[PATCH] cma: don't quit at first error when activating reserved areas

* [PATCH] cma: don't quit at first error when activating reserved areas
@ 2020-07-30 16:31 Mike Kravetz
  2020-07-30 19:16 ` Roman Gushchin
  2020-07-31  0:51 ` Song Bao Hua (Barry Song)
  0 siblings, 2 replies; 3+ messages in thread
From: Mike Kravetz @ 2020-07-30 16:31 UTC (permalink / raw)
  To: linux-mm, linux-kernel
  Cc: Marek Szyprowski, Michal Nazarewicz, Kyungmin Park, Barry Song,
	Roman Gushchin, Andrew Morton, Mike Kravetz, stable

The routine cma_init_reserved_areas is designed to activate all
reserved cma areas.  It quits when it first encounters an error.
This can leave some areas in a state where they are reserved but
not activated.  There is no feedback to code which performed the
reservation.  Attempting to allocate memory from areas in such a
state will result in a BUG.

Modify cma_init_reserved_areas to always attempt to activate all
areas.  The called routine, cma_activate_area is responsible for
leaving the area in a valid state.  No one is making active use
of returned error codes, so change the routine to void.

How to reproduce:  This example uses kernelcore, hugetlb and cma
as an easy way to reproduce.  However, this is a more general cma
issue.

Two node x86 VM 16GB total, 8GB per node
Kernel command line parameters, kernelcore=4G hugetlb_cma=8G
Related boot time messages,
  hugetlb_cma: reserve 8192 MiB, up to 4096 MiB per node
  cma: Reserved 4096 MiB at 0x0000000100000000
  hugetlb_cma: reserved 4096 MiB on node 0
  cma: Reserved 4096 MiB at 0x0000000300000000
  hugetlb_cma: reserved 4096 MiB on node 1
  cma: CMA area hugetlb could not be activated

 # echo 8 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] SMP PTI
  ...
  Call Trace:
    bitmap_find_next_zero_area_off+0x51/0x90
    cma_alloc+0x1a5/0x310
    alloc_fresh_huge_page+0x78/0x1a0
    alloc_pool_huge_page+0x6f/0xf0
    set_max_huge_pages+0x10c/0x250
    nr_hugepages_store_common+0x92/0x120
    ? __kmalloc+0x171/0x270
    kernfs_fop_write+0xc1/0x1a0
    vfs_write+0xc7/0x1f0
    ksys_write+0x5f/0xe0
    do_syscall_64+0x4d/0x90
    entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: c64be2bb1c6e ("drivers: add Contiguous Memory Allocator")
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: <stable@vger.kernel.org>
---
 mm/cma.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/mm/cma.c b/mm/cma.c
index 26ecff818881..0963c0f9c502 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -93,17 +93,15 @@ static void cma_clear_bitmap(struct cma *cma, unsigned long pfn,
 	mutex_unlock(&cma->lock);
 }
 
-static int __init cma_activate_area(struct cma *cma)
+static void __init cma_activate_area(struct cma *cma)
 {
 	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
 	unsigned i = cma->count >> pageblock_order;
 	struct zone *zone;
 
 	cma->bitmap = bitmap_zalloc(cma_bitmap_maxno(cma), GFP_KERNEL);
-	if (!cma->bitmap) {
-		cma->count = 0;
-		return -ENOMEM;
-	}
+	if (!cma->bitmap)
+		goto out_error;
 
 	WARN_ON_ONCE(!pfn_valid(pfn));
 	zone = page_zone(pfn_to_page(pfn));
@@ -133,25 +131,22 @@ static int __init cma_activate_area(struct cma *cma)
 	spin_lock_init(&cma->mem_head_lock);
 #endif
 
-	return 0;
+	return;
 
 not_in_zone:
-	pr_err("CMA area %s could not be activated\n", cma->name);
 	bitmap_free(cma->bitmap);
+out_error:
 	cma->count = 0;
-	return -EINVAL;
+	pr_err("CMA area %s could not be activated\n", cma->name);
+	return;
 }
 
 static int __init cma_init_reserved_areas(void)
 {
 	int i;
 
-	for (i = 0; i < cma_area_count; i++) {
-		int ret = cma_activate_area(&cma_areas[i]);
-
-		if (ret)
-			return ret;
-	}
+	for (i = 0; i < cma_area_count; i++)
+		cma_activate_area(&cma_areas[i]);
 
 	return 0;
 }
-- 
2.25.4



^ permalink raw reply related	[flat|nested] 3+ messages in thread