Revision 18e19f195cd888f65643a77a0c6aee8f5be6439a authored by Wei Yang on 21 February 2020, 04:04:27 UTC, committed by Linus Torvalds on 21 February 2020, 19:22:15 UTC
When we use SPARSEMEM instead of SPARSEMEM_VMEMMAP, pfn_to_page() doesn't work before sparse_init_one_section() is called. This leads to a crash when hotplug memory: BUG: unable to handle page fault for address: 0000000006400000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP PTI CPU: 3 PID: 221 Comm: kworker/u16:1 Tainted: G W 5.5.0-next-20200205+ #343 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.0.0 02/06/2015 Workqueue: kacpi_hotplug acpi_hotplug_work_fn RIP: 0010:__memset+0x24/0x30 Code: cc cc cc cc cc cc 0f 1f 44 00 00 49 89 f9 48 89 d1 83 e2 07 48 c1 e9 03 40 0f b6 f6 48 b8 01 01 01 01 01 01 01 01 48 0f af c6 <f3> 48 ab 89 d1 f3 aa 4c 89 c8 c3 90 49 89 f9 40 88 f0 48 89 d1 f3 RSP: 0018:ffffb43ac0373c80 EFLAGS: 00010a87 RAX: ffffffffffffffff RBX: ffff8a1518800000 RCX: 0000000000050000 RDX: 0000000000000000 RSI: 00000000000000ff RDI: 0000000006400000 RBP: 0000000000140000 R08: 0000000000100000 R09: 0000000006400000 R10: 0000000000000000 R11: 0000000000000002 R12: 0000000000000000 R13: 0000000000000028 R14: 0000000000000000 R15: ffff8a153ffd9280 FS: 0000000000000000(0000) GS:ffff8a153ab00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000006400000 CR3: 0000000136fca000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: sparse_add_section+0x1c9/0x26a __add_pages+0xbf/0x150 add_pages+0x12/0x60 add_memory_resource+0xc8/0x210 __add_memory+0x62/0xb0 acpi_memory_device_add+0x13f/0x300 acpi_bus_attach+0xf6/0x200 acpi_bus_scan+0x43/0x90 acpi_device_hotplug+0x275/0x3d0 acpi_hotplug_work_fn+0x1a/0x30 process_one_work+0x1a7/0x370 worker_thread+0x30/0x380 kthread+0x112/0x130 ret_from_fork+0x35/0x40 We should use memmap as it did. On x86 the impact is limited to x86_32 builds, or x86_64 configurations that override the default setting for SPARSEMEM_VMEMMAP. Other memory hotplug archs (arm64, ia64, and ppc) also default to SPARSEMEM_VMEMMAP=y. [dan.j.williams@intel.com: changelog update] {rppt@linux.ibm.com: changelog update] Link: http://lkml.kernel.org/r/20200219030454.4844-1-bhe@redhat.com Fixes: ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug") Signed-off-by: Wei Yang <richardw.yang@linux.intel.com> Signed-off-by: Baoquan He <bhe@redhat.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Baoquan He <bhe@redhat.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 76073c6
offwaketime_kern.c
/* Copyright (c) 2016 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <uapi/linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <uapi/linux/ptrace.h>
#include <uapi/linux/perf_event.h>
#include <linux/version.h>
#include <linux/sched.h>
#define _(P) ({typeof(P) val; bpf_probe_read(&val, sizeof(val), &P); val;})
#define MINBLOCK_US 1
struct key_t {
char waker[TASK_COMM_LEN];
char target[TASK_COMM_LEN];
u32 wret;
u32 tret;
};
struct bpf_map_def SEC("maps") counts = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(struct key_t),
.value_size = sizeof(u64),
.max_entries = 10000,
};
struct bpf_map_def SEC("maps") start = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = 10000,
};
struct wokeby_t {
char name[TASK_COMM_LEN];
u32 ret;
};
struct bpf_map_def SEC("maps") wokeby = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(u32),
.value_size = sizeof(struct wokeby_t),
.max_entries = 10000,
};
struct bpf_map_def SEC("maps") stackmap = {
.type = BPF_MAP_TYPE_STACK_TRACE,
.key_size = sizeof(u32),
.value_size = PERF_MAX_STACK_DEPTH * sizeof(u64),
.max_entries = 10000,
};
#define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP)
SEC("kprobe/try_to_wake_up")
int waker(struct pt_regs *ctx)
{
struct task_struct *p = (void *) PT_REGS_PARM1(ctx);
struct wokeby_t woke;
u32 pid;
pid = _(p->pid);
bpf_get_current_comm(&woke.name, sizeof(woke.name));
woke.ret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS);
bpf_map_update_elem(&wokeby, &pid, &woke, BPF_ANY);
return 0;
}
static inline int update_counts(void *ctx, u32 pid, u64 delta)
{
struct wokeby_t *woke;
u64 zero = 0, *val;
struct key_t key;
__builtin_memset(&key.waker, 0, sizeof(key.waker));
bpf_get_current_comm(&key.target, sizeof(key.target));
key.tret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS);
key.wret = 0;
woke = bpf_map_lookup_elem(&wokeby, &pid);
if (woke) {
key.wret = woke->ret;
__builtin_memcpy(&key.waker, woke->name, sizeof(key.waker));
bpf_map_delete_elem(&wokeby, &pid);
}
val = bpf_map_lookup_elem(&counts, &key);
if (!val) {
bpf_map_update_elem(&counts, &key, &zero, BPF_NOEXIST);
val = bpf_map_lookup_elem(&counts, &key);
if (!val)
return 0;
}
(*val) += delta;
return 0;
}
#if 1
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
char prev_comm[16];
int prev_pid;
int prev_prio;
long long prev_state;
char next_comm[16];
int next_pid;
int next_prio;
};
SEC("tracepoint/sched/sched_switch")
int oncpu(struct sched_switch_args *ctx)
{
/* record previous thread sleep time */
u32 pid = ctx->prev_pid;
#else
SEC("kprobe/finish_task_switch")
int oncpu(struct pt_regs *ctx)
{
struct task_struct *p = (void *) PT_REGS_PARM1(ctx);
/* record previous thread sleep time */
u32 pid = _(p->pid);
#endif
u64 delta, ts, *tsp;
ts = bpf_ktime_get_ns();
bpf_map_update_elem(&start, &pid, &ts, BPF_ANY);
/* calculate current thread's delta time */
pid = bpf_get_current_pid_tgid();
tsp = bpf_map_lookup_elem(&start, &pid);
if (!tsp)
/* missed start or filtered */
return 0;
delta = bpf_ktime_get_ns() - *tsp;
bpf_map_delete_elem(&start, &pid);
delta = delta / 1000;
if (delta < MINBLOCK_US)
return 0;
return update_counts(ctx, pid, delta);
}
char _license[] SEC("license") = "GPL";
u32 _version SEC("version") = LINUX_VERSION_CODE;
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...