summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/admin-guide/cgroup-v2.rst6
-rw-r--r--fs/proc/task_mmu.c14
-rw-r--r--include/linux/mm.h5
-rw-r--r--include/linux/sched.h4
-rw-r--r--include/linux/vm_event_item.h2
-rw-r--r--kernel/sched/core.c9
-rw-r--r--kernel/sched/debug.c4
-rw-r--r--lib/alloc_tag.c3
-rw-r--r--lib/maple_tree.c1
-rw-r--r--mm/damon/core.c8
-rw-r--r--mm/hugetlb.c9
-rw-r--r--mm/kasan/report.c45
-rw-r--r--mm/memcontrol.c2
-rw-r--r--mm/migrate.c14
-rw-r--r--mm/rmap.c46
-rw-r--r--mm/vmalloc.c22
-rw-r--r--mm/vmstat.c2
-rw-r--r--samples/damon/mtier.c8
-rw-r--r--samples/damon/prcl.c8
-rw-r--r--samples/damon/wsse.c8
-rw-r--r--scripts/gdb/linux/constants.py.in7
-rw-r--r--scripts/gdb/linux/interrupts.py16
-rw-r--r--scripts/gdb/linux/mapletree.py252
-rw-r--r--scripts/gdb/linux/vfs.py2
-rw-r--r--scripts/gdb/linux/xarray.py28
-rw-r--r--tools/include/linux/kallsyms.h4
26 files changed, 399 insertions, 130 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 0cc35a14afbe..bd98ea3175ec 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1732,12 +1732,6 @@ The following nested keys are defined.
numa_hint_faults (npn)
Number of NUMA hinting faults.
- numa_task_migrated (npn)
- Number of task migration by NUMA balancing.
-
- numa_task_swapped (npn)
- Number of task swap by NUMA balancing.
-
pgdemote_kswapd
Number of pages demoted by kswapd.
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4be91eb6ea5c..751479eb128f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -36,9 +36,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
unsigned long text, lib, swap, anon, file, shmem;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
- anon = get_mm_counter(mm, MM_ANONPAGES);
- file = get_mm_counter(mm, MM_FILEPAGES);
- shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+ anon = get_mm_counter_sum(mm, MM_ANONPAGES);
+ file = get_mm_counter_sum(mm, MM_FILEPAGES);
+ shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES);
/*
* Note: to minimize their overhead, mm maintains hiwater_vm and
@@ -59,7 +59,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
text = min(text, mm->exec_vm << PAGE_SHIFT);
lib = (mm->exec_vm << PAGE_SHIFT) - text;
- swap = get_mm_counter(mm, MM_SWAPENTS);
+ swap = get_mm_counter_sum(mm, MM_SWAPENTS);
SEQ_PUT_DEC("VmPeak:\t", hiwater_vm);
SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm);
SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm);
@@ -92,12 +92,12 @@ unsigned long task_statm(struct mm_struct *mm,
unsigned long *shared, unsigned long *text,
unsigned long *data, unsigned long *resident)
{
- *shared = get_mm_counter(mm, MM_FILEPAGES) +
- get_mm_counter(mm, MM_SHMEMPAGES);
+ *shared = get_mm_counter_sum(mm, MM_FILEPAGES) +
+ get_mm_counter_sum(mm, MM_SHMEMPAGES);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = mm->data_vm + mm->stack_vm;
- *resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
+ *resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES);
return mm->total_vm;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0ef2ba0c667a..fa538feaa8d9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2568,6 +2568,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
return percpu_counter_read_positive(&mm->rss_stat[member]);
}
+static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member)
+{
+ return percpu_counter_sum_positive(&mm->rss_stat[member]);
+}
+
void mm_trace_rss_stat(struct mm_struct *mm, int member);
static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52..aa9c5be7a632 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -548,10 +548,6 @@ struct sched_statistics {
