SURFACE_GPE is not set # CONFIG_SURFACE_HOTPLUG is not set # CONFIG_SURFACE_PLATFORM_PROFILE is not set # CONFIG_SURFACE_PRO3_BUTTON is not set CONFIG_SURFACE_AGGREGATOR=y CONFIG_SURFACE_AGGREGATOR_BUS=y CONFIG_X86_PLATFORM_DEVICES=y CONFIG_WMI_BMOF=y # CONFIG_HUAWEI_WMI is not set # CONFIG_X86_PLATFORM_DRIVERS_UNIWILL is not set # CONFIG_MXM_WMI is not set # CONFIG_NVIDIA_WMI_EC_BACKLIGHT is not set # CONFIG_XIAOMI_WMI is not set # CONFIG_REDMI_WMI is not set # CONFIG_GIGABYTE_WMI is not set # CONFIG_BITLAND_MIFS_WMI is not set # CONFIG_ACERHDF is not set # CONFIG_ACER_WIRELESS is not set # CONFIG_ACER_WMI is not set # # AMD HSMP Driver # # CONFIG_AMD_HSMP_ACPI is not set # CONFIG_AMD_HSMP_PLAT is not set # end of AMD HSMP Driver CONFIG_AMD_PMF=y CONFIG_AMD_PMF_DEBUG=y # CONFIG_AMD_PMC is not set # CONFIG_AMD_HFI is not set # CONFIG_AMD_3D_VCACHE is not set # CONFIG_AMD_WBRF is not set # CONFIG_AMD_ISP_PLATFORM is not set # CONFIG_ADV_SWBUTTON is not set # CONFIG_APPLE_GMUX is not set # CONFIG_ASUS_LAPTOP is not set # CONFIG_ASUS_WIRELESS is not set # CONFIG_ASUS_ARMOURY is not set CONFIG_ASUS_WMI=y # CONFIG_ASUS_WMI_DEPRECATED_ATTRS is not set # CONFIG_ASUS_NB_WMI is not set CONFIG_ASUS_TF103C_DOCK=y # CONFIG_AYANEO_EC is not set CONFIG_EEEPC_LAPTOP=y # CONFIG_EEEPC_WMI is not set # CONFIG_X86_PLATFORM_DRIVERS_DELL is not set # CONFIG_AMILO_RFKILL is not set # CONFIG_FUJITSU_LAPTOP is not set # CONFIG_FUJITSU_TABLET is not set # CONFIG_GPD_POCKET_FAN is not set # CONFIG_X86_PLATFORM_DRIVERS_HP is not set # CONFIG_WIRELESS_HOTKEY is not set # CONFIG_IBM_RTL is not set # CONFIG_SENSORS_HDAPS is not set # CONFIG_INTEL_ATOMISP2_PM is not set # CONFIG_INTEL_IFS is not set # CONFIG_INTEL_SAR_INT1092 is not set # CONFIG_INTEL_SKL_INT3472 is not set # # Intel Speed Select Technology interface support # # CONFIG_INTEL_SPEED_SELECT_INTERFACE is not set # end of Intel Speed Select Technology interface support # CONFIG_INTEL_WMI_SBL_FW_UPDATE is not set # CONFIG_INTEL_WMI_THUNDERBOLT is not set # # Intel Uncore Frequency Control # # CONFIG_INTEL_UNCORE_FREQ_CONTROL is not set # end of Intel Uncore Frequency Control # CONFIG_INTEL_HID_EVENT is not set # CONFIG_INTEL_VBTN is not set # CONFIG_INTEL_EHL_PSE_IO is not set # CONFIG_INTEL_INT0002_VGPIO is not set # CONFIG_INTEL_OAKTRAIL is not set # CONFIG_INTEL_BXTWC_PMIC_TMU is not set CONFIG_INTEL_CHTWC_INT33FE=y CONFIG_INTEL_ISHTP_ECLITE=y # CONFIG_INTEL_PUNIT_IPC is not set # CONFIG_INTEL_RST is not set # CONFIG_INTEL_SMARTCONNECT is not set # CONFIG_INTEL_TURBO_MAX_3 is not set # CONFIG_INTEL_VSEC is not set # CONFIG_IDEAPAD_LAPTOP is not set # CONFIG_LENOVO_WMI_HOTKEY_UTILITIES is not set # CONFIG_LENOVO_WMI_CAMERA is not set # CONFIG_THINKPAD_ACPI is not set # CONFIG_THINKPAD_LMI is not set # CONFIG_YOGABOOK is not set # CONFIG_YT2_1380 is not set # CONFIG_LENOVO_WMI_GAMEZONE is not set # CONFIG_LENOVO_WMI_TUNING is not set # CONFIG_ACPI_QUICKSTART is not set # CONFIG_MEEGOPAD_ANX7428 is not set # CONFIG_MSI_EC is not set # CONFIG_MSI_LAPTOP is not set # CONFIG_MSI_WMI is not set # CONFIG_MSI_WMI_PLATFORM is not set # CONFIG_PCENGINES_APU2 is not set # CONFIG_PORTWELL_EC is not set # CONFIG_BARCO_P50_GPIO is not set # CONFIG_SAMSUNG_GALAXYBOOK is not set # CONFIG_SAMSUNG_LAPTOP is not set # CONFIG_SAMSUNG_Q10 is not set # CONFIG_ACPI_TOSHIBA is not set # CONFIG_TOSHIBA_BT_RFKILL is not set # CONFIG_TOSHIBA_HAPS is not set # CONFIG_TOSHIBA_WMI is not set # CONFIG_ACPI_CMPC is not set # CONFIG_COMPAL_LAPTOP is not set # CONFIG_LG_LAPTOP is not set # CONFIG_PANASONIC_LAPTOP is not set # CONFIG_SONY_LAPTOP is not set # CONFIG_SYSTEM76_ACPI is not set # CONFIG_TOPSTAR_LAPTOP is not set # CONFIG_SERIAL_MULTI_INSTANTIATE is not set # CONFIG_INSPUR_PLATFORM_PROFILE is not set # CONFIG_DASHARO_ACPI is not set # CONFIG_INTEL_IPS is not set CONFIG_INTEL_SCU_IPC=y # CONFIG_INTEL_SCU_PCI is not set # CONFIG_INTEL_SCU_PLATFORM is not set # CONFIG_SIEMENS_SIMATIC_IPC is not set # CONFIG_SILICOM_PLATFORM is not set # CONFIG_WINMATE_FM07_KEYS is not set # CONFIG_OXP_EC is not set # CONFIG_TUXEDO_NB04_WMI_AB is not set CONFIG_P2SB=y CONFIG_ACPI_WMI=y # CONFIG_ACPI_WMI_LEGACY_DEVICE_NAMES is not set CONFIG_HAVE_CLK=y CONFIG_HAVE_CLK_PREPARE=y CONFIG_COMMON_CLK=y # CONFIG_LMK04832 is not set # CONFIG_COMMON_CLK_MAX9485 is not set # CONFIG_COMMON_CLK_SI5341 is not set # CONFIG_COMMON_CLK_SI5351 is not set # CONFIG_COMMON_CLK_SI514 is not set # CONFIG_COMMON_CLK_SI544 is not set # CONFIG_COMMON_CLK_SI570 is not set # CONFIG_COMMON_CLK_CDCE706 is not set # CONFIG_COMMON_CLK_CDCE925 is not set # CONFIG_COMMON_CLK_CS2000_CP is not set # CONFIG_CLK_TWL is not set # CONFIG_COMMON_CLK_AXI_CLKGEN is not set # CONFIG_COMMON_CLK_RS9_PCIE is not set # CONFIG_COMMON_CLK_SI521XX is not set # CONFIG_COMMON_CLK_VC3 is not set # CONFIG_COMMON_CLK_VC5 is not set # CONFIG_COMMON_CLK_VC7 is not set # CONFIG_COMMON_CLK_FIXED_MMIO is not set # CONFIG_CLK_LGM_CGU is not set # CONFIG_XILINX_VCU is not set # CONFIG_COMMON_CLK_XLNX_CLKWZRD is not set # CONFIG_HWSPINLOCK is not set # # Clock Source drivers # CONFIG_CLKEVT_I8253=y CONFIG_I8253_LOCK=y CONFIG_CLKBLD_I8253=y # end of Clock Source drivers CONFIG_MAILBOX=y # CONFIG_PLATFORM_MHU is not set CONFIG_PCC=y # CONFIG_ALTERA_MBOX is not set # CONFIG_MAILBOX_TEST is not set CONFIG_IOMMU_IOVA=y CONFIG_IOMMU_API=y CONFIG_IOMMU_SUPPORT=y # # Generic IOMMU Pagetable Support # # end of Generic IOMMU Pagetable Support # CONFIG_IOMMU_DEBUGFS is not set # CONFIG_IOMMU_DEFAULT_DMA_STRICT is not set CONFIG_IOMMU_DEFAULT_DMA_LAZY=y # CONFIG_IOMMU_DEFAULT_PASSTHROUGH is not set CONFIG_OF_IOMMU=y CONFIG_IOMMU_DMA=y CONFIG_IOMMU_SVA=y CONFIG_IOMMU_IOPF=y CONFIG_AMD_IOMMU=y CONFIG_DMAR_TABLE=y CONFIG_INTEL_IOMMU=y # CONFIG_INTEL_IOMMU_SVM is not set # CONFIG_INTEL_IOMMU_DEFAULT_ON is not set CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON=y CONFIG_INTEL_IOMMU_PERF_EVENTS=y # CONFIG_IOMMUFD is not set # CONFIG_IRQ_REMAP is not set # CONFIG_VIRTIO_IOMMU is not set CONFIG_GENERIC_PT=y # CONFIG_DEBUG_GENERIC_PT is not set CONFIG_IOMMU_PT=y CONFIG_IOMMU_PT_AMDV1=y CONFIG_IOMMU_PT_VTDSS=y # CONFIG_IOMMU_PT_RISCV64 is not set CONFIG_IOMMU_PT_X86_64=y # # Remoteproc drivers # # CONFIG_REMOTEPROC is not set # end of Remoteproc drivers # # Rpmsg drivers # # CONFIG_RPMSG_QCOM_GLINK_RPM is not set # CONFIG_RPMSG_VIRTIO is not set # end of Rpmsg drivers CONFIG_SOUNDWIRE=y # # SoundWire Devices # # CONFIG_SOUNDWIRE_AMD is not set # CONFIG_SOUNDWIRE_INTEL is not set # CONFIG_SOUNDWIRE_QCOM is not set # # SOC (System On Chip) specific Drivers # # # Amlogic SoC drivers # # end of Amlogic SoC drivers # # Broadcom SoC drivers # # end of Broadcom SoC drivers # # NXP/Freescale QorIQ SoC drivers # # end of NXP/Freescale QorIQ SoC drivers # # fujitsu SoC drivers # # end of fujitsu SoC drivers # # i.MX SoC drivers # # end of i.MX SoC drivers # # Enable LiteX SoC Builder specific drivers # # CONFIG_LITEX_SOC_CONTROLLER is not set # end of Enable LiteX SoC Builder specific drivers # CONFIG_WPCM450_SOC is not set # # Qualcomm SoC drivers # # end of Qualcomm SoC drivers # CONFIG_SOC_TI is not set # # Xilinx SoC drivers # # end of Xilinx SoC drivers # end of SOC (System On Chip) specific Drivers # # PM