The following commit has been merged in the master branch:
commit dd161f74f8198c62f9bcf893f72c64bbb0d68b25
Merge: 5c2a430e85994f4873ea5ec42091baa1153bc731
dc208c69c033d3caba0509da1ae065d2b5ff165f
Author: Linus Torvalds <[email protected]>
Date: Thu Mar 27 15:44:34 2025 -0700
Merge tag 'trace-sorttable-v6.15' of
git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace
Pull tracing / sorttable updates from Steven Rostedt:
- Implement arm64 build time sorting of the mcount location table
When gcc is used to build arm64, the mcount_loc section is all zeros
in the vmlinux elf file. The addresses are stored in the Elf_Rela
location.
To sort at build time, an array is allocated and the addresses are
added to it via the content of the mcount_loc section as well as he
Elf_Rela data. After sorting, the information is put back into the
Elf_Rela which now has the section sorted.
- Make sorting of mcount location table for arm64 work with clang as
well
When clang is used, the mcount_loc section contains the addresses,
unlike the gcc build. An array is still created and the sorting works
for both methods.
- Remove weak functions from the mcount_loc section
Have the sorttable code pass in the data of functions defined via
'nm -S' which shows the functions as well as their sizes. Using this
information the sorttable code can determine if a function in the
mcount_loc section was weak and overridden. If the function is not
found, it is set to be zero. On boot, when the mcount_loc section is
read and the ftrace table is created, if the address in the
mcount_loc is not in the kernel core text then it is removed and not
added to the ftrace_filter_functions (the functions that can be
attached by ftrace callbacks).
- Update and fix the reporting of how much data is used for ftrace
functions
On boot, a report of how many pages were used by the ftrace table as
well as how they were grouped (the table holds a list of sections
that are groups of pages that were able to be allocated). The
removing of the weak functions required the accounting to be updated.
* tag 'trace-sorttable-v6.15' of
git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
scripts/sorttable: Allow matches to functions before function entry
scripts/sorttable: Use normal sort if theres no relocs in the mcount
section
ftrace: Check against is_kernel_text() instead of kaslr_offset()
ftrace: Test mcount_loc addr before calling ftrace_call_addr()
ftrace: Have ftrace pages output reflect freed pages
ftrace: Update the mcount_loc check of skipped entries
scripts/sorttable: Zero out weak functions in mcount_loc table
scripts/sorttable: Always use an array for the mcount_loc sorting
scripts/sorttable: Have mcount rela sort use direct values
arm64: scripts/sorttable: Implement sorting mcount_loc at boot for arm64
diff --combined arch/arm64/Kconfig
index f2d724c1dfd29,4521ecefc0312..62dc903ecc7fe
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@@ -162,7 -162,6 +162,7 @@@ config ARM6
select GENERIC_SMP_IDLE_THREAD
select GENERIC_TIME_VSYSCALL
select GENERIC_GETTIMEOFDAY
+ select GENERIC_VDSO_DATA_STORE
select GENERIC_VDSO_TIME_NS
select HARDIRQS_SW_RESEND
select HAS_IOPORT
@@@ -218,6 -217,7 +218,7 @@@
if DYNAMIC_FTRACE_WITH_ARGS
select HAVE_SAMPLE_FTRACE_DIRECT
select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
+ select HAVE_BUILDTIME_MCOUNT_SORT
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_GUP_FAST
select HAVE_FTRACE_GRAPH_FUNC
@@@ -251,7 -251,6 +252,7 @@@
select HAVE_KRETPROBES
select HAVE_GENERIC_VDSO
select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU
+ select HOTPLUG_SMT if HOTPLUG_CPU
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
select KASAN_VMALLOC if KASAN
@@@ -325,7 -324,7 +326,7 @@@ config ARCH_MMAP_RND_BITS_MI
default 18
# max bits determined by the following formula:
-# VA_BITS - PAGE_SHIFT - 3
+# VA_BITS - PTDESC_TABLE_SHIFT
config ARCH_MMAP_RND_BITS_MAX
default 19 if ARM64_VA_BITS=36
default 24 if ARM64_VA_BITS=39
@@@ -1304,15 -1303,6 +1305,15 @@@ config NVIDIA_CARMEL_CNP_ERRATU
If unsure, say Y.
+config ROCKCHIP_ERRATUM_3568002
+ bool "Rockchip 3568002: GIC600 can not access physical addresses higher
than 4GB"
+ default y
+ help
+ The Rockchip RK3566 and RK3568 GIC600 SoC integrations have AXI
+ addressing limited to the first 32bit of physical address space.
