aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/core.c34
-rw-r--r--kernel/bpf/local_storage.c3
-rw-r--r--kernel/bpf/queue_stack_maps.c16
-rw-r--r--kernel/bpf/verifier.c2
-rw-r--r--kernel/debug/kdb/kdb_bt.c4
-rw-r--r--kernel/debug/kdb/kdb_io.c15
-rw-r--r--kernel/debug/kdb/kdb_keyboard.c4
-rw-r--r--kernel/debug/kdb/kdb_main.c35
-rw-r--r--kernel/debug/kdb/kdb_private.h2
-rw-r--r--kernel/debug/kdb/kdb_support.c28
-rw-r--r--kernel/dma/swiotlb.c3
-rw-r--r--kernel/events/uprobes.c12
-rw-r--r--kernel/sched/fair.c62
-rw-r--r--kernel/sched/psi.c43
-rw-r--r--kernel/trace/bpf_trace.c8
-rw-r--r--kernel/trace/ftrace.c7
-rw-r--r--kernel/trace/trace.h57
-rw-r--r--kernel/trace/trace_functions_graph.c53
-rw-r--r--kernel/trace/trace_irqsoff.c2
-rw-r--r--kernel/trace/trace_sched_wakeup.c2
20 files changed, 275 insertions, 117 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1a796e0799ec..b1a3545d0ec8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -672,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
bpf_prog_unlock_free(fp);
}
+int bpf_jit_get_func_addr(const struct bpf_prog *prog,
+ const struct bpf_insn *insn, bool extra_pass,
+ u64 *func_addr, bool *func_addr_fixed)
+{
+ s16 off = insn->off;
+ s32 imm = insn->imm;
+ u8 *addr;
+
+ *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
+ if (!*func_addr_fixed) {
+ /* Place-holder address till the last pass has collected
+ * all addresses for JITed subprograms in which case we
+ * can pick them up from prog->aux.
+ */
+ if (!extra_pass)
+ addr = NULL;
+ else if (prog->aux->func &&
+ off >= 0 && off < prog->aux->func_cnt)
+ addr = (u8 *)prog->aux->func[off]->bpf_func;
+ else
+ return -EINVAL;
+ } else {
+ /* Address of a BPF helper call. Since part of the core
+ * kernel, it's always at a fixed location. __bpf_call_base
+ * and the helper with imm relative to it are both in core
+ * kernel.
+ */
+ addr = (u8 *)__bpf_call_base + imm;
+ }
+
+ *func_addr = (unsigned long)addr;
+ return 0;
+}
+
static int bpf_jit_blind_insn(const struct bpf_insn *from,
const struct bpf_insn *aux,
struct bpf_insn *to_buff)
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c97a8f968638..bed9d48a7ae9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
return -ENOENT;
new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
- map->value_size, __GFP_ZERO | GFP_USER,
+ map->value_size,
+ __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
map->numa_node);
if (!new)
return -ENOMEM;
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8bbd72d3a121..b384ea9f3254 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -7,6 +7,7 @@
#include <linux/bpf.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/capability.h>
#include "percpu_freelist.h"
#define QUEUE_STACK_CREATE_FLAG_MASK \
@@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
/* Called from syscall */
static int queue_stack_map_alloc_check(union bpf_attr *attr)
{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 0 ||
+ attr->value_size == 0 ||
attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
return -EINVAL;
@@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
{
int ret, numa_node = bpf_map_attr_numa_node(attr);
struct bpf_queue_stack *qs;
- u32 size, value_size;
- u64 queue_size, cost;
-
- size = attr->max_entries + 1;
- value_size = attr->value_size;
-
- queue_size = sizeof(*qs) + (u64) value_size * size;
+ u64 size, queue_size, cost;
- cost = queue_size;
+ size = (u64) attr->max_entries + 1;
+ cost = queue_size = sizeof(*qs) + size * attr->value_size;
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-E2BIG);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1971ca325fb4..6dd419550aba 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5650,7 +5650,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