Domains # # # Amlogic PM Domains # # end of Amlogic PM Domains # # Broadcom PM Domains # # end of Broadcom PM Domains # # i.MX PM Domains # # end of i.MX PM Domains # # Qualcomm PM Domains # # end of Qualcomm PM Domains # end of PM Domains # CONFIG_PM_DEVFREQ is not set CONFIG_EXTCON=y # # Extcon Device Drivers # # CONFIG_EXTCON_ADC_JACK is not set # CONFIG_EXTCON_FSA9480 is not set # CONFIG_EXTCON_GPIO is not set # CONFIG_EXTCON_INTEL_INT3496 is not set CONFIG_EXTCON_INTEL_CHT_WC=y # CONFIG_EXTCON_LC824206XA is not set # CONFIG_EXTCON_MAX3355 is not set # CONFIG_EXTCON_MAX14526 is not set CONFIG_EXTCON_PTN5150=y # CONFIG_EXTCON_RT8973A is not set # CONFIG_EXTCON_SM5502 is not set # CONFIG_EXTCON_USB_GPIO is not set # CONFIG_EXTCON_USBC_CROS_EC is not set CONFIG_EXTCON_USBC_TUSB320=y # CONFIG_MEMORY is not set CONFIG_IIO=y CONFIG_IIO_BUFFER=y # CONFIG_IIO_BUFFER_CB is not set # CONFIG_IIO_BUFFER_DMA is not set # CONFIG_IIO_BUFFER_DMAENGINE is not set # CONFIG_IIO_BUFFER_HW_CONSUMER is not set CONFIG_IIO_KFIFO_BUF=y CONFIG_IIO_TRIGGERED_BUFFER=y # CONFIG_IIO_CONFIGFS is not set CONFIG_IIO_TRIGGER=y CONFIG_IIO_CONSUMERS_PER_TRIGGER=2 # CONFIG_IIO_SW_DEVICE is not set # CONFIG_IIO_SW_TRIGGER is not set # CONFIG_IIO_TRIGGERED_EVENT is not set # # Accelerometers # # CONFIG_ADIS16201 is not set # CONFIG_ADIS16209 is not set # CONFIG_ADXL313_I2C is not set # CONFIG_ADXL313_SPI is not set # CONFIG_ADXL345_I2C is not set # CONFIG_ADXL345_SPI is not set # CONFIG_ADXL355_I2C is not set # CONFIG_ADXL355_SPI is not set # CONFIG_ADXL367_SPI is not set # CONFIG_ADXL367_I2C is not set # CONFIG_ADXL372_SPI is not set # CONFIG_ADXL372_I2C is not set # CONFIG_ADXL380_SPI is not set # CONFIG_ADXL380_I2C is not set # CONFIG_BMA180 is not set # CONFIG_BMA220 is not set # CONFIG_BMA400 is not set # CONFIG_BMC150_ACCEL is not set # CONFIG_BMI088_ACCEL is not set # CONFIG_DA280 is not set # CONFIG_DA311 is not set # CONFIG_DMARD06 is not set # CONFIG_DMARD09 is not set # CONFIG_DMARD10 is not set # CONFIG_FXLS8962AF_I2C is not set # CONFIG_FXLS8962AF_SPI is not set CONFIG_HID_SENSOR_ACCEL_3D=y # CONFIG_IIO_ST_ACCEL_3AXIS is not set # CONFIG_IIO_KX022A_SPI is not set # CONFIG_IIO_KX022A_I2C is not set # CONFIG_KXSD9 is not set # CONFIG_KXCJK1013 is not set # CONFIG_MC3230 is not set # CONFIG_MMA7455_I2C is not set # CONFIG_MMA7455_SPI is not set # CONFIG_MMA7660 is not set # CONFIG_MMA8452 is not set # CONFIG_MMA9551 is not set # CONFIG_MMA9553 is not set # CONFIG_MSA311 is not set # CONFIG_MXC4005 is not set # CONFIG_MXC6255 is not set # CONFIG_SCA3000 is not set # CONFIG_SCA3300 is not set # CONFIG_STK8312 is not set # CONFIG_STK8BA50 is not set # end of Accelerometers # # Analog to digital converters # # CONFIG_AD4000 is not set # CONFIG_AD4080 is not set # CONFIG_AD4130 is not set # CONFIG_AD4134 is not set # CONFIG_AD4170_4 is not set # CONFIG_AD4695 is not set # CONFIG_AD7091R5 is not set # CONFIG_AD7091R8 is not set # CONFIG_AD7124 is not set # CONFIG_AD7173 is not set # CONFIG_AD7191 is not set # CONFIG_AD7192 is not set # CONFIG_AD7266 is not set # CONFIG_AD7280 is not set # CONFIG_AD7291 is not set # CONFIG_AD7292 is not set # CONFIG_AD7298 is not set # CONFIG_AD7380 is not set # CONFIG_AD7476 is not set # CONFIG_AD7606_IFACE_PARALLEL is not set # CONFIG_AD7606_IFACE_SPI is not set # CONFIG_AD7766 is not set # CONFIG_AD7768_1 is not set # CONFIG_AD7779 is not set # CONFIG_AD7780 is not set # CONFIG_AD7791 is not set # CONFIG_AD7793 is not set # CONFIG_AD7887 is not set # CONFIG_AD7923 is not set # CONFIG_AD7944 is not set # CONFIG_AD7949 is not set # CONFIG_AD799X is not set # CONFIG_AD9467 is not set # CONFIG_ADE9000 is not set # CONFIG_CC10001_ADC is not set CONFIG_DLN2_ADC=y # CONFIG_ENVELOPE_DETECTOR is not set # CONFIG_GEHC_PMC_ADC is not set # CONFIG_HI8435 is not set # CONFIG_HX711 is not set # CONFIG_INA2XX_ADC is not set # CONFIG_LTC2309 is not set # CONFIG_LTC2471 is not set # CONFIG_LTC2485 is not set # CONFIG_LTC2496 is not set # CONFIG_LTC2497 is not set # CONFIG_MAX1027 is not set # CONFIG_MAX11100 is not set # CONFIG_MAX1118 is not set # CONFIG_MAX11205 is not set # CONFIG_MAX11410 is not set # CONFIG_MAX1241 is not set # CONFIG_MAX1363 is not set # CONFIG_MAX14001 is not set # CONFIG_MAX34408 is not set # CONFIG_MAX9611 is not set # CONFIG_MCP320X is not set # CONFIG_MCP3422 is not set # CONFIG_MCP3564 is not set # CONFIG_MCP3911 is not set # CONFIG_MEDIATEK_MT6360_ADC is not set # CONFIG_MEDIATEK_MT6370_ADC is not set # CONFIG_NAU7802 is not set # CONFIG_NCT7201 is not set # CONFIG_PAC1921 is not set # CONFIG_PAC1934 is not set # CONFIG_ROHM_BD79112 is not set # CONFIG_ROHM_BD79124 is not set # CONFIG_RICHTEK_RTQ6056 is not set # CONFIG_SD_ADC_MODULATOR is not set # CONFIG_TI_ADC081C is not set # CONFIG_TI_ADC0832 is not set # CONFIG_TI_ADC084S021 is not set # CONFIG_TI_ADC108S102 is not set # CONFIG_TI_ADC12138 is not set # CONFIG_TI_ADC128S052 is not set # CONFIG_TI_ADC161S626 is not set # CONFIG_TI_ADS1015 is not set # CONFIG_TI_ADS1018 is not set # CONFIG_TI_ADS1100 is not set # CONFIG_TI_ADS1119 is not set # CONFIG_TI_ADS124S08 is not set # CONFIG_TI_ADS1298 is not set # CONFIG_TI_ADS131E08 is not set # CONFIG_TI_ADS131M02 is not set # CONFIG_TI_ADS7138 is not set # CONFIG_TI_ADS7924 is not set # CONFIG_TI_ADS7950 is not set # CONFIG_TI_ADS8344 is not set # CONFIG_TI_ADS8688 is not set # CONFIG_TI_LMP92064 is not set # CONFIG_TI_TLC4541 is not set # CONFIG_TI_TSC2046 is not set # CONFIG_TWL4030_MADC is not set # CONFIG_TWL6030_GPADC is not set # CONFIG_VF610_ADC is not set CONFIG_VIPERBOARD_ADC=y # CONFIG_XILINX_XADC is not set # end of Analog to digital converters # # Analog to digital and digital to analog converters # # CONFIG_AD74115 is not set # CONFIG_AD74413R is not set # end of Analog to digital and digital to analog converters # # Analog Front Ends # # CONFIG_IIO_RESCALE is not set # end of Analog Front Ends # # Amplifiers # # CONFIG_AD8366 is not set # CONFIG_ADA4250 is not set # CONFIG_ADL8113 is not set # CONFIG_HMC425 is not set # end of Amplifiers # # Capacitance to digital converters # # CONFIG_AD7150 is not set # CONFIG_AD7746 is not set # end of Capacitance to digital converters # # Chemical Sensors # # CONFIG_AOSONG_AGS02MA is not set # CONFIG_ATLAS_PH_SENSOR is not set # CONFIG_ATLAS_EZO_SENSOR is not set # CONFIG_BME680 is not set # CONFIG_CCS811 is not set # CONFIG_ENS160 is not set # CONFIG_IAQCORE is not set # CONFIG_MHZ19B is not set # CONFIG_PMS7003 is not set # CONFIG_SCD30_CORE is not set # CONFIG_SCD4X is not set # CONFIG_SEN0322 is not set # CONFIG_SENSIRION_SGP30 is not set # CONFIG_SENSIRION_SGP40 is not set # CONFIG_SPS30_I2C is not set # CONFIG_SPS30_SERIAL is not set # CONFIG_SENSEAIR_SUNRISE_CO2 is not set # CONFIG_VZ89X is not set # end of Chemical Sensors # # Hid Sensor IIO Common # CONFIG_HID_SENSOR_IIO_COMMON=y CONFIG_HID_SENSOR_IIO_TRIGGER=y # end of Hid Sensor IIO Common # # IIO SCMI Sensors # # end of IIO SCMI Sensors # # SSP Sensor Common # # CONFIG_IIO_SSP_SENSORHUB is not set # end of SSP Sensor Common # # Digital to analog converters # # CONFIG_AD3530R is not set # CONFIG_AD3552R_HS is not set # CONFIG_AD3552R is not set # CONFIG_AD5064 is not set # CONFIG_AD5360 is