summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-06-26 15:32:39 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-06-26 15:32:39 -0700
commit2c96136a3f8dad6bfe35b003fb8b312f13a107e8 (patch)
treedcc5713059bf56cf70dfc4ec0d53ef7cbc88bcd1 /mm
parent3e5822e0f99e429fa8b03c956dad890179b5b3b1 (diff)
parent84b9b44b99780d35fe72ac63c4724f158771e898 (diff)
Merge tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 confidential computing update from Borislav Petkov: - Add support for unaccepted memory as specified in the UEFI spec v2.9. The gist of it all is that Intel TDX and AMD SEV-SNP confidential computing guests define the notion of accepting memory before using it and thus preventing a whole set of attacks against such guests like memory replay and the like. There are a couple of strategies of how memory should be accepted - the current implementation does an on-demand way of accepting. * tag 'x86_cc_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: virt: sevguest: Add CONFIG_CRYPTO dependency x86/efi: Safely enable unaccepted memory in UEFI x86/sev: Add SNP-specific unaccepted memory support x86/sev: Use large PSC requests if applicable x86/sev: Allow for use of the early boot GHCB for PSC requests x86/sev: Put PSC struct on the stack in prep for unaccepted memory support x86/sev: Fix calculation of end address based on number of pages x86/tdx: Add unaccepted memory support x86/tdx: Refactor try_accept_one() x86/tdx: Make _tdx_hypercall() and __tdx_module_call() available in boot stub efi/unaccepted: Avoid load_unaligned_zeropad() stepping into unaccepted memory efi: Add unaccepted memory support x86/boot/compressed: Handle unaccepted memory efi/libstub: Implement support for unaccepted memory efi/x86: Get full memory map in allocate_e820() mm: Add support for unaccepted memory
Diffstat (limited to 'mm')
-rw-r--r--mm/memblock.c9
-rw-r--r--mm/mm_init.c7
-rw-r--r--mm/page_alloc.c173
-rw-r--r--mm/vmstat.c3
4 files changed, 192 insertions, 0 deletions
diff --git a/mm/memblock.c b/mm/memblock.c
index 3feafea06ab2..50b921119600 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1436,6 +1436,15 @@ done:
*/
kmemleak_alloc_phys(found, size, 0);
+ /*
+ * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP,
+ * require memory to be accepted before it can be used by the
+ * guest.
+ *
+ * Accept the memory of the allocated buffer.
+ */
+ accept_memory(found, found + size);
+
return found;
}
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 7f7f9c677854..1cfc08e25f93 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1375,6 +1375,10 @@ static void __meminit zone_init_free_lists(struct zone *zone)
INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
zone->free_area[order].nr_free = 0;
}
+
+#ifdef CONFIG_UNACCEPTED_MEMORY
+ INIT_LIST_HEAD(&zone->unaccepted_pages);
+#endif
}
void __meminit init_currently_empty_zone(struct zone *zone,
@@ -1960,6 +1964,9 @@ static void __init deferred_free_range(unsigned long pfn,
return;
}
+ /* Accept chunks smaller than MAX_ORDER upfront */
+ accept_memory(PFN_PHYS(pfn), PFN_PHYS(pfn + nr_pages));
+
for (i = 0; i < nr_pages; i++, page++, pfn++) {
if (pageblock_aligned(pfn))
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 47421bedc12b..d239fba3f31c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -387,6 +387,12 @@ EXPORT_SYMBOL(nr_node_ids);
EXPORT_SYMBOL(nr_online_nodes);
#endif
+static bool page_contains_unaccepted(struct page *page, unsigned int order);
+static void accept_page(struct page *page, unsigned int order);
+static bool try_to_accept_memory(struct zone *zone, unsigned int order);
+static inline bool has_unaccepted_memory(void);
+static bool __free_unaccepted(struct page *page);
+
int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -1481,6 +1487,13 @@ void __free_pages_core(struct page *page, unsigned int order)
atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
+ if (page_contains_unaccepted(page, order)) {
+ if (order == MAX_ORDER && __free_unaccepted(page))
+ return;
+
+ accept_page(page, order);
+ }
+
/*
* Bypass PCP and place fresh pages right to the tail, primarily
* relevant for memory onlining.