return;
/* NOTE: fake 'exit' subprog should be updated as well. */
for (i = 0; i <= env->subprog_cnt; i++) {
- if (env->subprog_info[i].start < off)
+ if (env->subprog_info[i].start <= off)
continue;
env->subprog_info[i].start += len - 1;
}
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index 6ad4a9fcbd6f..7921ae4fca8d 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -179,14 +179,14 @@ kdb_bt(int argc, const char **argv)
kdb_printf("no process for cpu %ld\n", cpu);
return 0;
}
- sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+ sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
kdb_parse(buf);
return 0;
}
kdb_printf("btc: cpu status: ");
kdb_parse("cpu\n");
for_each_online_cpu(cpu) {
- sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+ sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
kdb_parse(buf);
touch_nmi_watchdog();
}
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index ed5d34925ad0..6a4b41484afe 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -216,7 +216,7 @@ static char *kdb_read(char *buffer, size_t bufsize)
int count;
int i;
int diag, dtab_count;
- int key;
+ int key, buf_size, ret;
diag = kdbgetintenv("DTABCOUNT", &dtab_count);
@@ -336,9 +336,8 @@ poll_again:
else
p_tmp = tmpbuffer;
len = strlen(p_tmp);
- count = kallsyms_symbol_complete(p_tmp,
- sizeof(tmpbuffer) -
- (p_tmp - tmpbuffer));
+ buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer);
+ count = kallsyms_symbol_complete(p_tmp, buf_size);
if (tab == 2 && count > 0) {
kdb_printf("\n%d symbols are found.", count);
if (count > dtab_count) {
@@ -350,9 +349,13 @@ poll_again:
}
kdb_printf("\n");
for (i = 0; i < count; i++) {
- if (WARN_ON(!kallsyms_symbol_next(p_tmp, i)))
+ ret = kallsyms_symbol_next(p_tmp, i, buf_size);
+ if (WARN_ON(!ret))
break;
- kdb_printf("%s ", p_tmp);
+ if (ret != -E2BIG)
+ kdb_printf("%s ", p_tmp);
+ else
+ kdb_printf("%s... ", p_tmp);
*(p_tmp + len) = '\0';
}
if (i >= dtab_count)
diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c
index 118527aa60ea..750497b0003a 100644
--- a/kernel/debug/kdb/kdb_keyboard.c
+++ b/kernel/debug/kdb/kdb_keyboard.c
@@ -173,11 +173,11 @@ int kdb_get_kbd_char(void)
case KT_LATIN:
if (isprint(keychar))
break; /* printable characters */
- /* drop through */
+ /* fall through */
case KT_SPEC:
if (keychar == K_ENTER)
break;
- /* drop through */
+ /* fall through */
default:
return -1; /* ignore unprintables */
}
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index bb4fe4e1a601..d72b32c66f7d 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1192,7 +1192,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
if (reason == KDB_REASON_DEBUG) {
/* special case below */
} else {
- kdb_printf("\nEntering kdb (current=0x%p, pid %d) ",
+ kdb_printf("\nEntering kdb (current=0x%px, pid %d) ",
kdb_current, kdb_current ? kdb_current->pid : 0);
#if defined(CONFIG_SMP)
kdb_printf("on processor %d ", raw_smp_processor_id());
@@ -1208,7 +1208,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
*/
switch (db_result) {
case KDB_DB_BPT:
- kdb_printf("\nEntering kdb (0x%p, pid %d) ",
+ kdb_printf("\nEntering kdb (0x%px, pid %d) ",
kdb_current, kdb_current->pid);
#if defined(CONFIG_SMP)
kdb_printf("on processor %d ", raw_smp_processor_id());
@@ -1493,6 +1493,7 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr,
char cbuf[32];
char *c = cbuf;
int i;
+ int j;
unsigned long word;
memset(cbuf, '\0', sizeof(cbuf));
@@ -1538,25 +1539,9 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr,
wc.word = word;
#define printable_char(c) \
({unsigned char __c = c; isascii(__c) && isprint(__c) ? __c : '.'; })