not set # CONFIG_AD5380 is not set # CONFIG_AD5421 is not set # CONFIG_AD5446_SPI is not set # CONFIG_AD5446_I2C is not set # CONFIG_AD5449 is not set # CONFIG_AD5592R is not set # CONFIG_AD5593R is not set # CONFIG_AD5504 is not set # CONFIG_AD5624R_SPI is not set # CONFIG_AD9739A is not set # CONFIG_LTC2688 is not set # CONFIG_AD5686_SPI is not set # CONFIG_AD5696_I2C is not set # CONFIG_AD5755 is not set # CONFIG_AD5758 is not set # CONFIG_AD5761 is not set # CONFIG_AD5764 is not set # CONFIG_AD5766 is not set # CONFIG_AD5770R is not set # CONFIG_AD5791 is not set # CONFIG_AD7293 is not set # CONFIG_AD7303 is not set # CONFIG_AD8460 is not set # CONFIG_AD8801 is not set # CONFIG_BD79703 is not set # CONFIG_DPOT_DAC is not set # CONFIG_DS4424 is not set # CONFIG_LTC1660 is not set # CONFIG_LTC2632 is not set # CONFIG_LTC2664 is not set # CONFIG_M62332 is not set # CONFIG_MAX517 is not set # CONFIG_MAX22007 is not set # CONFIG_MAX5522 is not set # CONFIG_MAX5821 is not set # CONFIG_MCP4725 is not set # CONFIG_MCP4728 is not set # CONFIG_MCP47FEB02 is not set # CONFIG_MCP4821 is not set # CONFIG_MCP4922 is not set # CONFIG_TI_DAC082S085 is not set # CONFIG_TI_DAC5571 is not set # CONFIG_TI_DAC7311 is not set # CONFIG_TI_DAC7612 is not set # CONFIG_VF610_DAC is not set # end of Digital to analog converters # # IIO dummy driver # # end of IIO dummy driver # # Filters # # CONFIG_ADMV8818 is not set # end of Filters # # Frequency Synthesizers DDS/PLL # # # Clock Generator/Distribution # # CONFIG_AD9523 is not set # end of Clock Generator/Distribution # # Phase-Locked Loop (PLL) frequency synthesizers # # CONFIG_ADF4350 is not set # CONFIG_ADF4371 is not set # CONFIG_ADF4377 is not set # CONFIG_ADMFM2000 is not set # CONFIG_ADMV1013 is not set # CONFIG_ADMV1014 is not set # CONFIG_ADMV4420 is not set # CONFIG_ADRF6780 is not set # end of Phase-Locked Loop (PLL) frequency synthesizers # end of Frequency Synthesizers DDS/PLL # # Digital gyroscope sensors # # CONFIG_ADIS16080 is not set # CONFIG_ADIS16130 is not set # CONFIG_ADIS16136 is not set # CONFIG_ADIS16260 is not set # CONFIG_ADXRS290 is not set # CONFIG_ADXRS450 is not set # CONFIG_BMG160 is not set # CONFIG_FXAS21002C is not set CONFIG_HID_SENSOR_GYRO_3D=y # CONFIG_MPU3050_I2C is not set # CONFIG_IIO_ST_GYRO_3AXIS is not set # CONFIG_ITG3200 is not set # end of Digital gyroscope sensors # # Health Sensors # # # Heart Rate Monitors # # CONFIG_AFE4403 is not set # CONFIG_AFE4404 is not set # CONFIG_MAX30100 is not set # CONFIG_MAX30102 is not set # end of Heart Rate Monitors # end of Health Sensors # # Humidity sensors # # CONFIG_AM2315 is not set # CONFIG_DHT11 is not set # CONFIG_ENS210 is not set # CONFIG_HDC100X is not set # CONFIG_HDC2010 is not set # CONFIG_HDC3020 is not set CONFIG_HID_SENSOR_HUMIDITY=y # CONFIG_HTS221 is not set # CONFIG_HTU21 is not set # CONFIG_SI7005 is not set # CONFIG_SI7020 is not set # end of Humidity sensors # # Inertial measurement units # # CONFIG_ADIS16400 is not set # CONFIG_ADIS16460 is not set # CONFIG_ADIS16475 is not set # CONFIG_ADIS16480 is not set # CONFIG_ADIS16550 is not set # CONFIG_BMI160_I2C is not set # CONFIG_BMI160_SPI is not set # CONFIG_BMI270_I2C is not set # CONFIG_BMI270_SPI is not set # CONFIG_BMI323_I2C is not set # CONFIG_BMI323_SPI is not set # CONFIG_BOSCH_BNO055_SERIAL is not set # CONFIG_BOSCH_BNO055_I2C is not set # CONFIG_FXOS8700_I2C is not set # CONFIG_FXOS8700_SPI is not set # CONFIG_KMX61 is not set # CONFIG_INV_ICM42600_I2C is not set # CONFIG_INV_ICM42600_SPI is not set # CONFIG_INV_ICM45600_I2C is not set # CONFIG_INV_ICM45600_SPI is not set # CONFIG_INV_MPU6050_I2C is not set # CONFIG_INV_MPU6050_SPI is not set # CONFIG_SMI240 is not set # CONFIG_SMI330_I2C is not set # CONFIG_SMI330_SPI is not set # CONFIG_IIO_ST_LSM6DSX is not set # CONFIG_IIO_ST_LSM9DS0 is not set # end of Inertial measurement units # # Light sensors # # CONFIG_ACPI_ALS is not set # CONFIG_ADJD_S311 is not set # CONFIG_ADUX1020 is not set # CONFIG_AL3000A is not set # CONFIG_AL3010 is not set # CONFIG_AL3320A is not set # CONFIG_APDS9160 is not set # CONFIG_APDS9300 is not set # CONFIG_APDS9306 is not set # CONFIG_APDS9960 is not set # CONFIG_AS73211 is not set # CONFIG_BH1745 is not set # CONFIG_BH1750 is not set # CONFIG_BH1780 is not set # CONFIG_CM32181 is not set # CONFIG_CM3232 is not set # CONFIG_CM3323 is not set # CONFIG_CM3605 is not set # CONFIG_CM36651 is not set # CONFIG_GP2AP002 is not set # CONFIG_GP2AP020A00F is not set # CONFIG_SENSORS_ISL29018 is not set # CONFIG_SENSORS_ISL29028 is not set # CONFIG_ISL29125 is not set # CONFIG_ISL76682 is not set CONFIG_HID_SENSOR_ALS=y CONFIG_HID_SENSOR_PROX=y # CONFIG_JSA1212 is not set # CONFIG_ROHM_BU27034 is not set # CONFIG_RPR0521 is not set # CONFIG_LTR390 is not set # CONFIG_LTR501 is not set # CONFIG_LTRF216A is not set # CONFIG_LV0104CS is not set # CONFIG_MAX44000 is not set # CONFIG_MAX44009 is not set # CONFIG_NOA1305 is not set # CONFIG_OPT3001 is not set # CONFIG_OPT4001 is not set # CONFIG_OPT4060 is not set # CONFIG_PA12203001 is not set # CONFIG_SI1133 is not set # CONFIG_SI1145 is not set # CONFIG_STK3310 is not set # CONFIG_ST_UVIS25 is not set # CONFIG_TCS3414 is not set # CONFIG_TCS3472 is not set # CONFIG_SENSORS_TSL2563 is not set # CONFIG_TSL2583 is not set # CONFIG_TSL2591 is not set # CONFIG_TSL2772 is not set # CONFIG_TSL4531 is not set # CONFIG_US5182D is not set # CONFIG_VCNL4000 is not set # CONFIG_VCNL4035 is not set # CONFIG_VEML3235 is not set # CONFIG_VEML6030 is not set # CONFIG_VEML6040 is not set # CONFIG_VEML6046X00 is not set # CONFIG_VEML6070 is not set # CONFIG_VEML6075 is not set # CONFIG_VL6180 is not set # CONFIG_ZOPT2201 is not set # end of Light sensors # # Magnetometer sensors # # CONFIG_AF8133J is not set # CONFIG_AK8974 is not set # CONFIG_AK8975 is not set # CONFIG_AK09911 is not set # CONFIG_ALS31300 is not set # CONFIG_BMC150_MAGN_I2C is not set # CONFIG_BMC150_MAGN_SPI is not set # CONFIG_MAG3110 is not set CONFIG_HID_SENSOR_MAGNETOMETER_3D=y # CONFIG_MMC35240 is not set # CONFIG_MMC5633 is not set # CONFIG_IIO_ST_MAGN_3AXIS is not set # CONFIG_INFINEON_TLV493D is not set # CONFIG_SENSORS_HMC5843_I2C is not set # CONFIG_SENSORS_HMC5843_SPI is not set # CONFIG_SENSORS_RM3100_I2C is not set # CONFIG_SENSORS_RM3100_SPI is not set # CONFIG_SI7210 is not set # CONFIG_TI_TMAG5273 is not set # CONFIG_YAMAHA_YAS530 is not set # end of Magnetometer sensors # # Multiplexers # # CONFIG_IIO_MUX is not set # end of Multiplexers # # Inclinometer sensors # CONFIG_HID_SENSOR_INCLINOMETER_3D=y CONFIG_HID_SENSOR_DEVICE_ROTATION=y # end of Inclinometer sensors # # Triggers - standalone # # CONFIG_IIO_INTERRUPT_TRIGGER is not set # CONFIG_IIO_SYSFS_TRIGGER is not set # end of Triggers - standalone # # Linear and angular position sensors # CONFIG_HID_SENSOR_CUSTOM_INTEL_HINGE=y # end of Linear and angular position sensors # # Digital potentiometers # # CONFIG_AD5110 is not set # CONFIG_AD5272 is not set # CONFIG_DS1803 is not set # CONFIG_MAX5432 is not set # CONFIG_MAX5481 is not set # CONFIG_MAX5487 is not set # CONFIG_MCP4018 is not set # CONFIG_MCP4131 is not set # CONFIG_MCP4531 is not set # CONFIG_MCP41010 is not set # CONFIG_TPL0102 