+
+ If unsure, say Y.
+
config ROCKCHIP_ERRATUM_3588001
bool "Rockchip 3588001: GIC600 can not support shareability attributes"
default y
diff --combined kernel/trace/ftrace.c
index fc88e0688daf0,bec7b5dbdb3b4..97c1be9f727ad
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@@ -540,7 -540,6 +540,7 @@@ static int function_stat_show(struct se
static struct trace_seq s;
unsigned long long avg;
unsigned long long stddev;
+ unsigned long long stddev_denom;
#endif
guard(mutex)(&ftrace_profile_lock);
@@@ -560,19 -559,23 +560,19 @@@
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
seq_puts(m, " ");
- /* Sample standard deviation (s^2) */
- if (rec->counter <= 1)
- stddev = 0;
- else {
- /*
- * Apply Welford's method:
- * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
- */
+ /*
+ * Variance formula:
+ * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
+ * Maybe Welford's method is better here?
+ * Divide only by 1000 for ns^2 -> us^2 conversion.
+ * trace_print_graph_duration will divide by 1000 again.
+ */
+ stddev = 0;
+ stddev_denom = rec->counter * (rec->counter - 1) * 1000;
+ if (stddev_denom) {
stddev = rec->counter * rec->time_squared -
rec->time * rec->time;
-
- /*
- * Divide only 1000 for ns^2 -> us^2 conversion.
- * trace_print_graph_duration will divide 1000 again.
- */
- stddev = div64_ul(stddev,
- rec->counter * (rec->counter - 1) * 1000);
+ stddev = div64_ul(stddev, stddev_denom);
}
trace_seq_init(&s);
@@@ -3217,22 -3220,15 +3217,22 @@@ static struct ftrace_hash *copy_hash(st
* The filter_hash updates uses just the append_hash() function
* and the notrace_hash does not.
*/
-static int append_hash(struct ftrace_hash **hash, struct ftrace_hash
*new_hash)
+static int append_hash(struct ftrace_hash **hash, struct ftrace_hash
*new_hash,
+ int size_bits)
{
struct ftrace_func_entry *entry;
int size;
int i;
- /* An empty hash does everything */
- if (ftrace_hash_empty(*hash))
- return 0;
+ if (*hash) {
+ /* An empty hash does everything */
+ if (ftrace_hash_empty(*hash))
+ return 0;
+ } else {
+ *hash = alloc_ftrace_hash(size_bits);
+ if (!*hash)
+ return -ENOMEM;
+ }
/* If new_hash has everything make hash have everything */
if (ftrace_hash_empty(new_hash)) {
@@@ -3296,18 -3292,16 +3296,18 @@@ static int intersect_hash(struct ftrace
/* Return a new hash that has a union of all @ops->filter_hash entries */
static struct ftrace_hash *append_hashes(struct ftrace_ops *ops)
{
- struct ftrace_hash *new_hash;
+ struct ftrace_hash *new_hash = NULL;
struct ftrace_ops *subops;
+ int size_bits;
int ret;
- new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits);
- if (!new_hash)
- return NULL;
+ if (ops->func_hash->filter_hash)
+ size_bits = ops->func_hash->filter_hash->size_bits;
+ else
+ size_bits = FTRACE_HASH_DEFAULT_BITS;
list_for_each_entry(subops, &ops->subop_list, list) {
- ret = append_hash(&new_hash, subops->func_hash->filter_hash);
+ ret = append_hash(&new_hash, subops->func_hash->filter_hash,
size_bits);
if (ret < 0) {
free_ftrace_hash(new_hash);
return NULL;
@@@ -3316,8 -3310,7 +3316,8 @@@
if (ftrace_hash_empty(new_hash))
break;
}
- return new_hash;
+ /* Can't return NULL as that means this failed */
+ return new_hash ? : EMPTY_HASH;
}
/* Make @ops trace evenything except what all its subops do not trace */
@@@ -3512,8 -3505,7 +3512,8 @@@ int ftrace_startup_subops(struct ftrace
filter_hash = alloc_and_copy_ftrace_hash(size_bits,
ops->func_hash->filter_hash);
if (!filter_hash)
return -ENOMEM;
- ret = append_hash(&filter_hash, subops->func_hash->filter_hash);
+ ret = append_hash(&filter_hash, subops->func_hash->filter_hash,