- switch (bytesperword) {
- case 8:
+ for (j = 0; j < bytesperword; j++)
*c++ = printable_char(*cp++);
- *c++ = printable_char(*cp++);
- *c++ = printable_char(*cp++);
- *c++ = printable_char(*cp++);
- addr += 4;
- case 4:
- *c++ = printable_char(*cp++);
- *c++ = printable_char(*cp++);
- addr += 2;
- case 2:
- *c++ = printable_char(*cp++);
- addr++;
- case 1:
- *c++ = printable_char(*cp++);
- addr++;
- break;
- }
+ addr += bytesperword;
#undef printable_char
}
}
@@ -2048,7 +2033,7 @@ static int kdb_lsmod(int argc, const char **argv)
if (mod->state == MODULE_STATE_UNFORMED)
continue;
- kdb_printf("%-20s%8u 0x%p ", mod->name,
+ kdb_printf("%-20s%8u 0x%px ", mod->name,
mod->core_layout.size, (void *)mod);
#ifdef CONFIG_MODULE_UNLOAD
kdb_printf("%4d ", module_refcount(mod));
@@ -2059,7 +2044,7 @@ static int kdb_lsmod(int argc, const char **argv)
kdb_printf(" (Loading)");
else
kdb_printf(" (Live)");
- kdb_printf(" 0x%p", mod->core_layout.base);
+ kdb_printf(" 0x%px", mod->core_layout.base);
#ifdef CONFIG_MODULE_UNLOAD
{
@@ -2341,7 +2326,7 @@ void kdb_ps1(const struct task_struct *p)
return;
cpu = kdb_process_cpu(p);
- kdb_printf("0x%p %8d %8d %d %4d %c 0x%p %c%s\n",
+ kdb_printf("0x%px %8d %8d %d %4d %c 0x%px %c%s\n",
(void *)p, p->pid, p->parent->pid,
kdb_task_has_cpu(p), kdb_process_cpu(p),
kdb_task_state_char(p),
@@ -2354,7 +2339,7 @@ void kdb_ps1(const struct task_struct *p)
} else {
if (KDB_TSK(cpu) != p)
kdb_printf(" Error: does not match running "
- "process table (0x%p)\n", KDB_TSK(cpu));
+ "process table (0x%px)\n", KDB_TSK(cpu));
}
}
}
@@ -2687,7 +2672,7 @@ int kdb_register_flags(char *cmd,
for_each_kdbcmd(kp, i) {
if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) {
kdb_printf("Duplicate kdb command registered: "
- "%s, func %p help %s\n", cmd, func, help);
+ "%s, func %px help %s\n", cmd, func, help);
return 1;
}
}
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 1e5a502ba4a7..2118d8258b7c 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -83,7 +83,7 @@ typedef struct __ksymtab {
unsigned long sym_start;
unsigned long sym_end;
} kdb_symtab_t;
-extern int kallsyms_symbol_next(char *prefix_name, int flag);
+extern int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size);
extern int kallsyms_symbol_complete(char *prefix_name, int max_len);
/* Exported Symbols for kernel loadable modules to use. */
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 990b3cc526c8..50bf9b119bad 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -40,7 +40,7 @@
int kdbgetsymval(const char *symname, kdb_symtab_t *symtab)
{
if (KDB_DEBUG(AR))
- kdb_printf("kdbgetsymval: symname=%s, symtab=%p\n", symname,
+ kdb_printf("kdbgetsymval: symname=%s, symtab=%px\n", symname,
symtab);
memset(symtab, 0, sizeof(*symtab));
symtab->sym_start = kallsyms_lookup_name(symname);
@@ -88,7 +88,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
char *knt1 = NULL;
if (KDB_DEBUG(AR))
- kdb_printf("kdbnearsym: addr=0x%lx, symtab=%p\n", addr, symtab);
+ kdb_printf("kdbnearsym: addr=0x%lx, symtab=%px\n", addr, symtab);
memset(symtab, 0, sizeof(*symtab));
if (addr < 4096)
@@ -149,7 +149,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
symtab->mod_name = "kernel";
if (KDB_DEBUG(AR))
kdb_printf("kdbnearsym: returns %d symtab->sym_start=0x%lx, "
- "symtab->mod_name=%p, symtab->sym_name=%p (%s)\n", ret,
+ "symtab->mod_name=%px, symtab->sym_name=%px (%s)\n", ret,
symtab->sym_start, symtab->mod_name, symtab->sym_name,
symtab->sym_name);
@@ -221,11 +221,13 @@ int kallsyms_symbol_complete(char *prefix_name, int max_len)
* Parameters:
* prefix_name prefix of a symbol name to lookup
* flag 0 means search from the head, 1 means continue search.
