6.1-stable patches

added patches:
	mm-always-release-pages-to-the-buddy-allocator-in-memblock_free_late.patch

diff --git a/queue-6.1/mm-always-release-pages-to-the-buddy-allocator-in-memblock_free_late.patch b/queue-6.1/mm-always-release-pages-to-the-buddy-allocator-in-memblock_free_late.patch
new file mode 100644 (file)
index 0000000..46100ed
--- /dev/null
+++ b/queue-6.1/mm-always-release-pages-to-the-buddy-allocator-in-memblock_free_late.patch
@@ -0,0 +1,104 @@
+From 115d9d77bb0f9152c60b6e8646369fa7f6167593 Mon Sep 17 00:00:00 2001
+From: Aaron Thompson <dev@aaront.org>
+Date: Fri, 6 Jan 2023 22:22:44 +0000
+Subject: mm: Always release pages to the buddy allocator in memblock_free_late().
+
+From: Aaron Thompson <dev@aaront.org>
+
+commit 115d9d77bb0f9152c60b6e8646369fa7f6167593 upstream.
+
+If CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, memblock_free_pages()
+only releases pages to the buddy allocator if they are not in the
+deferred range. This is correct for free pages (as defined by
+for_each_free_mem_pfn_range_in_zone()) because free pages in the
+deferred range will be initialized and released as part of the deferred
+init process. memblock_free_pages() is called by memblock_free_late(),
+which is used to free reserved ranges after memblock_free_all() has
+run. All pages in reserved ranges have been initialized at that point,
+and accordingly, those pages are not touched by the deferred init
+process. This means that currently, if the pages that
+memblock_free_late() intends to release are in the deferred range, they
+will never be released to the buddy allocator. They will forever be
+reserved.
+
+In addition, memblock_free_pages() calls kmsan_memblock_free_pages(),
+which is also correct for free pages but is not correct for reserved
+pages. KMSAN metadata for reserved pages is initialized by
+kmsan_init_shadow(), which runs shortly before memblock_free_all().
+
+For both of these reasons, memblock_free_pages() should only be called
+for free pages, and memblock_free_late() should call __free_pages_core()
+directly instead.
+
+One case where this issue can occur in the wild is EFI boot on
+x86_64. The x86 EFI code reserves all EFI boot services memory ranges
+via memblock_reserve() and frees them later via memblock_free_late()
+(efi_reserve_boot_services() and efi_free_boot_services(),
+respectively). If any of those ranges happens to fall within the
+deferred init range, the pages will not be released and that memory will
+be unavailable.
+
+For example, on an Amazon EC2 t3.micro VM (1 GB) booting via EFI:
+
+v6.2-rc2:
+  # grep -E 'Node|spanned|present|managed' /proc/zoneinfo
+  Node 0, zone      DMA
+          spanned  4095
+          present  3999
+          managed  3840
+  Node 0, zone    DMA32
+          spanned  246652
+          present  245868
+          managed  178867
+
+v6.2-rc2 + patch:
+  # grep -E 'Node|spanned|present|managed' /proc/zoneinfo
+  Node 0, zone      DMA
+          spanned  4095
+          present  3999
+          managed  3840
+  Node 0, zone    DMA32
+          spanned  246652
+          present  245868
+          managed  222816   # +43,949 pages
+
+Fixes: 3a80a7fa7989 ("mm: meminit: initialise a subset of struct pages if CONFIG_DEFERRED_STRUCT_PAGE_INIT is set")
+Signed-off-by: Aaron Thompson <dev@aaront.org>
+Link: https://lore.kernel.org/r/01010185892de53e-e379acfb-7044-4b24-b30a-e2657c1ba989-000000@us-west-2.amazonses.com
+Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ mm/memblock.c                     |    8 +++++++-
+ tools/testing/memblock/internal.h |    4 ++++
+ 2 files changed, 11 insertions(+), 1 deletion(-)
+
+--- a/mm/memblock.c
++++ b/mm/memblock.c
+@@ -1640,7 +1640,13 @@ void __init memblock_free_late(phys_addr
+       end = PFN_DOWN(base + size);
+ 
+       for (; cursor < end; cursor++) {
+-              memblock_free_pages(pfn_to_page(cursor), cursor, 0);
++              /*
++               * Reserved pages are always initialized by the end of
++               * memblock_free_all() (by memmap_init() and, if deferred
++               * initialization is enabled, memmap_init_reserved_pages()), so
++               * these pages can be released directly to the buddy allocator.
++               */
++              __free_pages_core(pfn_to_page(cursor), 0);
+               totalram_pages_inc();
+       }
+ }
+--- a/tools/testing/memblock/internal.h
++++ b/tools/testing/memblock/internal.h
+@@ -15,6 +15,10 @@ bool mirrored_kernelcore = false;
+ 
+ struct page {};
+ 
++void __free_pages_core(struct page *page, unsigned int order)
++{
++}
++
+ void memblock_free_pages(struct page *page, unsigned long pfn,
+                        unsigned int order)
+ {

diff --git a/queue-6.1/series b/queue-6.1/series
index 8e2d043e89a58521c7c4c63a8ff0fdec9675c1d1..1830c1b059ef7f8f7bb9cce5588ef291fab25d9c 100644 (file)
--- a/queue-6.1/series
+++ b/queue-6.1/series
@@ -79,3 +79,4 @@ drm-amd-pm-enable-gpo-dynamic-control-support-for-sm.patch-18688
 drm-amdgpu-add-soc21-common-ip-block-support-for-gc-.patch
 drm-amdgpu-enable-pg-cg-flags-on-gc11_0_4-for-vcn.patch
 drm-amdgpu-enable-vcn-dpg-for-gc-ip-v11.0.4.patch
+mm-always-release-pages-to-the-buddy-allocator-in-memblock_free_late.patch