u64 nr_failed_migrations_running;
u64 nr_failed_migrations_hot;
u64 nr_forced_migrations;
-#ifdef CONFIG_NUMA_BALANCING
- u64 numa_task_migrated;
- u64 numa_task_swapped;
-#endif
u64 nr_wakeups;
u64 nr_wakeups_sync;
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 91a3ce9a2687..9e15a088ba38 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -66,8 +66,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
NUMA_HINT_FAULTS,
NUMA_HINT_FAULTS_LOCAL,
NUMA_PAGE_MIGRATE,
- NUMA_TASK_MIGRATE,
- NUMA_TASK_SWAP,
#endif
#ifdef CONFIG_MIGRATION
PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ec68fc686bd7..81c6df746df1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3362,10 +3362,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
#ifdef CONFIG_NUMA_BALANCING
static void __migrate_swap_task(struct task_struct *p, int cpu)
{
- __schedstat_inc(p->stats.numa_task_swapped);
- count_vm_numa_event(NUMA_TASK_SWAP);
- count_memcg_event_mm(p->mm, NUMA_TASK_SWAP);
-
if (task_on_rq_queued(p)) {
struct rq *src_rq, *dst_rq;
struct rq_flags srf, drf;
@@ -7939,9 +7935,8 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
return -EINVAL;
- __schedstat_inc(p->stats.numa_task_migrated);
- count_vm_numa_event(NUMA_TASK_MIGRATE);
- count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE);
+ /* TODO: This is not properly updating schedstats */
+
trace_sched_move_numa(p, curr_cpu, target_cpu);
return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9d71baf08075..557246880a7e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1210,10 +1210,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
P_SCHEDSTAT(nr_failed_migrations_running);
P_SCHEDSTAT(nr_failed_migrations_hot);
P_SCHEDSTAT(nr_forced_migrations);
-#ifdef CONFIG_NUMA_BALANCING
- P_SCHEDSTAT(numa_task_migrated);
- P_SCHEDSTAT(numa_task_swapped);
-#endif
P_SCHEDSTAT(nr_wakeups);
P_SCHEDSTAT(nr_wakeups_sync);
P_SCHEDSTAT(nr_wakeups_migrate);
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 3a74d63a959e..0142bc916f73 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -135,6 +135,9 @@ size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sl
struct codetag_bytes n;
unsigned int i, nr = 0;
+ if (IS_ERR_OR_NULL(alloc_tag_cttype))
+ return 0;
+
if (can_sleep)
codetag_lock_module_list(alloc_tag_cttype, true);
else if (!codetag_trylock_module_list(alloc_tag_cttype))
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 00524e55a21e..ef66be963798 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -5319,6 +5319,7 @@ static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt,
struct maple_enode *start;
if (mte_is_leaf(enode)) {
+ mte_set_node_dead(enode);
node->type = mte_node_type(enode);
goto free_leaf;
}
diff --git a/mm/damon/core.c b/mm/damon/core.c
index b217e0120e09..979b29e16ef4 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1449,6 +1449,7 @@ static unsigned long damon_get_intervals_score(struct damon_ctx *c)
}
}
target_access_events = max_access_events * goal_bp / 10000;
+ target_access_events = target_access_events ? : 1;
return access_events * 10000 / target_access_events;
}
@@ -2355,9 +2356,8 @@ static void kdamond_usleep(unsigned long usecs)
*
* If there is a &struct damon_call_control request that registered via
* &damon_call() on @ctx, do or cancel the invocation of the function depending
- * on @cancel. @cancel is set when the kdamond is deactivated by DAMOS
- * watermarks, or the kdamond is already out of the main loop and therefore
- * will be terminated.
+ * on @cancel. @cancel is set when the kdamond is already out of the main loop
+ * and therefore will be terminated.