+ * buf_size maximum length that can be written to prefix_name
+ * buffer
* Returns:
* 1 if a symbol matches the given prefix.
* 0 if no string found
*/
-int kallsyms_symbol_next(char *prefix_name, int flag)
+int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size)
{
int prefix_len = strlen(prefix_name);
static loff_t pos;
@@ -235,10 +237,8 @@ int kallsyms_symbol_next(char *prefix_name, int flag)
pos = 0;
while ((name = kdb_walk_kallsyms(&pos))) {
- if (strncmp(name, prefix_name, prefix_len) == 0) {
- strncpy(prefix_name, name, strlen(name)+1);
- return 1;
- }
+ if (!strncmp(name, prefix_name, prefix_len))
+ return strscpy(prefix_name, name, buf_size);
}
return 0;
}
@@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size)
*word = w8;
break;
}
- /* drop through */
+ /* fall through */
default:
diag = KDB_BADWIDTH;
kdb_printf("kdb_getphysword: bad width %ld\n", (long) size);
@@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size)
*word = w8;
break;
}
- /* drop through */
+ /* fall through */
default:
diag = KDB_BADWIDTH;
kdb_printf("kdb_getword: bad width %ld\n", (long) size);
@@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size)
diag = kdb_putarea(addr, w8);
break;
}
- /* drop through */
+ /* fall through */
default:
diag = KDB_BADWIDTH;
kdb_printf("kdb_putword: bad width %ld\n", (long) size);
@@ -887,13 +887,13 @@ void debug_kusage(void)
__func__, dah_first);
if (dah_first) {
h_used = (struct debug_alloc_header *)debug_alloc_pool;
- kdb_printf("%s: h_used %p size %d\n", __func__, h_used,
+ kdb_printf("%s: h_used %px size %d\n", __func__, h_used,
h_used->size);
}
do {
h_used = (struct debug_alloc_header *)
((char *)h_free + dah_overhead + h_free->size);
- kdb_printf("%s: h_used %p size %d caller %p\n",
+ kdb_printf("%s: h_used %px size %d caller %px\n",
__func__, h_used, h_used->size, h_used->caller);
h_free = (struct debug_alloc_header *)
(debug_alloc_pool + h_free->next);
@@ -902,7 +902,7 @@ void debug_kusage(void)
((char *)h_free + dah_overhead + h_free->size);
if ((char *)h_used - debug_alloc_pool !=
sizeof(debug_alloc_pool_aligned))
- kdb_printf("%s: h_used %p size %d caller %p\n",
+ kdb_printf("%s: h_used %px size %d caller %px\n",
__func__, h_used, h_used->size, h_used->caller);
out:
spin_unlock(&dap_lock);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 5731daa09a32..045930e32c0e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -679,7 +679,8 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
}
if (!dev_is_dma_coherent(dev) &&
- (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
+ (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 &&
+ dev_addr != DIRECT_MAPPING_ERROR)
arch_sync_dma_for_device(dev, phys, size, dir);
return dev_addr;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 96d4bee83489..322e97bbb437 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -829,7 +829,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
BUG_ON((uprobe->offset & ~PAGE_MASK) +
UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
- smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+ smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
set_bit(UPROBE_COPY_INSN, &uprobe->flags);
out:
@@ -2178,10 +2178,18 @@ static void handle_swbp(struct pt_regs *regs)
* After we hit the bp, _unregister + _register can install the
* new and not-yet-analyzed uprobe at the same address, restart.