+ size_bits);
if (ret < 0) {
free_ftrace_hash(filter_hash);
return ret;
@@@ -5715,9 -5707,6 +5715,9 @@@ __ftrace_match_addr(struct ftrace_hash
return -ENOENT;
free_hash_entry(hash, entry);
return 0;
+ } else if (__ftrace_lookup_ip(hash, ip) != NULL) {
+ /* Already exists */
+ return 0;
}
entry = add_hash_entry(hash, ip);
@@@ -7016,6 -7005,7 +7016,7 @@@ static int ftrace_process_locs(struct m
unsigned long *p;
unsigned long addr;
unsigned long flags = 0; /* Shut up gcc */
+ unsigned long pages;
int ret = -ENOMEM;
count = end - start;
@@@ -7023,6 -7013,8 +7024,8 @@@
if (!count)
return 0;
+ pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE);
+
/*
* Sorting mcount in vmlinux at build time depend on
* CONFIG_BUILDTIME_MCOUNT_SORT, while mcount loc in
@@@ -7067,7 -7059,9 +7070,9 @@@
pg = start_pg;
while (p < end) {
unsigned long end_offset;
- addr = ftrace_call_adjust(*p++);
+
+ addr = *p++;
+
/*
* Some architecture linkers will pad between
* the different mcount_loc sections of different
@@@ -7079,6 -7073,19 +7084,19 @@@
continue;
}
+ /*
+ * If this is core kernel, make sure the address is in core
+ * or inittext, as weak functions get zeroed and KASLR can
+ * move them to something other than zero. It just will not
+ * move it to an area where kernel text is.
+ */
+ if (!mod && !(is_kernel_text(addr) ||
is_kernel_inittext(addr))) {
+ skipped++;
+ continue;
+ }
+
+ addr = ftrace_call_adjust(addr);
+
end_offset = (pg->index+1) * sizeof(pg->records[0]);
if (end_offset > PAGE_SIZE << pg->order) {
/* We should have allocated enough */
@@@ -7118,11 -7125,41 +7136,41 @@@
/* We should have used all pages unless we skipped some */
if (pg_unuse) {
- WARN_ON(!skipped);
+ unsigned long pg_remaining, remaining = 0;
+ unsigned long skip;
+
+ /* Count the number of entries unused and compare it to
skipped. */
+ pg_remaining = (ENTRIES_PER_PAGE << pg->order) - pg->index;
+
+ if (!WARN(skipped < pg_remaining, "Extra allocated pages for
ftrace")) {
+
+ skip = skipped - pg_remaining;
+
+ for (pg = pg_unuse; pg; pg = pg->next)
+ remaining += 1 << pg->order;
+
+ pages -= remaining;
+
+ skip = DIV_ROUND_UP(skip, ENTRIES_PER_PAGE);
+
+ /*
+ * Check to see if the number of pages remaining would
+ * just fit the number of entries skipped.
+ */
+ WARN(skip != remaining, "Extra allocated pages for
ftrace: %lu with %lu skipped",
+ remaining, skipped);
+ }
/* Need to synchronize with ftrace_location_range() */
synchronize_rcu();
ftrace_free_pages(pg_unuse);
}
+
+ if (!mod) {
+ count -= skipped;
+ pr_info("ftrace: allocating %ld entries in %ld pages\n",
+ count, pages);
+ }
+
return ret;
}
@@@ -7768,9 -7805,6 +7816,6 @@@ void __init ftrace_init(void
goto failed;
}
- pr_info("ftrace: allocating %ld entries in %ld pages\n",
- count, DIV_ROUND_UP(count, ENTRIES_PER_PAGE));
-
ret = ftrace_process_locs(NULL,
__start_mcount_loc,
__stop_mcount_loc);
diff --combined scripts/link-vmlinux.sh
index 67e66333bd2a3,59b07fe6fd004..94c78244a2b08
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@@ -144,6 -144,10 +144,6 @@@ kallsyms(
kallsymopt="${kallsymopt} --all-symbols"
fi
- if is_enabled CONFIG_KALLSYMS_ABSOLUTE_PERCPU; then
- kallsymopt="${kallsymopt} --absolute-percpu"
- fi
-
info KSYMS "${2}.S"
scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"
@@@ -173,12 -177,14 +173,14 @@@ mksysmap(
sorttable()
{
- ${objtree}/scripts/sorttable ${1}
+ ${NM} -S ${1} > .tmp_vmlinux.nm-sort
+ ${objtree}/scripts/sorttable -s .tmp_vmlinux.nm-sort ${1}
}
cleanup()
{
rm -f .btf.*
+ rm -f .tmp_vmlinux.nm-sort
rm -f System.map
rm -f vmlinux
rm -f vmlinux.map
--
LinuxNextTracking