*/
static void kdamond_call(struct damon_ctx *ctx, bool cancel)
{
@@ -2405,7 +2405,7 @@ static int kdamond_wait_activation(struct damon_ctx *ctx)
if (ctx->callback.after_wmarks_check &&
ctx->callback.after_wmarks_check(ctx))
break;
- kdamond_call(ctx, true);
+ kdamond_call(ctx, false);
damos_walk_cancel(ctx);
}
return -EBUSY;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9dc95eac558c..a0d285d20992 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2340,12 +2340,15 @@ struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
struct folio *folio;
spin_lock_irq(&hugetlb_lock);
+ if (!h->resv_huge_pages) {
+ spin_unlock_irq(&hugetlb_lock);
+ return NULL;
+ }
+
folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid,
nmask);
- if (folio) {
- VM_BUG_ON(!h->resv_huge_pages);
+ if (folio)
h->resv_huge_pages--;
- }
spin_unlock_irq(&hugetlb_lock);
return folio;
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 8357e1a33699..b0877035491f 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -370,36 +370,6 @@ static inline bool init_task_stack_addr(const void *addr)
sizeof(init_thread_union.stack));
}
-/*
- * This function is invoked with report_lock (a raw_spinlock) held. A
- * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping
- * rt_spinlock.
- *
- * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a
- * lockdep warning for this raw_spinlock -> spinlock dependency. This config
- * option is enabled by default to ensure better test coverage to expose this
- * kind of RT kernel problem. This lockdep splat, however, can be suppressed
- * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the
- * invalid PREEMPT_RT case has been taken care of.
- */
-static inline struct vm_struct *kasan_find_vm_area(void *addr)
-{
- static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP);
- struct vm_struct *va;
-
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- return NULL;
-
- /*
- * Suppress lockdep warning and fetch vmalloc area of the
- * offending address.
- */
- lock_map_acquire_try(&vmalloc_map);
- va = find_vm_area(addr);
- lock_map_release(&vmalloc_map);
- return va;
-}
-
static void print_address_description(void *addr, u8 tag,
struct kasan_report_info *info)
{
@@ -429,19 +399,8 @@ static void print_address_description(void *addr, u8 tag,
}
if (is_vmalloc_addr(addr)) {
- struct vm_struct *va = kasan_find_vm_area(addr);
-
- if (va) {
- pr_err("The buggy address belongs to the virtual mapping at\n"
- " [%px, %px) created by:\n"
- " %pS\n",
- va->addr, va->addr + va->size, va->caller);
- pr_err("\n");
-
- page = vmalloc_to_page(addr);
- } else {
- pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr);
- }
+ pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr);
+ page = vmalloc_to_page(addr);
}
if (page) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 902da8a9c643..70fdeda1120b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -474,8 +474,6 @@ static const unsigned int memcg_vm_event_stat[] = {
NUMA_PAGE_MIGRATE,
NUMA_PTE_UPDATES,
NUMA_HINT_FAULTS,
- NUMA_TASK_MIGRATE,
- NUMA_TASK_SWAP,
#endif
};
diff --git a/mm/migrate.c b/mm/migrate.c
index 8cf0f9c9599d..2c88f3b33833 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2399,6 +2399,7 @@ set_status:
static int get_compat_pages_array(const void __user *chunk_pages[],
const void __user * __user *pages,
+ unsigned long chunk_offset,
unsigned long chunk_nr)
{
compat_uptr_t __user *pages32 = (compat_uptr_t __user *)pages;
@@ -2406,7 +2407,7 @@ static int get_compat_pages_array(const void __user *chunk_pages[],