*/
- smp_rmb(); /* pairs with wmb() in install_breakpoint() */
if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
goto out;
+ /*
+ * Pairs with the smp_wmb() in prepare_uprobe().
+ *
+ * Guarantees that if we see the UPROBE_COPY_INSN bit set, then
+ * we must also see the stores to &uprobe->arch performed by the
+ * prepare_uprobe() call.
+ */
+ smp_rmb();
+
/* Tracing handlers use ->utask to communicate with fetch methods */
if (!get_utask())
goto out;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3648d0300fdf..ac855b2f4774 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5674,11 +5674,11 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
return target;
}
-static unsigned long cpu_util_wake(int cpu, struct task_struct *p);
+static unsigned long cpu_util_without(int cpu, struct task_struct *p);
-static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+static unsigned long capacity_spare_without(int cpu, struct task_struct *p)
{
- return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0);
+ return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0);
}
/*
@@ -5738,7 +5738,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
- spare_cap = capacity_spare_wake(i, p);
+ spare_cap = capacity_spare_without(i, p);
if (spare_cap > max_spare_cap)
max_spare_cap = spare_cap;
@@ -5889,8 +5889,8 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
return prev_cpu;
/*
- * We need task's util for capacity_spare_wake, sync it up to prev_cpu's
- * last_update_time.
+ * We need task's util for capacity_spare_without, sync it up to
+ * prev_cpu's last_update_time.
*/
if (!(sd_flag & SD_BALANCE_FORK))
sync_entity_load_avg(&p->se);
@@ -6216,10 +6216,19 @@ static inline unsigned long cpu_util(int cpu)
}
/*
- * cpu_util_wake: Compute CPU utilization with any contributions from
- * the waking task p removed.
+ * cpu_util_without: compute cpu utilization without any contributions from *p
+ * @cpu: the CPU which utilization is requested
+ * @p: the task which utilization should be discounted
+ *
+ * The utilization of a CPU is defined by the utilization of tasks currently
+ * enqueued on that CPU as well as tasks which are currently sleeping after an
+ * execution on that CPU.
+ *
+ * This method returns the utilization of the specified CPU by discounting the
+ * utilization of the specified task, whenever the task is currently
+ * contributing to the CPU utilization.
*/
-static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
+static unsigned long cpu_util_without(int cpu, struct task_struct *p)
{
struct cfs_rq *cfs_rq;
unsigned int util;
@@ -6231,7 +6240,7 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
cfs_rq = &cpu_rq(cpu)->cfs;
util = READ_ONCE(cfs_rq->avg.util_avg);
- /* Discount task's blocked util from CPU's util */
+ /* Discount task's util from CPU's util */
util -= min_t(unsigned int, util, task_util(p));
/*
@@ -6240,14 +6249,14 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
* a) if *p is the only task sleeping on this CPU, then:
* cpu_util (== task_util) > util_est (== 0)
* and thus we return:
- * cpu_util_wake = (cpu_util - task_util) = 0
+ * cpu_util_without = (cpu_util - task_util) = 0
*
* b) if other tasks are SLEEPING on this CPU, which is now exiting
* IDLE, then:
* cpu_util >= task_util
* cpu_util > util_est (== 0)
* and thus we discount *p's blocked utilization to return:
- * cpu_util_wake = (cpu_util - task_util) >= 0
+ * cpu_util_without = (cpu_util - task_util) >= 0
*
* c) if other tasks are RUNNABLE on that CPU and
* util_est > cpu_util
@@ -6260,8 +6269,33 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
* covered by the following code when estimated utilization is
* enabled.