is not set # CONFIG_X9250 is not set # end of Digital potentiometers # # Digital potentiostats # # CONFIG_LMP91000 is not set # end of Digital potentiostats # # Pressure sensors # # CONFIG_ABP060MG is not set # CONFIG_ABP2030PA_I2C is not set # CONFIG_ABP2030PA_SPI is not set # CONFIG_ROHM_BM1390 is not set # CONFIG_BMP280 is not set # CONFIG_DLHL60D is not set # CONFIG_DPS310 is not set CONFIG_HID_SENSOR_PRESS=y # CONFIG_HP03 is not set # CONFIG_HSC030PA is not set # CONFIG_ICP10100 is not set # CONFIG_MPL115_I2C is not set # CONFIG_MPL115_SPI is not set # CONFIG_MPL3115 is not set # CONFIG_MPRLS0025PA_I2C is not set # CONFIG_MPRLS0025PA_SPI is not set # CONFIG_MS5611 is not set # CONFIG_MS5637 is not set # CONFIG_SDP500 is not set # CONFIG_IIO_ST_PRESS is not set # CONFIG_T5403 is not set # CONFIG_HP206C is not set # CONFIG_ZPA2326 is not set # CONFIG_ADP810 is not set # end of Pressure sensors # # Lightning sensors # # CONFIG_AS3935 is not set # end of Lightning sensors # # Proximity and distance sensors # # CONFIG_CROS_EC_MKBP_PROXIMITY is not set # CONFIG_D3323AA is not set # CONFIG_HX9023S is not set # CONFIG_IRSD200 is not set # CONFIG_ISL29501 is not set # CONFIG_LIDAR_LITE_V2 is not set # CONFIG_MB1232 is not set # CONFIG_PING is not set # CONFIG_RFD77402 is not set # CONFIG_SRF04 is not set # CONFIG_SX9310 is not set # CONFIG_SX9324 is not set # CONFIG_SX9360 is not set # CONFIG_SX9500 is not set # CONFIG_SRF08 is not set # CONFIG_VCNL3020 is not set # CONFIG_VL53L0X_I2C is not set # CONFIG_VL53L1X_I2C is not set # CONFIG_AW96103 is not set # end of Proximity and distance sensors # # Resolver to digital converters # # CONFIG_AD2S90 is not set # CONFIG_AD2S1200 is not set # CONFIG_AD2S1210 is not set # end of Resolver to digital converters # # Temperature sensors # # CONFIG_LTC2983 is not set # CONFIG_MAXIM_THERMOCOUPLE is not set CONFIG_HID_SENSOR_TEMP=y # CONFIG_MLX90614 is not set # CONFIG_MLX90632 is not set # CONFIG_MLX90635 is not set # CONFIG_TMP006 is not set # CONFIG_TMP007 is not set # CONFIG_TMP117 is not set # CONFIG_TSYS01 is not set # CONFIG_TSYS02D is not set # CONFIG_MAX30208 is not set # CONFIG_MAX31856 is not set # CONFIG_MAX31865 is not set # CONFIG_MCP9600 is not set # end of Temperature sensors # CONFIG_NTB is not set # CONFIG_PWM is not set # # IRQ chip support # CONFIG_IRQCHIP=y CONFIG_IRQ_MSI_LIB=y # CONFIG_AL_FIC is not set # CONFIG_XILINX_INTC is not set # end of IRQ chip support # CONFIG_IPACK_BUS is not set CONFIG_RESET_CONTROLLER=y # CONFIG_RESET_GPIO is not set # CONFIG_RESET_INTEL_GW is not set # CONFIG_RESET_SIMPLE is not set # CONFIG_RESET_TI_SYSCON is not set # CONFIG_RESET_TI_TPS380X is not set # # PHY Subsystem # CONFIG_GENERIC_PHY=y # CONFIG_PHY_CAN_TRANSCEIVER is not set # CONFIG_PHY_GOOGLE_USB is not set CONFIG_USB_LGM_PHY=y # CONFIG_PHY_NXP_PTN3222 is not set # # PHY drivers for Broadcom platforms # # CONFIG_BCM_KONA_USB2_PHY is not set # end of PHY drivers for Broadcom platforms # CONFIG_PHY_CADENCE_TORRENT is not set # CONFIG_PHY_CADENCE_DPHY is not set # CONFIG_PHY_CADENCE_DPHY_RX is not set # CONFIG_PHY_CADENCE_SIERRA is not set # CONFIG_PHY_CADENCE_SALVO is not set # CONFIG_PHY_INTEL_LGM_COMBO is not set # CONFIG_PHY_INTEL_LGM_EMMC is not set # CONFIG_PHY_PXA_28NM_HSIC is not set # CONFIG_PHY_PXA_28NM_USB2 is not set CONFIG_PHY_CPCAP_USB=y # CONFIG_PHY_MAPPHONE_MDM6600 is not set # CONFIG_PHY_OCELOT_SERDES is not set CONFIG_PHY_QCOM_USB_HS=y CONFIG_PHY_QCOM_USB_HSIC=y CONFIG_PHY_SAMSUNG_USB2=y CONFIG_PHY_TUSB1210=y # end of PHY Subsystem # CONFIG_POWERCAP is not set # CONFIG_MCB is not set # # Performance monitor support # # CONFIG_DWC_PCIE_PMU is not set # end of Performance monitor support CONFIG_RAS=y CONFIG_USB4=y # CONFIG_USB4_DEBUGFS_WRITE is not set # CONFIG_USB4_DMA_TEST is not set # # Android # # CONFIG_ANDROID_BINDER_IPC is not set # end of Android # CONFIG_LIBNVDIMM is not set # CONFIG_DAX is not set CONFIG_NVMEM=y CONFIG_NVMEM_SYSFS=y CONFIG_NVMEM_LAYOUTS=y # # Layout Types # # CONFIG_NVMEM_LAYOUT_SL28_VPD is not set # CONFIG_NVMEM_LAYOUT_ONIE_TLV is not set # CONFIG_NVMEM_LAYOUT_U_BOOT_ENV is not set # end of Layout Types # CONFIG_NVMEM_RMEM is not set # # HW tracing support # # CONFIG_STM is not set # CONFIG_INTEL_TH is not set # end of HW tracing support # CONFIG_FPGA is not set # CONFIG_FSI is not set CONFIG_TEE=y CONFIG_AMDTEE=y # CONFIG_MUX_CORE is not set # CONFIG_SIOX is not set # CONFIG_SLIMBUS is not set # CONFIG_INTERCONNECT is not set # CONFIG_COUNTER is not set CONFIG_MOST=y CONFIG_MOST_USB_HDM=y # CONFIG_MOST_CDEV is not set # CONFIG_MOST_SND is not set # CONFIG_PECI is not set # CONFIG_HTE is not set # end of Device Drivers # # File systems # CONFIG_DCACHE_WORD_ACCESS=y # CONFIG_VALIDATE_FS_PARSER is not set CONFIG_FS_IOMAP=y CONFIG_BUFFER_HEAD=y CONFIG_LEGACY_DIRECT_IO=y # CONFIG_EXT2_FS is not set CONFIG_EXT4_FS=y CONFIG_EXT4_USE_FOR_EXT2=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y # CONFIG_EXT4_DEBUG is not set CONFIG_JBD2=y # CONFIG_JBD2_DEBUG is not set CONFIG_FS_MBCACHE=y # CONFIG_JFS_FS is not set # CONFIG_XFS_FS is not set # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set # CONFIG_BTRFS_FS is not set # CONFIG_NILFS2_FS is not set # CONFIG_F2FS_FS is not set CONFIG_FS_POSIX_ACL=y CONFIG_EXPORTFS=y # CONFIG_EXPORTFS_BLOCK_OPS is not set CONFIG_FILE_LOCKING=y # CONFIG_FS_ENCRYPTION is not set # CONFIG_FS_VERITY is not set CONFIG_FSNOTIFY=y CONFIG_DNOTIFY=y CONFIG_INOTIFY_USER=y # CONFIG_FANOTIFY is not set CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_QUOTA_DEBUG is not set CONFIG_QUOTA_TREE=y # CONFIG_QFMT_V1 is not set CONFIG_QFMT_V2=y CONFIG_QUOTACTL=y CONFIG_AUTOFS_FS=y # CONFIG_FUSE_FS is not set # CONFIG_OVERLAY_FS is not set # # Caches # CONFIG_NETFS_SUPPORT=y # CONFIG_NETFS_STATS is not set # CONFIG_NETFS_DEBUG is not set # CONFIG_FSCACHE is not set # end of Caches # # CD-ROM/DVD Filesystems # CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y # CONFIG_UDF_FS is not set # end of CD-ROM/DVD Filesystems # # DOS/FAT/EXFAT/NT Filesystems # CONFIG_FAT_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_FAT_DEFAULT_CODEPAGE=437 CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" # CONFIG_FAT_DEFAULT_UTF8 is not set # CONFIG_EXFAT_FS is not set # CONFIG_NTFS_FS is not set # CONFIG_NTFS3_FS is not set # end of DOS/FAT/EXFAT/NT Filesystems # # Pseudo filesystems # CONFIG_PROC_FS=y CONFIG_PROC_KCORE=y CONFIG_PROC_VMCORE=y # CONFIG_PROC_VMCORE_DEVICE_DUMP is not set CONFIG_PROC_SYSCTL=y CONFIG_PROC_PAGE_MONITOR=y # CONFIG_PROC_CHILDREN is not set CONFIG_PROC_PID_ARCH_STATUS=y CONFIG_KERNFS=y CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_XATTR=y # CONFIG_TMPFS_INODE64 is not set # CONFIG_TMPFS_QUOTA is not set CONFIG_ARCH_SUPPORTS_HUGETLBFS=y CONFIG_HUGETLBFS=y # CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON is not set CONFIG_HUGETLB_PAGE=y CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP=y CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING=y CONFIG_ARCH_HAS_GIGANTIC_PAGE=y CONFIG_CONFIGFS_FS=y # end of Pseudo filesystems CONFIG_MISC_FILESYSTEMS=y # CONFIG_ORANGEFS_FS is not set # CONFIG_ADFS_FS is not set # CONFIG_AFFS_FS is not set # CONFIG_ECRYPT_FS is not set # CONFIG_HFS_FS is not set # CONFIG_HFSPLUS_FS is not set # CONFIG_BEFS_FS is not set # CONFIG_BFS_FS is not set # CONFIG_EFS_FS is not set # CONFIG_CRAMFS is not set # CONFIG_SQUASHFS is not set # CONFIG_VXFS_FS is not set # CONFIG_MINIX_FS is not set # CONFIG_OMFS_FS is not set # CONFIG_HPFS_FS is not set # CONFIG_QNX4FS_FS is not set # CONFIG_QNX6FS_FS is not set # CONFIG_ROMFS_FS is not set # CONFIG_PSTORE is not set # CONFIG_UFS_FS is not set # CONFIG_EROFS_FS is not set CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=y # CONFIG_NFS_V2 is not set CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y # CONFIG_NFS_SWAP is not set CONFIG_NFS_V4_0=y # CONFIG_NFS_V4_2 is not set CONFIG_PNFS_FILE_LAYOUT=y CONFIG_PNFS_BLOCK=y CONFIG_PNFS_FLEXFILE_LAYOUT=y CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN="kernel.org" # CONFIG_NFS_V4_1_MIGRATION is not set CONFIG_ROOT_NFS=y # CONFIG_NFS_FSCACHE is not set # CONFIG_NFS_USE_LEGACY_DNS is not set CONFIG_NFS_USE_KERNEL_DNS=y CONFIG_NFS_DISABLE_UDP_SUPPORT=y # CONFIG_NFSD is not set CONFIG_GRACE_PERIOD=y CONFIG_LOCKD=y CONFIG_LOCKD_V4=y CONFIG_NFS_ACL_SUPPORT=y CONFIG_NFS_COMMON=y CONFIG_SUNRPC=y CONFIG_SUNRPC_GSS=y CONFIG_SUNRPC_BACKCHANNEL=y CONFIG_RPCSEC_GSS_KRB5=y CONFIG_RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA1=y # CONFIG_RPCSEC_GSS_KRB5_ENCTYPES_CAMELLIA is not set # CONFIG_RPCSEC_GSS_KRB5_ENCTYPES_AES_SHA2 is not set # CONFIG_SUNRPC_DEBUG is not set # CONFIG_SUNRPC_XPRT_RDMA is not set # CONFIG_CEPH_FS is not set # CONFIG_CIFS is not set # CONFIG_SMB_SERVER is not set # CONFIG_CODA_FS is not set # CONFIG_AFS_FS is not set CONFIG_9P_FS=y # CONFIG_9P_FS_POSIX_ACL is not set # CONFIG_9P_FS_SECURITY is not set CONFIG_NLS=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y # CONFIG_NLS_CODEPAGE_737 is not set # CONFIG_NLS_CODEPAGE_775 is not set # CONFIG_NLS_CODEPAGE_850 is not set # CONFIG_NLS_CODEPAGE_852 is not set # CONFIG_NLS_CODEPAGE_855 is not set # CONFIG_NLS_CODEPAGE_857 is not set # CONFIG_NLS_CODEPAGE_860 is not set # CONFIG_NLS_CODEPAGE_861 is not set # CONFIG_NLS_CODEPAGE_862 is not set # CONFIG_NLS_CODEPAGE_863 is not set # CONFIG_NLS_CODEPAGE_864 is not set # CONFIG_NLS_CODEPAGE_865 is not set # CONFIG_NLS_CODEPAGE_866 is not set # CONFIG_NLS_CODEPAGE_869 is not set # CONFIG_NLS_CODEPAGE_936 is not set # CONFIG_NLS_CODEPAGE_950 is not set # CONFIG_NLS_CODEPAGE_932 is not set # CONFIG_NLS_CODEPAGE_949 is not set # CONFIG_NLS_CODEPAGE_874 is not set # CONFIG_NLS_ISO8859_8 is not set # CONFIG_NLS_CODEPAGE_1250 is not set # CONFIG_NLS_CODEPAGE_1251 is not set CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y # CONFIG_NLS_ISO8859_2 is not set # CONFIG_NLS_ISO8859_3 is not set # CONFIG_NLS_ISO8859_4 is not set # CONFIG_NLS_ISO8859_5 is not set # CONFIG_NLS_ISO8859_6 is not set # CONFIG_NLS_ISO8859_7 is not set # CONFIG_NLS_ISO8859_9 is not set # CONFIG_NLS_ISO8859_13 is not set # CONFIG_NLS_ISO8859_14 is not set # CONFIG_NLS_ISO8859_15 is not set # CONFIG_NLS_KOI8_R is not set # CONFIG_NLS_KOI8_U is not set # CONFIG_NLS_MAC_ROMAN is not set # CONFIG_NLS_MAC_CELTIC is not set # CONFIG_NLS_MAC_CENTEURO is not set # CONFIG_NLS_MAC_CROATIAN is not set # CONFIG_NLS_MAC_CYRILLIC is not set # CONFIG_NLS_MAC_GAELIC is not set # CONFIG_NLS_MAC_GREEK is not set # CONFIG_NLS_MAC_ICELAND is not set # CONFIG_NLS_MAC_INUIT is not set # CONFIG_NLS_MAC_ROMANIAN is not set # CONFIG_NLS_MAC_TURKISH is not set CONFIG_NLS_UTF8=y # CONFIG_DLM is not set # CONFIG_UNICODE is not set CONFIG_IO_WQ=y # end of File systems # # Security options # CONFIG_KEYS=y # CONFIG_KEYS_REQUEST_CACHE is not set # CONFIG_PERSISTENT_KEYRINGS is not set # CONFIG_BIG_KEYS is not set # CONFIG_TRUSTED_KEYS is not set # CONFIG_ENCRYPTED_KEYS is not set # CONFIG_KEY_DH_OPERATIONS is not set # CONFIG_SECURITY_DMESG_RESTRICT is not set CONFIG_PROC_MEM_ALWAYS_FORCE=y # CONFIG_PROC_MEM_FORCE_PTRACE is not set # CONFIG_PROC_MEM_NO_FORCE is not set # CONFIG_MSEAL_SYSTEM_MAPPINGS is not set CONFIG_SECURITY=y CONFIG_HAS_SECURITY_AUDIT=y CONFIG_SECURITYFS=y CONFIG_SECURITY_NETWORK=y # CONFIG_SECURITY_INFINIBAND is not set # CONFIG_SECURITY_NETWORK_XFRM is not set # CONFIG_SECURITY_PATH is not set # CONFIG_INTEL_TXT is not set CONFIG_LSM_MMAP_MIN_ADDR=65536 # CONFIG_STATIC_USERMODEHELPER is not set CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DEVELOP=y CONFIG_SECURITY_SELINUX_AVC_STATS=y CONFIG_SECURITY_SELINUX_SIDTAB_HASH_BITS=9 CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE=256 CONFIG_SECURITY_SELINUX_AVC_HASH_BITS=9 # CONFIG_SECURITY_SELINUX_DEBUG is not set # CONFIG_SECURITY_SMACK is not set # CONFIG_SECURITY_TOMOYO is not set # CONFIG_SECURITY_APPARMOR is not set # CONFIG_SECURITY_LOADPIN is not set # CONFIG_SECURITY_YAMA is not set # CONFIG_SECURITY_SAFESETID is not set # CONFIG_SECURITY_LOCKDOWN_LSM is not set # CONFIG_SECURITY_LANDLOCK is not set # CONFIG_SECURITY_IPE is not set CONFIG_INTEGRITY=y # CONFIG_INTEGRITY_SIGNATURE is not set CONFIG_INTEGRITY_AUDIT=y # CONFIG_IMA is not set # CONFIG_EVM is not set CONFIG_DEFAULT_SECURITY_SELINUX=y # CONFIG_DEFAULT_SECURITY_DAC is not set CONFIG_LSM="landlock,lockdown,yama,loadpin,safesetid,selinux,smack,tomoyo,apparmor,ipe,bpf" # # Kernel hardening options # # # Memory initialization # CONFIG_CC_HAS_AUTO_VAR_INIT_PATTERN=y CONFIG_CC_HAS_AUTO_VAR_INIT_ZERO_BARE=y CONFIG_CC_HAS_AUTO_VAR_INIT_ZERO=y # CONFIG_INIT_STACK_NONE is not set # CONFIG_INIT_STACK_ALL_PATTERN is not set CONFIG_INIT_STACK_ALL_ZERO=y CONFIG_CC_HAS_SANCOV_STACK_DEPTH_CALLBACK=y # CONFIG_KSTACK_ERASE is not set CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y # CONFIG_INIT_ON_FREE_DEFAULT_ON is not set CONFIG_CC_HAS_ZERO_CALL_USED_REGS=y # CONFIG_ZERO_CALL_USED_REGS is not set # end of Memory initialization # # Bounds checking # CONFIG_FORTIFY_SOURCE=y CONFIG_HARDENED_USERCOPY=y # CONFIG_HARDENED_USERCOPY_DEFAULT_ON is not set # end of Bounds checking # # Hardening of kernel data structures # CONFIG_LIST_HARDENED=y CONFIG_BUG_ON_DATA_CORRUPTION=y # end of Hardening of kernel data structures CONFIG_CC_HAS_RANDSTRUCT=y CONFIG_RANDSTRUCT_NONE=y # CONFIG_RANDSTRUCT_FULL is not set # end of Kernel hardening options # end of Security options CONFIG_CRYPTO=y # # Crypto core or helper # CONFIG_CRYPTO_ALGAPI=y CONFIG_CRYPTO_ALGAPI2=y CONFIG_CRYPTO_AEAD=y CONFIG_CRYPTO_AEAD2=y CONFIG_CRYPTO_SIG=y CONFIG_CRYPTO_SIG2=y CONFIG_CRYPTO_SKCIPHER=y CONFIG_CRYPTO_SKCIPHER2=y CONFIG_CRYPTO_HASH=y CONFIG_CRYPTO_HASH2=y CONFIG_CRYPTO_RNG=y CONFIG_CRYPTO_RNG2=y CONFIG_CRYPTO_AKCIPHER2=y CONFIG_CRYPTO_AKCIPHER=y CONFIG_CRYPTO_KPP2=y CONFIG_CRYPTO_KPP=y CONFIG_CRYPTO_ACOMP2=y CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_MANAGER2=y # CONFIG_CRYPTO_USER is not set # CONFIG_CRYPTO_SELFTESTS is not set # CONFIG_CRYPTO_NULL is not set # CONFIG_CRYPTO_PCRYPT is not set # CONFIG_CRYPTO_CRYPTD is not set CONFIG_CRYPTO_AUTHENC=y CONFIG_CRYPTO_KRB5ENC=y # CONFIG_CRYPTO_BENCHMARK is not set # end of Crypto core or helper # # Public-key cryptography # CONFIG_CRYPTO_RSA=y # CONFIG_CRYPTO_DH is not set CONFIG_CRYPTO_ECC=y CONFIG_CRYPTO_ECDH=y # CONFIG_CRYPTO_ECDSA is not set # CONFIG_CRYPTO_ECRDSA is not set # CONFIG_CRYPTO_MLDSA is not set # end of Public-key cryptography # # Block ciphers # CONFIG_CRYPTO_AES=y # CONFIG_CRYPTO_ARIA is not set # CONFIG_CRYPTO_BLOWFISH is not set CONFIG_CRYPTO_CAMELLIA=y # CONFIG_CRYPTO_CAST5 is not set # CONFIG_CRYPTO_CAST6 is not set # CONFIG_CRYPTO_DES is not set CONFIG_CRYPTO_FCRYPT=y # CONFIG_CRYPTO_SERPENT is not set # CONFIG_CRYPTO_SM4_GENERIC is not set # CONFIG_CRYPTO_TWOFISH is not set # end of Block ciphers # # Length-preserving ciphers and modes # # CONFIG_CRYPTO_ADIANTUM is not set # CONFIG_CRYPTO_CHACHA20 is not set CONFIG_CRYPTO_CBC=y CONFIG_CRYPTO_CTR=y CONFIG_CRYPTO_CTS=y CONFIG_CRYPTO_ECB=y # CONFIG_CRYPTO_HCTR2 is not set # CONFIG_CRYPTO_LRW is not set CONFIG_CRYPTO_PCBC=y # CONFIG_CRYPTO_XTS is not set # end of Length-preserving ciphers and modes # # AEAD (authenticated encryption with associated data) ciphers # # CONFIG_CRYPTO_AEGIS128 is not set # CONFIG_CRYPTO_CHACHA20POLY1305 is not set CONFIG_CRYPTO_CCM=y CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_GENIV=y CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_ECHAINIV=y # CONFIG_CRYPTO_ESSIV is not set # end of AEAD (authenticated encryption with associated data) ciphers # # Hashes, digests, and MACs # # CONFIG_CRYPTO_BLAKE2B is not set CONFIG_CRYPTO_CMAC=y CONFIG_CRYPTO_HMAC=y # CONFIG_CRYPTO_MD4 is not set # CONFIG_CRYPTO_MD5 is not set # CONFIG_CRYPTO_RMD160 is not set CONFIG_CRYPTO_SHA1=y CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_CRYPTO_SHA3=y # CONFIG_CRYPTO_SM3 is not set # CONFIG_CRYPTO_STREEBOG is not set # CONFIG_CRYPTO_WP512 is not set # CONFIG_CRYPTO_XCBC is not set # CONFIG_CRYPTO_XXHASH is not set # end of Hashes, digests, and MACs # # CRCs (cyclic redundancy checks) # # CONFIG_CRYPTO_CRC32C is not set # CONFIG_CRYPTO_CRC32 is not set # end of CRCs (cyclic redundancy checks) # # Compression # CONFIG_CRYPTO_DEFLATE=y CONFIG_CRYPTO_LZO=y # CONFIG_CRYPTO_842 is not set # CONFIG_CRYPTO_LZ4 is not set # CONFIG_CRYPTO_LZ4HC is not set # CONFIG_CRYPTO_ZSTD is not set # end of Compression # # Random number generation # CONFIG_CRYPTO_DRBG_MENU=y CONFIG_CRYPTO_DRBG_HMAC=y # CONFIG_CRYPTO_DRBG_HASH is not set # CONFIG_CRYPTO_DRBG_CTR is not set CONFIG_CRYPTO_DRBG=y CONFIG_CRYPTO_JITTERENTROPY=y CONFIG_CRYPTO_JITTERENTROPY_MEMORY_BLOCKS=64 CONFIG_CRYPTO_JITTERENTROPY_MEMORY_BLOCKSIZE=32 CONFIG_CRYPTO_JITTERENTROPY_OSR=1 # end of Random number generation # # Userspace interface # # CONFIG_CRYPTO_USER_API_HASH is not set # CONFIG_CRYPTO_USER_API_SKCIPHER is not set # CONFIG_CRYPTO_USER_API_RNG is not set # CONFIG_CRYPTO_USER_API_AEAD is not set # end of Userspace interface # # Accelerated Cryptographic Algorithms for CPU (x86) # # CONFIG_CRYPTO_AES_NI_INTEL is not set # CONFIG_CRYPTO_BLOWFISH_X86_64 is not set # CONFIG_CRYPTO_CAMELLIA_X86_64 is not set # CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64 is not set # CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64 is not set # CONFIG_CRYPTO_CAST5_AVX_X86_64 is not set # CONFIG_CRYPTO_CAST6_AVX_X86_64 is not set # CONFIG_CRYPTO_SERPENT_SSE2_X86_64 is not set # CONFIG_CRYPTO_SERPENT_AVX_X86_64 is not set # CONFIG_CRYPTO_SERPENT_AVX2_X86_64 is not set # CONFIG_CRYPTO_SM4_AESNI_AVX_X86_64 is not set # CONFIG_CRYPTO_SM4_AESNI_AVX2_X86_64 is not set # CONFIG_CRYPTO_TWOFISH_X86_64 is not set # CONFIG_CRYPTO_TWOFISH_X86_64_3WAY is not set # CONFIG_CRYPTO_TWOFISH_AVX_X86_64 is not set # CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64 is not set # CONFIG_CRYPTO_ARIA_AESNI_AVX2_X86_64 is not set # CONFIG_CRYPTO_ARIA_GFNI_AVX512_X86_64 is not set # CONFIG_CRYPTO_AEGIS128_AESNI_SSE2 is not set # end of Accelerated Cryptographic Algorithms for CPU (x86) CONFIG_CRYPTO_HW=y # CONFIG_CRYPTO_DEV_PADLOCK is not set # CONFIG_CRYPTO_DEV_ATMEL_ECC is not set # CONFIG_CRYPTO_DEV_ATMEL_SHA204A is not set CONFIG_CRYPTO_DEV_CCP=y CONFIG_CRYPTO_DEV_CCP_DD=y # CONFIG_CRYPTO_DEV_SP_CCP is not set CONFIG_CRYPTO_DEV_SP_PSP=y # CONFIG_CRYPTO_DEV_NITROX_CNN55XX is not set # CONFIG_CRYPTO_DEV_QAT_DH895xCC is not set # CONFIG_CRYPTO_DEV_QAT_C3XXX is not set # CONFIG_CRYPTO_DEV_QAT_C62X is not set # CONFIG_CRYPTO_DEV_QAT_4XXX is not set # CONFIG_CRYPTO_DEV_QAT_420XX is not set # CONFIG_CRYPTO_DEV_QAT_6XXX is not set # CONFIG_CRYPTO_DEV_QAT_DH895xCCVF is not set # CONFIG_CRYPTO_DEV_QAT_C3XXXVF is not set # CONFIG_CRYPTO_DEV_QAT_C62XVF is not set # CONFIG_CRYPTO_DEV_VIRTIO is not set # CONFIG_CRYPTO_DEV_SAFEXCEL is not set # CONFIG_CRYPTO_DEV_CCREE is not set # CONFIG_CRYPTO_DEV_AMLOGIC_GXL is not set CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y CONFIG_X509_CERTIFICATE_PARSER=y # CONFIG_PKCS8_PRIVATE_KEY_PARSER is not set CONFIG_PKCS7_MESSAGE_PARSER=y # CONFIG_PKCS7_TEST_KEY is not set # CONFIG_SIGNED_PE_FILE_VERIFICATION is not set # CONFIG_FIPS_SIGNATURE_SELFTEST is not set # # Certificates for signature checking # CONFIG_SYSTEM_TRUSTED_KEYRING=y CONFIG_SYSTEM_TRUSTED_KEYS="" # CONFIG_SYSTEM_EXTRA_CERTIFICATE is not set # CONFIG_SECONDARY_TRUSTED_KEYRING is not set # CONFIG_SYSTEM_BLACKLIST_KEYRING is not set CONFIG_OPENSSL_SUPPORTS_ML_DSA=y # end of Certificates for signature checking CONFIG_CRYPTO_KRB5=y # CONFIG_CRYPTO_KRB5_SELFTESTS is not set CONFIG_BINARY_PRINTF=y # # Library routines # CONFIG_LINEAR_RANGES=y # CONFIG_PACKING is not set CONFIG_BITREVERSE=y CONFIG_GENERIC_STRNCPY_FROM_USER=y CONFIG_GENERIC_STRNLEN_USER=y CONFIG_GENERIC_NET_UTILS=y # CONFIG_CORDIC is not set # CONFIG_PRIME_NUMBERS is not set CONFIG_RATIONAL=y CONFIG_GENERIC_IOMAP=y CONFIG_ARCH_USE_CMPXCHG_LOCKREF=y CONFIG_ARCH_HAS_FAST_MULTIPLIER=y CONFIG_ARCH_USE_SYM_ANNOTATIONS=y CONFIG_CRC8=y CONFIG_CRC16=y CONFIG_CRC_CCITT=y CONFIG_CRC_ITU_T=y CONFIG_CRC_T10DIF=y CONFIG_CRC_T10DIF_ARCH=y CONFIG_CRC32=y CONFIG_CRC32_ARCH=y CONFIG_CRC_OPTIMIZATIONS=y CONFIG_CRYPTO_HASH_INFO=y CONFIG_CRYPTO_LIB_UTILS=y CONFIG_CRYPTO_LIB_AES=y CONFIG_CRYPTO_LIB_AES_ARCH=y CONFIG_CRYPTO_LIB_AES_CBC_MACS=y CONFIG_CRYPTO_LIB_ARC4=y CONFIG_CRYPTO_LIB_BLAKE2S_ARCH=y CONFIG_CRYPTO_LIB_CHACHA=y CONFIG_CRYPTO_LIB_CHACHA_ARCH=y CONFIG_CRYPTO_LIB_CURVE25519=y CONFIG_CRYPTO_LIB_CURVE25519_ARCH=y CONFIG_CRYPTO_LIB_CURVE25519_GENERIC=y CONFIG_CRYPTO_LIB_GF128HASH=y CONFIG_CRYPTO_LIB_GF128HASH_ARCH=y CONFIG_CRYPTO_LIB_MD5=y CONFIG_CRYPTO_LIB_POLY1305=y CONFIG_CRYPTO_LIB_POLY1305_ARCH=y CONFIG_CRYPTO_LIB_POLY1305_RSIZE=11 CONFIG_CRYPTO_LIB_CHACHA20POLY1305=y CONFIG_CRYPTO_LIB_SHA1=y CONFIG_CRYPTO_LIB_SHA1_ARCH=y CONFIG_CRYPTO_LIB_SHA256=y CONFIG_CRYPTO_LIB_SHA256_ARCH=y CONFIG_CRYPTO_LIB_SHA512=y CONFIG_CRYPTO_LIB_SHA512_ARCH=y CONFIG_CRYPTO_LIB_SHA3=y CONFIG_XXHASH=y # CONFIG_RANDOM32_SELFTEST is not set CONFIG_ZLIB_INFLATE=y CONFIG_ZLIB_DEFLATE=y CONFIG_LZO_COMPRESS=y CONFIG_LZO_DECOMPRESS=y CONFIG_LZ4_COMPRESS=y CONFIG_LZ4_DECOMPRESS=y CONFIG_ZSTD_COMMON=y CONFIG_ZSTD_DECOMPRESS=y CONFIG_XZ_DEC=y CONFIG_XZ_DEC_X86=y CONFIG_XZ_DEC_POWERPC=y CONFIG_XZ_DEC_ARM=y CONFIG_XZ_DEC_ARMTHUMB=y CONFIG_XZ_DEC_ARM64=y CONFIG_XZ_DEC_SPARC=y CONFIG_XZ_DEC_RISCV=y # CONFIG_XZ_DEC_MICROLZMA is not set CONFIG_XZ_DEC_BCJ=y # CONFIG_XZ_DEC_TEST is not set CONFIG_DECOMPRESS_GZIP=y CONFIG_DECOMPRESS_BZIP2=y CONFIG_DECOMPRESS_LZMA=y CONFIG_DECOMPRESS_XZ=y CONFIG_DECOMPRESS_LZO=y CONFIG_DECOMPRESS_LZ4=y CONFIG_DECOMPRESS_ZSTD=y CONFIG_GENERIC_ALLOCATOR=y CONFIG_TEXTSEARCH=y