int i;
for (i = 0; i < chunk_nr; i++) {
- if (get_user(p, pages32 + i))
+ if (get_user(p, pages32 + chunk_offset + i))
return -EFAULT;
chunk_pages[i] = compat_ptr(p);
}
@@ -2425,27 +2426,28 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
#define DO_PAGES_STAT_CHUNK_NR 16UL
const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
int chunk_status[DO_PAGES_STAT_CHUNK_NR];
+ unsigned long chunk_offset = 0;
while (nr_pages) {
unsigned long chunk_nr = min(nr_pages, DO_PAGES_STAT_CHUNK_NR);
if (in_compat_syscall()) {
if (get_compat_pages_array(chunk_pages, pages,
- chunk_nr))
+ chunk_offset, chunk_nr))
break;
} else {
- if (copy_from_user(chunk_pages, pages,
+ if (copy_from_user(chunk_pages, pages + chunk_offset,
chunk_nr * sizeof(*chunk_pages)))
break;
}
do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);
- if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status)))
+ if (copy_to_user(status + chunk_offset, chunk_status,
+ chunk_nr * sizeof(*status)))
break;
- pages += chunk_nr;
- status += chunk_nr;
+ chunk_offset += chunk_nr;
nr_pages -= chunk_nr;
}
return nr_pages ? -EFAULT : 0;
diff --git a/mm/rmap.c b/mm/rmap.c
index fb63d9256f09..1320b88fab74 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1845,23 +1845,32 @@ void folio_remove_rmap_pud(struct folio *folio, struct page *page,
#endif
}
-/* We support batch unmapping of PTEs for lazyfree large folios */
-static inline bool can_batch_unmap_folio_ptes(unsigned long addr,
- struct folio *folio, pte_t *ptep)
+static inline unsigned int folio_unmap_pte_batch(struct folio *folio,
+ struct page_vma_mapped_walk *pvmw,
+ enum ttu_flags flags, pte_t pte)
{
const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
- int max_nr = folio_nr_pages(folio);
- pte_t pte = ptep_get(ptep);
+ unsigned long end_addr, addr = pvmw->address;
+ struct vm_area_struct *vma = pvmw->vma;
+ unsigned int max_nr;
+
+ if (flags & TTU_HWPOISON)
+ return 1;
+ if (!folio_test_large(folio))
+ return 1;
+ /* We may only batch within a single VMA and a single page table. */
+ end_addr = pmd_addr_end(addr, vma->vm_end);
+ max_nr = (end_addr - addr) >> PAGE_SHIFT;
+
+ /* We only support lazyfree batching for now ... */
if (!folio_test_anon(folio) || folio_test_swapbacked(folio))
- return false;
+ return 1;
if (pte_unused(pte))
- return false;
- if (pte_pfn(pte) != folio_pfn(folio))
- return false;
+ return 1;
- return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL,
- NULL, NULL) == max_nr;
+ return folio_pte_batch(folio, addr, pvmw->pte, pte, max_nr, fpb_flags,
+ NULL, NULL, NULL);
}
/*
@@ -2024,9 +2033,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
if (pte_dirty(pteval))
folio_mark_dirty(folio);
} else if (likely(pte_present(pteval))) {
- if (folio_test_large(folio) && !(flags & TTU_HWPOISON) &&
- can_batch_unmap_folio_ptes(address, folio, pvmw.pte))
- nr_pages = folio_nr_pages(folio);
+ nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval);
end_addr = address + nr_pages * PAGE_SIZE;
flush_cache_range(vma, address, end_addr);
@@ -2206,13 +2213,16 @@ discard:
hugetlb_remove_rmap(folio);
} else {
folio_remove_rmap_ptes(folio, subpage, nr_pages, vma);
- folio_ref_sub(folio, nr_pages - 1);
}
if (vma->vm_flags & VM_LOCKED)
mlock_drain_local();
- folio_put(folio);
- /* We have already batched the entire folio */
- if (nr_pages > 1)
+ folio_put_refs(folio, nr_pages);
+
+ /*
+ * If we are sure that we batched the entire folio and cleared
+ * all PTEs, we can just optimize and stop right here.