*/
- if (sched_feat(UTIL_EST))
- util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued));
+ if (sched_feat(UTIL_EST)) {
+ unsigned int estimated =
+ READ_ONCE(cfs_rq->avg.util_est.enqueued);
+
+ /*
+ * Despite the following checks we still have a small window
+ * for a possible race, when an execl's select_task_rq_fair()
+ * races with LB's detach_task():
+ *
+ * detach_task()
+ * p->on_rq = TASK_ON_RQ_MIGRATING;
+ * ---------------------------------- A
+ * deactivate_task() \
+ * dequeue_task() + RaceTime
+ * util_est_dequeue() /
+ * ---------------------------------- B
+ *
+ * The additional check on "current == p" it's required to
+ * properly fix the execl regression and it helps in further
+ * reducing the chances for the above race.
+ */
+ if (unlikely(task_on_rq_queued(p) || current == p)) {
+ estimated -= min_t(unsigned int, estimated,
+ (_task_util_est(p) | UTIL_AVG_UNCHANGED));
+ }
+ util = max(util, estimated);
+ }
/*
* Utilization (estimated) can exceed the CPU capacity, thus let's
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 7cdecfc010af..3d7355d7c3e3 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -633,38 +633,39 @@ void psi_cgroup_free(struct cgroup *cgroup)
*/
void cgroup_move_task(struct task_struct *task, struct css_set *to)
{
- bool move_psi = !psi_disabled;
unsigned int task_flags = 0;
struct rq_flags rf;
struct rq *rq;
- if (move_psi) {
- rq = task_rq_lock(task, &rf);
+ if (psi_disabled) {
+ /*
+ * Lame to do this here, but the scheduler cannot be locked
+ * from the outside, so we move cgroups from inside sched/.
+ */
+ rcu_assign_pointer(task->cgroups, to);
+ return;
+ }
- if (task_on_rq_queued(task))
- task_flags = TSK_RUNNING;
- else if (task->in_iowait)
- task_flags = TSK_IOWAIT;
+ rq = task_rq_lock(task, &rf);
- if (task->flags & PF_MEMSTALL)
- task_flags |= TSK_MEMSTALL;
+ if (task_on_rq_queued(task))
+ task_flags = TSK_RUNNING;
+ else if (task->in_iowait)
+ task_flags = TSK_IOWAIT;
- if (task_flags)
- psi_task_change(task, task_flags, 0);
- }
+ if (task->flags & PF_MEMSTALL)
+ task_flags |= TSK_MEMSTALL;
- /*
- * Lame to do this here, but the scheduler cannot be locked
- * from the outside, so we move cgroups from inside sched/.
- */
+ if (task_flags)
+ psi_task_change(task, task_flags, 0);
+
+ /* See comment above */
rcu_assign_pointer(task->cgroups, to);
- if (move_psi) {
- if (task_flags)
- psi_task_change(task, 0, task_flags);
+ if (task_flags)
+ psi_task_change(task, 0, task_flags);
- task_rq_unlock(rq, task, &rf);
- }
+ task_rq_unlock(rq, task, &rf);
}
#endif /* CONFIG_CGROUPS */
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 08fcfe440c63..9864a35c8bb5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -196,11 +196,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
i++;
} else if (fmt[i] == 'p' || fmt[i] == 's') {
mod[fmt_cnt]++;
- i++;
- if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
+ /* disallow any further format extensions */
+ if (fmt[i + 1] != 0 &&
+ !isspace(fmt[i + 1]) &&
+ !ispunct(fmt[i + 1]))
return -EINVAL;
fmt_cnt++;
- if (fmt[i - 1] == 's') {
+ if (fmt[i] == 's') {
if (str_seen)
/* allow only one '%s' per fmt string */
return -EINVAL;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f536f601bd46..77734451cb05 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -817,7 +817,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static int profile_graph_entry(struct ftrace_graph_ent *trace)
{
- int index = trace->depth;
+ int index = current->curr_ret_stack;
function_profile_call(trace->func, 0, NULL, NULL);
@@ -852,7 +852,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
if (!fgraph_graph_time) {
int index;
- index = trace->depth;
+ index = current->curr_ret_stack;
/* Append this call time to the parent time to subtract */
if (index)
@@ -6814,6 +6814,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
atomic_set(&t->tracing_graph_pause, 0);
atomic_set(&t->trace_overrun, 0);
t->curr_ret_stack = -1;
+ t->curr_ret_depth = -1;
/* Make sure the tasks see the -1 first: */
smp_wmb();
t->ret_stack = ret_stack_list[start++];
@@ -7038,6 +7039,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack)
void ftrace_graph_init_idle_task(struct task_struct *t, int cpu)
{
t->curr_ret_stack = -1;
+ t->curr_ret_depth = -1;
/*
* The idle task has no parent, it either has its own
* stack or no stack at all.