CONFIG_TEXTSEARCH_KMP=y CONFIG_TEXTSEARCH_BM=y CONFIG_TEXTSEARCH_FSM=y CONFIG_INTERVAL_TREE=y CONFIG_XARRAY_MULTI=y CONFIG_ASSOCIATIVE_ARRAY=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_IOPORT_MAP=y CONFIG_HAS_DMA=y CONFIG_DMA_OPS_HELPERS=y CONFIG_NEED_SG_DMA_FLAGS=y CONFIG_NEED_SG_DMA_LENGTH=y CONFIG_NEED_DMA_MAP_STATE=y CONFIG_ARCH_DMA_ADDR_T_64BIT=y CONFIG_DMA_DECLARE_COHERENT=y CONFIG_SWIOTLB=y # CONFIG_SWIOTLB_DYNAMIC is not set CONFIG_DMA_NEED_SYNC=y # CONFIG_DMA_RESTRICTED_POOL is not set # CONFIG_DMA_API_DEBUG is not set # CONFIG_DMA_MAP_BENCHMARK is not set CONFIG_SGL_ALLOC=y CONFIG_CHECK_SIGNATURE=y CONFIG_CPU_RMAP=y CONFIG_DQL=y CONFIG_GLOB=y CONFIG_NLATTR=y CONFIG_CLZ_TAB=y CONFIG_IRQ_POLL=y CONFIG_MPILIB=y CONFIG_DIMLIB=y CONFIG_LIBFDT=y CONFIG_OID_REGISTRY=y CONFIG_HAVE_GENERIC_VDSO=y CONFIG_GENERIC_GETTIMEOFDAY=y CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT=y CONFIG_VDSO_GETRANDOM=y CONFIG_SG_POOL=y CONFIG_ARCH_HAS_PMEM_API=y CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION=y CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE=y CONFIG_ARCH_HAS_COPY_MC=y CONFIG_ARCH_STACKWALK=y CONFIG_STACKDEPOT=y CONFIG_STACKDEPOT_MAX_FRAMES=64 CONFIG_REF_TRACKER=y CONFIG_SBITMAP=y # CONFIG_LWQ_TEST is not set # end of Library routines CONFIG_FIRMWARE_TABLE=y CONFIG_UNION_FIND=y # # Kernel hacking # # # printk and dmesg options # CONFIG_PRINTK_TIME=y CONFIG_PRINTK_CALLER=y # CONFIG_STACKTRACE_BUILD_ID is not set CONFIG_CONSOLE_LOGLEVEL_DEFAULT=7 CONFIG_CONSOLE_LOGLEVEL_QUIET=4 CONFIG_MESSAGE_LOGLEVEL_DEFAULT=4 # CONFIG_BOOT_PRINTK_DELAY is not set # CONFIG_DYNAMIC_DEBUG is not set # CONFIG_DYNAMIC_DEBUG_CORE is not set CONFIG_SYMBOLIC_ERRNAME=y CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_BUGVERBOSE_DETAILED is not set # end of printk and dmesg options CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_MISC=y # # Compile-time checks and compiler options # CONFIG_DEBUG_INFO=y CONFIG_AS_HAS_NON_CONST_ULEB128=y # CONFIG_DEBUG_INFO_NONE is not set # CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT is not set CONFIG_DEBUG_INFO_DWARF4=y # CONFIG_DEBUG_INFO_DWARF5 is not set # CONFIG_DEBUG_INFO_REDUCED is not set CONFIG_DEBUG_INFO_COMPRESSED_NONE=y # CONFIG_DEBUG_INFO_COMPRESSED_ZLIB is not set # CONFIG_DEBUG_INFO_COMPRESSED_ZSTD is not set # CONFIG_DEBUG_INFO_SPLIT is not set # CONFIG_DEBUG_INFO_BTF is not set CONFIG_PAHOLE_HAS_BTF_TAG=y CONFIG_PAHOLE_HAS_LANG_EXCLUDE=y # CONFIG_GDB_SCRIPTS is not set CONFIG_FRAME_WARN=2048 # CONFIG_STRIP_ASM_SYMS is not set # CONFIG_HEADERS_INSTALL is not set CONFIG_SECTION_MISMATCH_WARN_ONLY=y # CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B is not set CONFIG_OBJTOOL=y # CONFIG_OBJTOOL_WERROR is not set CONFIG_NOINSTR_VALIDATION=y # CONFIG_VMLINUX_MAP is not set # CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set # end of Compile-time checks and compiler options # # Generic Kernel Debugging Instruments # # CONFIG_MAGIC_SYSRQ is not set CONFIG_DEBUG_FS=y CONFIG_DEBUG_FS_ALLOW_ALL=y # CONFIG_DEBUG_FS_ALLOW_NONE is not set CONFIG_HAVE_ARCH_KGDB=y # CONFIG_KGDB is not set CONFIG_ARCH_HAS_UBSAN=y # CONFIG_UBSAN is not set CONFIG_HAVE_ARCH_KCSAN=y CONFIG_HAVE_KCSAN_COMPILER=y CONFIG_KCSAN=y CONFIG_CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE=y CONFIG_KCSAN_SELFTEST=y # CONFIG_KCSAN_EARLY_ENABLE is not set CONFIG_KCSAN_NUM_WATCHPOINTS=64 CONFIG_KCSAN_UDELAY_TASK=80 CONFIG_KCSAN_UDELAY_INTERRUPT=20 CONFIG_KCSAN_DELAY_RANDOMIZE=y CONFIG_KCSAN_SKIP_WATCH=4000 CONFIG_KCSAN_SKIP_WATCH_RANDOMIZE=y # CONFIG_KCSAN_INTERRUPT_WATCHER is not set CONFIG_KCSAN_REPORT_ONCE_IN_MS=3000 # CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN is not set # CONFIG_KCSAN_STRICT is not set CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=y # CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is not set CONFIG_KCSAN_IGNORE_ATOMICS=y CONFIG_KCSAN_PERMISSIVE=y # end of Generic Kernel Debugging Instruments # # Networking Debugging # CONFIG_NET_DEV_REFCNT_TRACKER=y CONFIG_NET_NS_REFCNT_TRACKER=y CONFIG_DEBUG_NET=y # CONFIG_DEBUG_NET_SMALL_RTNL is not set # end of Networking Debugging # # Memory Debugging # # CONFIG_PAGE_EXTENSION is not set # CONFIG_DEBUG_PAGEALLOC is not set CONFIG_SLUB_DEBUG=y # CONFIG_SLUB_DEBUG_ON is not set # CONFIG_PAGE_OWNER is not set # CONFIG_PAGE_TABLE_CHECK is not set # CONFIG_PAGE_POISONING is not set # CONFIG_DEBUG_PAGE_REF is not set # CONFIG_DEBUG_RODATA_TEST is not set CONFIG_ARCH_HAS_DEBUG_WX=y CONFIG_DEBUG_WX=y CONFIG_ARCH_HAS_PTDUMP=y CONFIG_PTDUMP=y # CONFIG_PTDUMP_DEBUGFS is not set CONFIG_HAVE_DEBUG_KMEMLEAK=y # CONFIG_DEBUG_KMEMLEAK is not set # CONFIG_PER_VMA_LOCK_STATS is not set # CONFIG_DEBUG_OBJECTS is not set # CONFIG_SHRINKER_DEBUG is not set CONFIG_DEBUG_STACK_USAGE=y CONFIG_SCHED_STACK_END_CHECK=y CONFIG_ARCH_HAS_DEBUG_VM_PGTABLE=y # CONFIG_DEBUG_VFS is not set # CONFIG_DEBUG_VM is not set # CONFIG_DEBUG_VM_PGTABLE is not set CONFIG_ARCH_HAS_DEBUG_VIRTUAL=y # CONFIG_DEBUG_VIRTUAL is not set CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_PER_CPU_MAPS is not set CONFIG_ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP=y # CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP is not set # CONFIG_MEM_ALLOC_PROFILING is not set CONFIG_HAVE_ARCH_KASAN=y CONFIG_HAVE_ARCH_KASAN_VMALLOC=y CONFIG_CC_HAS_KASAN_GENERIC=y CONFIG_CC_HAS_KASAN_SW_TAGS=y CONFIG_CC_HAS_WORKING_NOSANITIZE_ADDRESS=y # CONFIG_KASAN is not set CONFIG_HAVE_ARCH_KFENCE=y # CONFIG_KFENCE is not set CONFIG_HAVE_ARCH_KMSAN=y CONFIG_HAVE_KMSAN_COMPILER=y # end of Memory Debugging # CONFIG_DEBUG_SHIRQ is not set # # Debug Oops, Lockups and Hangs # CONFIG_PANIC_ON_OOPS=y CONFIG_PANIC_TIMEOUT=86400 # CONFIG_SOFTLOCKUP_DETECTOR is not set CONFIG_HAVE_HARDLOCKUP_DETECTOR_BUDDY=y # CONFIG_HARDLOCKUP_DETECTOR is not set CONFIG_HARDLOCKUP_CHECK_TIMESTAMP=y # CONFIG_DETECT_HUNG_TASK is not set # CONFIG_WQ_WATCHDOG is not set # CONFIG_WQ_CPU_INTENSIVE_REPORT is not set # CONFIG_TEST_LOCKUP is not set # end of Debug Oops, Lockups and Hangs # # Scheduler Debugging # CONFIG_SCHED_INFO=y CONFIG_SCHEDSTATS=y # end of Scheduler Debugging # CONFIG_DEBUG_PREEMPT is not set # CONFIG_DEBUG_ATOMIC is not set # # Lock Debugging (spinlocks, mutexes, etc...) # CONFIG_LOCK_DEBUGGING_SUPPORT=y # CONFIG_PROVE_LOCKING is not set # CONFIG_LOCK_STAT is not set # CONFIG_DEBUG_RT_MUTEXES is not set # CONFIG_DEBUG_SPINLOCK is not set # CONFIG_DEBUG_MUTEXES is not set # CONFIG_DEBUG_WW_MUTEX_SLOWPATH is not set # CONFIG_DEBUG_RWSEMS is not set # CONFIG_DEBUG_LOCK_ALLOC is not set # CONFIG_DEBUG_ATOMIC_SLEEP is not set # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set # CONFIG_LOCK_TORTURE_TEST is not set # CONFIG_WW_MUTEX_SELFTEST is not set # CONFIG_SCF_TORTURE_TEST is not set # CONFIG_CSD_LOCK_WAIT_DEBUG is not set # end of Lock Debugging (spinlocks, mutexes, etc...) CONFIG_NMI_CHECK_CPU=y # CONFIG_DEBUG_IRQFLAGS is not set CONFIG_STACKTRACE=y # CONFIG_DEBUG_KOBJECT is not set # # Debug kernel data structures # CONFIG_DEBUG_LIST=y CONFIG_DEBUG_PLIST=y # CONFIG_DEBUG_SG is not set # CONFIG_DEBUG_NOTIFIERS is not set # CONFIG_DEBUG_MAPLE_TREE is not set # end of Debug kernel data structures # # RCU Debugging # # CONFIG_RCU_SCALE_TEST is not set # CONFIG_RCU_TORTURE_TEST is not set # CONFIG_RCU_REF_SCALE_TEST is not set CONFIG_RCU_CPU_STALL_TIMEOUT=100 CONFIG_RCU_EXP_CPU_STALL_TIMEOUT=0 # CONFIG_RCU_CPU_STALL_CPUTIME is not set # CONFIG_RCU_TRACE is not set # CONFIG_RCU_EQS_DEBUG is not set # end of RCU Debugging # CONFIG_DEBUG_WQ_FORCE_RR_CPU is not set # CONFIG_CPU_HOTPLUG_STATE_CONTROL is not set # CONFIG_LATENCYTOP is not set CONFIG_USER_STACKTRACE_SUPPORT=y CONFIG_NOP_TRACER=y CONFIG_HAVE_RETHOOK=y CONFIG_HAVE_FUNCTION_TRACER=y CONFIG_HAVE_DYNAMIC_FTRACE=y CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS=y CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS=y CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS=y CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS=y CONFIG_HAVE_DYNAMIC_FTRACE_NO_PATCHABLE=y CONFIG_HAVE_DYNAMIC_FTRACE_WITH_JMP=y CONFIG_HAVE_SYSCALL_TRACEPOINTS=y CONFIG_HAVE_FENTRY=y CONFIG_HAVE_OBJTOOL_MCOUNT=y CONFIG_HAVE_OBJTOOL_NOP_MCOUNT=y CONFIG_HAVE_C_RECORDMCOUNT=y CONFIG_HAVE_BUILDTIME_MCOUNT_SORT=y CONFIG_TRACE_CLOCK=y CONFIG_RING_BUFFER=y CONFIG_EVENT_TRACING=y CONFIG_CONTEXT_SWITCH_TRACER=y CONFIG_TRACING=y CONFIG_GENERIC_TRACER=y CONFIG_TRACING_SUPPORT=y CONFIG_FTRACE=y CONFIG_TRACEFS_AUTOMOUNT_DEPRECATED=y # CONFIG_BOOTTIME_TRACING is not set # CONFIG_FUNCTION_TRACER is not set # CONFIG_STACK_TRACER is not set # CONFIG_IRQSOFF_TRACER is not set # CONFIG_PREEMPT_TRACER is not set # CONFIG_SCHED_TRACER is not set # CONFIG_HWLAT_TRACER is not set # CONFIG_OSNOISE_TRACER is not set # CONFIG_TIMERLAT_TRACER is not set # CONFIG_MMIOTRACE is not set # CONFIG_FTRACE_SYSCALLS is not set # CONFIG_TRACER_SNAPSHOT is not set CONFIG_BRANCH_PROFILE_NONE=y # CONFIG_PROFILE_ANNOTATED_BRANCHES is not set CONFIG_BLK_DEV_IO_TRACE=y CONFIG_UPROBE_EVENTS=y CONFIG_EPROBE_EVENTS=y CONFIG_BPF_EVENTS=y CONFIG_DYNAMIC_EVENTS=y CONFIG_PROBE_EVENTS=y # CONFIG_SYNTH_EVENTS is not set # CONFIG_USER_EVENTS is not set # CONFIG_HIST_TRIGGERS is not set CONFIG_TRACE_EVENT_INJECT=y # CONFIG_TRACEPOINT_BENCHMARK is not set # CONFIG_RING_BUFFER_BENCHMARK is not set # CONFIG_TRACE_EVAL_MAP_FILE is not set # CONFIG_FTRACE_STARTUP_TEST is not set # CONFIG_RING_BUFFER_STARTUP_TEST is not set # CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS is not set # CONFIG_PREEMPTIRQ_DELAY_TEST is not set # CONFIG_RV is not set # CONFIG_TRACE_REMOTE_TEST is not set CONFIG_PROVIDE_OHCI1394_DMA_INIT=y # CONFIG_SAMPLES is not set CONFIG_HAVE_SAMPLE_FTRACE_DIRECT=y CONFIG_HAVE_SAMPLE_FTRACE_DIRECT_MULTI=y CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y # CONFIG_STRICT_DEVMEM is not set # # x86 Debugging # CONFIG_EARLY_PRINTK_USB=y CONFIG_X86_VERBOSE_BOOTUP=y CONFIG_EARLY_PRINTK=y CONFIG_EARLY_PRINTK_DBGP=y # CONFIG_EARLY_PRINTK_USB_XDBC is not set # CONFIG_DEBUG_TLBFLUSH is not set CONFIG_HAVE_MMIOTRACE_SUPPORT=y # CONFIG_X86_DECODER_SELFTEST is not set CONFIG_IO_DELAY_0X80=y # CONFIG_IO_DELAY_0XED is not set # CONFIG_IO_DELAY_UDELAY is not set # CONFIG_IO_DELAY_NONE is not set CONFIG_DEBUG_BOOT_PARAMS=y # CONFIG_CPA_DEBUG is not set CONFIG_DEBUG_ENTRY=y # CONFIG_DEBUG_NMI_SELFTEST is not set CONFIG_X86_DEBUG_FPU=y # CONFIG_PUNIT_ATOM_DEBUG is not set CONFIG_UNWINDER_ORC=y # CONFIG_UNWINDER_FRAME_POINTER is not set # end of x86 Debugging # # Kernel Testing and Coverage # # CONFIG_KUNIT is not set # CONFIG_NOTIFIER_ERROR_INJECTION is not set CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y CONFIG_FAIL_PAGE_ALLOC=y CONFIG_FAULT_INJECTION_USERCOPY=y CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y # CONFIG_FAIL_MMC_REQUEST is not set # CONFIG_FAIL_SKB_REALLOC is not set CONFIG_FAULT_INJECTION_CONFIGFS=y # CONFIG_FAULT_INJECTION_STACKTRACE_FILTER is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_KCOV=y CONFIG_KCOV_ENABLE_COMPARISONS=y CONFIG_KCOV_INSTRUMENT_ALL=y CONFIG_KCOV_IRQ_AREA_SIZE=0x40000 # CONFIG_KCOV_SELFTEST is not set CONFIG_RUNTIME_TESTING_MENU=y # CONFIG_TEST_DHRY is not set # CONFIG_LKDTM is not set # CONFIG_TEST_DIV64 is not set # CONFIG_TEST_MULDIV64 is not set # CONFIG_BACKTRACE_SELF_TEST is not set # CONFIG_TEST_REF_TRACKER is not set # CONFIG_RBTREE_TEST is not set # CONFIG_REED_SOLOMON_TEST is not set # CONFIG_INTERVAL_TREE_TEST is not set # CONFIG_PERCPU_TEST is not set # CONFIG_ATOMIC64_SELFTEST is not set # CONFIG_TEST_HEXDUMP is not set # CONFIG_TEST_KSTRTOX is not set # CONFIG_TEST_BITMAP is not set # CONFIG_TEST_XARRAY is not set # CONFIG_TEST_MAPLE_TREE is not set # CONFIG_TEST_RHASHTABLE is not set # CONFIG_TEST_IDA is not set # CONFIG_TEST_LKM is not set # CONFIG_TEST_BITOPS is not set # CONFIG_TEST_VMALLOC is not set # CONFIG_TEST_WORKQUEUE is not set # CONFIG_TEST_BPF is not set # CONFIG_FIND_BIT_BENCHMARK is not set # CONFIG_TEST_FIRMWARE is not set # CONFIG_TEST_SYSCTL is not set # CONFIG_CONTEXT_ANALYSIS_TEST is not set # CONFIG_TEST_UDELAY is not set # CONFIG_TEST_STATIC_KEYS is not set # CONFIG_TEST_KMOD is not set # CONFIG_TEST_KALLSYMS is not set # CONFIG_TEST_MEMCAT_P is not set # CONFIG_TEST_MEMINIT is not set # CONFIG_TEST_FREE_PAGES is not set # CONFIG_TEST_CLOCKSOURCE_WATCHDOG is not set # CONFIG_TEST_OBJPOOL is not set CONFIG_ARCH_USE_MEMTEST=y # CONFIG_MEMTEST is not set # end of Kernel Testing and Coverage # # Rust hacking # # end of Rust hacking # end of Kernel hacking CONFIG_IO_URING_ZCRX=y CONFIG_IO_URING_BPF=y
KernelRepo	git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
ReproCID	0
ReproOpts
ReproSyzID	0
SyzkallerCommit	6ccb967e465e832a7bfd7a116ad00d52a0923a5d

DenialOfService	❌
Exploitable	❌
FilesystemTrigger	❌
NetworkTrigger	❌
PeripheralTrigger	❌
RemoteTrigger	❌
Unprivileged	❌
UserNamespace	❌
VMGuestTrigger	❌
VMHostTrigger	❌
Explanation	The reported bug is a KCSAN data-race between a write to `cpu_base->expires_next` in `hrtimer_interrupt` and a read of the same variable in `print_cpu`. Analysis: 1. Trigger mechanism: The read occurs in `print_cpu`, which is invoked by `timer_list_show`. This function is executed when reading the `/proc/timer_list` file or when triggering the SysRq-Q command. 2. Privilege level: The `/proc/timer_list` file is created with `0400` permissions (`proc_create_seq_private("timer_list", 0400, ...)`), meaning it is only readable by the global root user. Unprivileged users cannot read it. Furthermore, it is not accessible from within an unprivileged user namespace because the file is owned by the global root (UID 0), which is not mapped into the user namespace, preventing `CAP_DAC_OVERRIDE` from bypassing the permission check. SysRq triggers also require root privileges (writing to `/proc/sysrq-trigger`) or physical access. 3. Impact: The data race is completely benign. `print_cpu` reads the 8-byte `expires_next` value locklessly simply to print it for diagnostic purposes. If a concurrent write occurs, the read might fetch an intermediate or torn value, which would merely result in a garbage timestamp being printed to the seq_file. This cannot cause memory corruption, control-flow hijacking, kernel crashes, or any form of denial-of-service. Conclusion: This is a benign diagnostic data race restricted to the root user. It has no security impact, is not exploitable, and cannot be triggered by unprivileged users, network traffic, or other external vectors.