+ */
+ if (nr_pages == folio_nr_pages(folio))
goto walk_done;
continue;
walk_abort:
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ab986dd09b6a..6dbcdceecae1 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -514,6 +514,7 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
+ int err = 0;
pte_t *pte;
/*
@@ -530,12 +531,18 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
do {
struct page *page = pages[*nr];
- if (WARN_ON(!pte_none(ptep_get(pte))))
- return -EBUSY;
- if (WARN_ON(!page))
- return -ENOMEM;
- if (WARN_ON(!pfn_valid(page_to_pfn(page))))
- return -EINVAL;
+ if (WARN_ON(!pte_none(ptep_get(pte)))) {
+ err = -EBUSY;
+ break;
+ }
+ if (WARN_ON(!page)) {
+ err = -ENOMEM;
+ break;
+ }
+ if (WARN_ON(!pfn_valid(page_to_pfn(page)))) {
+ err = -EINVAL;
+ break;
+ }
set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
(*nr)++;
@@ -543,7 +550,8 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
arch_leave_lazy_mmu_mode();
*mask |= PGTBL_PTE_MODIFIED;
- return 0;
+
+ return err;
}
static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 429ae5339bfe..a78d70ddeacd 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1346,8 +1346,6 @@ const char * const vmstat_text[] = {
"numa_hint_faults",
"numa_hint_faults_local",
"numa_pages_migrated",
- "numa_task_migrated",
- "numa_task_swapped",
#endif
#ifdef CONFIG_MIGRATION
"pgmigrate_success",
diff --git a/samples/damon/mtier.c b/samples/damon/mtier.c
index 36d2cd933f5a..c94254b77fc9 100644
--- a/samples/damon/mtier.c
+++ b/samples/damon/mtier.c
@@ -164,8 +164,12 @@ static int damon_sample_mtier_enable_store(
if (enable == enabled)
return 0;
- if (enable)
- return damon_sample_mtier_start();
+ if (enable) {
+ err = damon_sample_mtier_start();
+ if (err)
+ enable = false;
+ return err;
+ }
damon_sample_mtier_stop();
return 0;
}
diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c
index 056b1b21a0fe..5597e6a08ab2 100644
--- a/samples/damon/prcl.c
+++ b/samples/damon/prcl.c
@@ -122,8 +122,12 @@ static int damon_sample_prcl_enable_store(
if (enable == enabled)
return 0;
- if (enable)
- return damon_sample_prcl_start();
+ if (enable) {
+ err = damon_sample_prcl_start();
+ if (err)
+ enable = false;
+ return err;
+ }
damon_sample_prcl_stop();
return 0;
}
diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c
index 11be25803274..e20238a249e7 100644
--- a/samples/damon/wsse.c
+++ b/samples/damon/wsse.c
@@ -102,8 +102,12 @@ static int damon_sample_wsse_enable_store(
if (enable == enabled)
return 0;
- if (enable)
- return damon_sample_wsse_start();
+ if (enable) {
+ err = damon_sample_wsse_start();
+ if (err)
+ enable = false;
+ return err;
+ }
damon_sample_wsse_stop();
return 0;
}
diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in
index fd6bd69c5096..f795302ddfa8 100644
--- a/scripts/gdb/linux/constants.py.in
+++ b/scripts/gdb/linux/constants.py.in
@@ -20,6 +20,7 @@
#include <linux/of_fdt.h>
#include <linux/page_ext.h>
#include <linux/radix-tree.h>
+#include <linux/maple_tree.h>
#include <linux/slab.h>
#include <linux/threads.h>
#include <linux/vmalloc.h>
@@ -93,6 +94,12 @@ LX_GDBPARSED(RADIX_TREE_MAP_SIZE)
LX_GDBPARSED(RADIX_TREE_MAP_SHIFT)
LX_GDBPARSED(RADIX_TREE_MAP_MASK)
+/* linux/maple_tree.h */
+LX_VALUE(MAPLE_NODE_SLOTS)
+LX_VALUE(MAPLE_RANGE64_SLOTS)
+LX_VALUE(MAPLE_ARANGE64_SLOTS)
+LX_GDBPARSED(MAPLE_NODE_MASK)
+
/* linux/vmalloc.h */
LX_VALUE(VM_IOREMAP)
LX_VALUE(VM_ALLOC)