@@ -7068,6 +7070,7 @@ void ftrace_graph_init_task(struct task_struct *t)
/* Make sure we do not use the parent ret_stack */
t->ret_stack = NULL;
t->curr_ret_stack = -1;
+ t->curr_ret_depth = -1;
if (ftrace_graph_active) {
struct ftrace_ret_stack *ret_stack;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3b8c0e24ab30..447bd96ee658 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -512,12 +512,44 @@ enum {
* can only be modified by current, we can reuse trace_recursion.
*/
TRACE_IRQ_BIT,
+
+ /* Set if the function is in the set_graph_function file */
+ TRACE_GRAPH_BIT,
+
+ /*
+ * In the very unlikely case that an interrupt came in
+ * at a start of graph tracing, and we want to trace
+ * the function in that interrupt, the depth can be greater
+ * than zero, because of the preempted start of a previous
+ * trace. In an even more unlikely case, depth could be 2
+ * if a softirq interrupted the start of graph tracing,
+ * followed by an interrupt preempting a start of graph
+ * tracing in the softirq, and depth can even be 3
+ * if an NMI came in at the start of an interrupt function
+ * that preempted a softirq start of a function that
+ * preempted normal context!!!! Luckily, it can't be
+ * greater than 3, so the next two bits are a mask
+ * of what the depth is when we set TRACE_GRAPH_BIT
+ */
+
+ TRACE_GRAPH_DEPTH_START_BIT,
+ TRACE_GRAPH_DEPTH_END_BIT,
};
#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0)
#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit)))
+#define trace_recursion_depth() \
+ (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3)
+#define trace_recursion_set_depth(depth) \
+ do { \
+ current->trace_recursion &= \
+ ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \
+ current->trace_recursion |= \
+ ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \
+ } while (0)
+
#define TRACE_CONTEXT_BITS 4
#define TRACE_FTRACE_START TRACE_FTRACE_BIT
@@ -843,8 +875,9 @@ extern void __trace_graph_return(struct trace_array *tr,
extern struct ftrace_hash *ftrace_graph_hash;
extern struct ftrace_hash *ftrace_graph_notrace_hash;
-static inline int ftrace_graph_addr(unsigned long addr)
+static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
{
+ unsigned long addr = trace->func;
int ret = 0;
preempt_disable_notrace();
@@ -855,6 +888,14 @@ static inline int ftrace_graph_addr(unsigned long addr)
}
if (ftrace_lookup_ip(ftrace_graph_hash, addr)) {
+
+ /*
+ * This needs to be cleared on the return functions
+ * when the depth is zero.