diff --git a/scripts/gdb/linux/interrupts.py b/scripts/gdb/linux/interrupts.py
index 616a5f26377a..f4f715a8f0e3 100644
--- a/scripts/gdb/linux/interrupts.py
+++ b/scripts/gdb/linux/interrupts.py
@@ -7,7 +7,7 @@ import gdb
from linux import constants
from linux import cpus
from linux import utils
-from linux import radixtree
+from linux import mapletree
irq_desc_type = utils.CachedType("struct irq_desc")
@@ -23,12 +23,12 @@ def irqd_is_level(desc):
def show_irq_desc(prec, irq):
text = ""
- desc = radixtree.lookup(gdb.parse_and_eval("&irq_desc_tree"), irq)
+ desc = mapletree.mtree_load(gdb.parse_and_eval("&sparse_irqs"), irq)
if desc is None:
return text
- desc = desc.cast(irq_desc_type.get_type())
- if desc is None:
+ desc = desc.cast(irq_desc_type.get_type().pointer())
+ if desc == 0:
return text
if irq_settings_is_hidden(desc):
@@ -110,7 +110,7 @@ def x86_show_mce(prec, var, pfx, desc):
pvar = gdb.parse_and_eval(var)
text = "%*s: " % (prec, pfx)
for cpu in cpus.each_online_cpu():
- text += "%10u " % (cpus.per_cpu(pvar, cpu))
+ text += "%10u " % (cpus.per_cpu(pvar, cpu).dereference())
text += " %s\n" % (desc)
return text
@@ -142,7 +142,7 @@ def x86_show_interupts(prec):
if constants.LX_CONFIG_X86_MCE:
text += x86_show_mce(prec, "&mce_exception_count", "MCE", "Machine check exceptions")
- text == x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls")
+ text += x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls")
text += show_irq_err_count(prec)
@@ -221,8 +221,8 @@ class LxInterruptList(gdb.Command):
gdb.write("CPU%-8d" % cpu)
gdb.write("\n")
- if utils.gdb_eval_or_none("&irq_desc_tree") is None:
- return
+ if utils.gdb_eval_or_none("&sparse_irqs") is None:
+ raise gdb.GdbError("Unable to find the sparse IRQ tree, is CONFIG_SPARSE_IRQ enabled?")
for irq in range(nr_irqs):
gdb.write(show_irq_desc(prec, irq))
diff --git a/scripts/gdb/linux/mapletree.py b/scripts/gdb/linux/mapletree.py
new file mode 100644
index 000000000000..d52d51c0a03f
--- /dev/null
+++ b/scripts/gdb/linux/mapletree.py
@@ -0,0 +1,252 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Maple tree helpers
+#
+# Copyright (c) 2025 Broadcom
+#
+# Authors:
+# Florian Fainelli <florian.fainelli@broadcom.com>
+
+import gdb
+
+from linux import utils
+from linux import constants
+from linux import xarray
+
+maple_tree_root_type = utils.CachedType("struct maple_tree")
+maple_node_type = utils.CachedType("struct maple_node")
+maple_enode_type = utils.CachedType("void")
+
+maple_dense = 0
+maple_leaf_64 = 1
+maple_range_64 = 2
+maple_arange_64 = 3
+
+class Mas(object):
+ ma_active = 0
+ ma_start = 1
+ ma_root = 2
+ ma_none = 3
+ ma_pause = 4
+ ma_overflow = 5
+ ma_underflow = 6
+ ma_error = 7
+
+ def __init__(self, mt, first, end):
+ if mt.type == maple_tree_root_type.get_type().pointer():
+ self.tree = mt.dereference()
+ elif mt.type != maple_tree_root_type.get_type():
+ raise gdb.GdbError("must be {} not {}"
+ .format(maple_tree_root_type.get_type().pointer(), mt.type))
+ self.tree = mt
+ self.index = first
+ self.last = end
+ self.node = None
+ self.status = self.ma_start
+ self.min = 0
+ self.max = -1
+
+ def is_start(self):
+ # mas_is_start()
+ return self.status == self.ma_start
+
+ def is_ptr(self):
+ # mas_is_ptr()
+ return self.status == self.ma_root
+
+ def is_none(self):
+ # mas_is_none()
+ return self.status == self.ma_none
+
+ def root(self):
+ # mas_root()
+ return self.tree['ma_root'].cast(maple_enode_type.get_type().pointer())
+
+ def start(self):
+ # mas_start()
+ if self.is_start() is False:
+ return None
+
+ self.min = 0
+ self.max = ~0
+
+ while True:
+ self.depth = 0
+ root = self.root()
+ if xarray.xa_is_node(root):
+ self.depth = 0
+ self.status = self.ma_active
+ self.node = mte_safe_root(root)
+ self.offset = 0
+ if mte_dead_node(self.node) is True:
+ continue
+
+ return None
+
+ self.node = None
+ # Empty tree
+ if root is None:
+ self.status = self.ma_none
+ self.offset = constants.LX_MAPLE_NODE_SLOTS
+ return None
+
+ # Single entry tree
+ self.status = self.ma_root
+ self.offset = constants.LX_MAPLE_NODE_SLOTS
+
+ if self.index != 0:
+ return None
+
+ return root
+
+ return None
+
+ def reset(self):
+ # mas_reset()
+ self.status = self.ma_start
+ self.node = None
+
+def mte_safe_root(node):
+ if node.type != maple_enode_type.get_type().pointer():
+ raise gdb.GdbError("{} must be {} not {}"
+ .format(mte_safe_root.__name__, maple_enode_type.get_type().pointer(), node.type))
+ ulong_type = utils.get_ulong_type()
+ indirect_ptr = node.cast(ulong_type) & ~0x2
+ val = indirect_ptr.cast(maple_enode_type.get_type().pointer())
+ return val
+
+def mte_node_type(entry):
+ ulong_type = utils.get_ulong_type()
+ val = None
+ if entry.type == maple_enode_type.get_type().pointer():
+ val = entry.cast(ulong_type)
+ elif entry.type == ulong_type:
+ val = entry
+ else:
+ raise gdb.GdbError("{} must be {} not {}"
+ .format(mte_node_type.__name__, maple_enode_type.get_type().pointer(), entry.type))
+ return (val >> 0x3) & 0xf
+
+def ma_dead_node(node):
+ if node.type != maple_node_type.get_type().pointer():
+ raise gdb.GdbError("{} must be {} not {}"
+ .format(ma_dead_node.__name__, maple_node_type.get_type().pointer(), node.type))
+ ulong_type = utils.get_ulong_type()
+ parent = node['parent']
+ indirect_ptr = node['parent'].cast(ulong_type) & ~constants.LX_MAPLE_NODE_MASK
+ return indirect_ptr == node
+
+def mte_to_node(enode):
+ ulong_type = utils.get_ulong_type()
+ if enode.type == maple_enode_type.get_type().pointer():
+ indirect_ptr = enode.cast(ulong_type)
+ elif enode.type == ulong_type:
+ indirect_ptr = enode
+ else:
+ raise gdb.GdbError("{} must be {} not {}"
+ .format(mte_to_node.__name__, maple_enode_type.get_type().pointer(), enode.type))
+ indirect_ptr = indirect_ptr & ~constants.LX_MAPLE_NODE_MASK
+ return indirect_ptr.cast(maple_node_type.get_type().pointer())
+
+def mte_dead_node(enode):
+ if enode.type != maple_enode_type.get_type().pointer():
+ raise gdb.GdbError("{} must be {} not {}"
+ .format(mte_dead_node.__name__, maple_enode_type.get_type().pointer(), enode.type))
+ node = mte_to_node(enode)
+ return ma_dead_node(node)
+
+def ma_is_leaf(tp):
+ result = tp < maple_range_64
+ return tp < maple_range_64
+
+def mt_pivots(t):
+ if t == maple_dense:
+ return 0
+ elif t == maple_leaf_64 or t == maple_range_64:
+ return constants.LX_MAPLE_RANGE64_SLOTS - 1
+ elif t == maple_arange_64:
+ return constants.LX_MAPLE_ARANGE64_SLOTS - 1
+
+def ma_pivots(node, t):
+ if node.type != maple_node_type.get_type().pointer():
+ raise gdb.GdbError("{}: must be {} not {}"
+ .format(ma_pivots.__name__, maple_node_type.get_type().pointer(), node.type))
+ if t == maple_arange_64:
+ return node['ma64']['pivot']
+ elif t == maple_leaf_64 or t == maple_range_64:
+ return node['mr64']['pivot']
+ else:
+ return None