+ */
+ trace_recursion_set(TRACE_GRAPH_BIT);
+ trace_recursion_set_depth(trace->depth);
+
/*
* If no irqs are to be traced, but a set_graph_function
* is set, and called by an interrupt handler, we still
@@ -872,6 +913,13 @@ out:
return ret;
}
+static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace)
+{
+ if (trace_recursion_test(TRACE_GRAPH_BIT) &&
+ trace->depth == trace_recursion_depth())
+ trace_recursion_clear(TRACE_GRAPH_BIT);
+}
+
static inline int ftrace_graph_notrace_addr(unsigned long addr)
{
int ret = 0;
@@ -885,7 +933,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr)
return ret;
}
#else
-static inline int ftrace_graph_addr(unsigned long addr)
+static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace)
{
return 1;
}
@@ -894,6 +942,8 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr)
{
return 0;
}
+static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace)
+{ }
#endif /* CONFIG_DYNAMIC_FTRACE */
extern unsigned int fgraph_max_depth;
@@ -901,7 +951,8 @@ extern unsigned int fgraph_max_depth;
static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace)
{
/* trace it when it is-nested-in or is a function enabled. */
- return !(trace->depth || ftrace_graph_addr(trace->func)) ||
+ return !(trace_recursion_test(TRACE_GRAPH_BIT) ||
+ ftrace_graph_addr(trace)) ||
(trace->depth < 0) ||
(fgraph_max_depth && trace->depth >= fgraph_max_depth);
}
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 169b3c44ee97..086af4f5c3e8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -118,8 +118,8 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration,
struct trace_seq *s, u32 flags);
/* Add a function return address to the trace stack on thread info.*/
-int
-ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
+static int
+ftrace_push_return_trace(unsigned long ret, unsigned long func,
unsigned long frame_pointer, unsigned long *retp)
{
unsigned long long calltime;
@@ -177,9 +177,31 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
current->ret_stack[index].retp = retp;
#endif
- *depth = current->curr_ret_stack;
+ return 0;
+}
+
+int function_graph_enter(unsigned long ret, unsigned long func,
+ unsigned long frame_pointer, unsigned long *retp)
+{
+ struct ftrace_graph_ent trace;
+
+ trace.func = func;
+ trace.depth = ++current->curr_ret_depth;
+
+ if (ftrace_push_return_trace(ret, func,
+ frame_pointer, retp))
+ goto out;
+
+ /* Only trace if the calling function expects to */
+ if (!ftrace_graph_entry(&trace))
+ goto out_ret;
return 0;
+ out_ret:
+ current->curr_ret_stack--;
+ out:
+ current->curr_ret_depth--;
+ return -EBUSY;
}
/* Retrieve a function return address to the trace stack on thread info.*/
@@ -241,7 +263,13 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
trace->func = current->ret_stack[index].func;
trace->calltime = current->ret_stack[index].calltime;
trace->overrun = atomic_read(&current->trace_overrun);
- trace->depth = index;
+ trace->depth = current->curr_ret_depth--;
+ /*
+ * We still want to trace interrupts coming in if
+ * max_depth is set to 1. Make sure the decrement is
+ * seen before ftrace_graph_return.
+ */
+ barrier();
}
/*
@@ -255,6 +283,12 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
ftrace_pop_return_trace(&trace, &ret, frame_pointer);
trace.rettime = trace_clock_local();
+ ftrace_graph_return(&trace);
+ /*
+ * The ftrace_graph_return() may still access the current
+ * ret_stack structure, we need to make sure the update of
+ * curr_ret_stack is after that.
+ */
barrier();
current->curr_ret_stack--;
/*
@@ -267,13 +301,6 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
return ret;
}
- /*
- * The trace should run after decrementing the ret counter
- * in case an interrupt were to come in. We don't want to
- * lose the interrupt if max_depth is set.
- */
- ftrace_graph_return(&trace);
-
if (unlikely(!ret)) {
ftrace_graph_stop();
WARN_ON(1);
@@ -482,6 +509,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
int cpu;
int pc;
+ ftrace_graph_addr_finish(trace);
+
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
@@ -505,6 +534,8 @@ void set_graph_array(struct trace_array *tr)
static void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
{
+ ftrace_graph_addr_finish(trace);
+
if (tracing_thresh &&
(trace->rettime - trace->calltime < tracing_thresh))
return;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index b7357f9f82a3..98ea6d28df15 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -208,6 +208,8 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
unsigned long flags;
int pc;
+ ftrace_graph_addr_finish(trace);
+
if (!func_prolog_dec(tr, &data, &flags))
return;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index a86b303e6c67..7d04b9890755 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -270,6 +270,8 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace)
unsigned long flags;
int pc;
+ ftrace_graph_addr_finish(trace);
+
if (!func_prolog_preempt_disable(tr, &data, &pc))
return;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.