+
+def ma_slots(node, tp):
+ if node.type != maple_node_type.get_type().pointer():
+ raise gdb.GdbError("{}: must be {} not {}"
+ .format(ma_slots.__name__, maple_node_type.get_type().pointer(), node.type))
+ if tp == maple_arange_64:
+ return node['ma64']['slot']
+ elif tp == maple_range_64 or tp == maple_leaf_64:
+ return node['mr64']['slot']
+ elif tp == maple_dense:
+ return node['slot']
+ else:
+ return None
+
+def mt_slot(mt, slots, offset):
+ ulong_type = utils.get_ulong_type()
+ return slots[offset].cast(ulong_type)
+
+def mtree_lookup_walk(mas):
+ ulong_type = utils.get_ulong_type()
+ n = mas.node
+
+ while True:
+ node = mte_to_node(n)
+ tp = mte_node_type(n)
+ pivots = ma_pivots(node, tp)
+ end = mt_pivots(tp)
+ offset = 0
+ while True:
+ if pivots[offset] >= mas.index:
+ break
+ if offset >= end:
+ break
+ offset += 1
+
+ slots = ma_slots(node, tp)
+ n = mt_slot(mas.tree, slots, offset)
+ if ma_dead_node(node) is True:
+ mas.reset()
+ return None
+ break
+
+ if ma_is_leaf(tp) is True:
+ break
+
+ return n
+
+def mtree_load(mt, index):
+ ulong_type = utils.get_ulong_type()
+ # MT_STATE(...)
+ mas = Mas(mt, index, index)
+ entry = None
+
+ while True:
+ entry = mas.start()
+ if mas.is_none():
+ return None
+
+ if mas.is_ptr():
+ if index != 0:
+ entry = None
+ return entry
+
+ entry = mtree_lookup_walk(mas)
+ if entry is None and mas.is_start():
+ continue
+ else:
+ break
+
+ if xarray.xa_is_zero(entry):
+ return None
+
+ return entry
diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py
index b5fbb18ccb77..9e921b645a68 100644
--- a/scripts/gdb/linux/vfs.py
+++ b/scripts/gdb/linux/vfs.py
@@ -22,7 +22,7 @@ def dentry_name(d):
if parent == d or parent == 0:
return ""
p = dentry_name(d['d_parent']) + "/"
- return p + d['d_shortname']['string'].string()
+ return p + d['d_name']['name'].string()
class DentryName(gdb.Function):
"""Return string of the full path of a dentry.
diff --git a/scripts/gdb/linux/xarray.py b/scripts/gdb/linux/xarray.py
new file mode 100644
index 000000000000..f4477b5def75
--- /dev/null
+++ b/scripts/gdb/linux/xarray.py
@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Xarray helpers
+#
+# Copyright (c) 2025 Broadcom
+#
+# Authors:
+# Florian Fainelli <florian.fainelli@broadcom.com>
+
+import gdb
+
+from linux import utils
+from linux import constants
+
+def xa_is_internal(entry):
+ ulong_type = utils.get_ulong_type()
+ return ((entry.cast(ulong_type) & 3) == 2)
+
+def xa_mk_internal(v):
+ return ((v << 2) | 2)
+
+def xa_is_zero(entry):
+ ulong_type = utils.get_ulong_type()
+ return entry.cast(ulong_type) == xa_mk_internal(257)
+
+def xa_is_node(entry):
+ ulong_type = utils.get_ulong_type()
+ return xa_is_internal(entry) and (entry.cast(ulong_type) > 4096)
diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h
index 5a37ccbec54f..f61a01dd7eb7 100644
--- a/tools/include/linux/kallsyms.h
+++ b/tools/include/linux/kallsyms.h
@@ -18,6 +18,7 @@ static inline const char *kallsyms_lookup(unsigned long addr,
return NULL;
}
+#ifdef HAVE_BACKTRACE_SUPPORT
#include <execinfo.h>
#include <stdlib.h>
static inline void print_ip_sym(const char *loglvl, unsigned long ip)
@@ -30,5 +31,8 @@ static inline void print_ip_sym(const char *loglvl, unsigned long ip)
free(name);
}
+#else
+static inline void print_ip_sym(const char *loglvl, unsigned long ip) {}
+#endif
#endif
generated by cgit (git 2.34.1) at 2025-07-13 13:47:15 +0000