@@ -3159,6 +3172,9 @@ static inline long __zone_watermark_unusable_free(struct zone *z,
if (!(alloc_flags & ALLOC_CMA))
unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
+#ifdef CONFIG_UNACCEPTED_MEMORY
+ unusable_free += zone_page_state(z, NR_UNACCEPTED);
+#endif
return unusable_free;
}
@@ -3458,6 +3474,11 @@ retry:
gfp_mask)) {
int ret;
+ if (has_unaccepted_memory()) {
+ if (try_to_accept_memory(zone, order))
+ goto try_this_zone;
+ }
+
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* Watermark failed for this zone, but see if we can
@@ -3510,6 +3531,11 @@ try_this_zone:
return page;
} else {
+ if (has_unaccepted_memory()) {
+ if (try_to_accept_memory(zone, order))
+ goto try_this_zone;
+ }
+
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/* Try again if zone has deferred pages */
if (deferred_pages_enabled()) {
@@ -7215,3 +7241,150 @@ bool has_managed_dma(void)
return false;
}
#endif /* CONFIG_ZONE_DMA */
+
+#ifdef CONFIG_UNACCEPTED_MEMORY
+
+/* Counts number of zones with unaccepted pages. */
+static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages);
+
+static bool lazy_accept = true;
+
+static int __init accept_memory_parse(char *p)
+{
+ if (!strcmp(p, "lazy")) {
+ lazy_accept = true;
+ return 0;
+ } else if (!strcmp(p, "eager")) {
+ lazy_accept = false;
+ return 0;
+ } else {
+ return -EINVAL;
+ }
+}
+early_param("accept_memory", accept_memory_parse);
+
+static bool page_contains_unaccepted(struct page *page, unsigned int order)
+{
+ phys_addr_t start = page_to_phys(page);
+ phys_addr_t end = start + (PAGE_SIZE << order);
+
+ return range_contains_unaccepted_memory(start, end);
+}
+
+static void accept_page(struct page *page, unsigned int order)
+{
+ phys_addr_t start = page_to_phys(page);
+
+ accept_memory(start, start + (PAGE_SIZE << order));
+}
+
+static bool try_to_accept_memory_one(struct zone *zone)
+{
+ unsigned long flags;
+ struct page *page;
+ bool last;
+
+ if (list_empty(&zone->unaccepted_pages))
+ return false;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ page = list_first_entry_or_null(&zone->unaccepted_pages,
+ struct page, lru);
+ if (!page) {
+ spin_unlock_irqrestore(&zone->lock, flags);
+ return false;
+ }
+
+ list_del(&page->lru);
+ last = list_empty(&zone->unaccepted_pages);
+
+ __mod_zone_freepage_state(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
+ __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ accept_page(page, MAX_ORDER);
+
+ __free_pages_ok(page, MAX_ORDER, FPI_TO_TAIL);
+
+ if (last)
+ static_branch_dec(&zones_with_unaccepted_pages);
+
+ return true;
+}
+
+static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+{
+ long to_accept;
+ int ret = false;
+
+ /* How much to accept to get to high watermark? */
+ to_accept = high_wmark_pages(zone) -
+ (zone_page_state(zone, NR_FREE_PAGES) -
+ __zone_watermark_unusable_free(zone, order, 0));
+
+ /* Accept at least one page */
+ do {
+ if (!try_to_accept_memory_one(zone))
+ break;
+ ret = true;
+ to_accept -= MAX_ORDER_NR_PAGES;
+ } while (to_accept > 0);
+
+ return ret;
+}
+
+static inline bool has_unaccepted_memory(void)
+{
+ return static_branch_unlikely(&zones_with_unaccepted_pages);
+}
+
+static bool __free_unaccepted(struct page *page)
+{
+ struct zone *zone = page_zone(page);
+ unsigned long flags;
+ bool first = false;
+
+ if (!lazy_accept)
+ return false;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ first = list_empty(&zone->unaccepted_pages);
+ list_add_tail(&page->lru, &zone->unaccepted_pages);
+ __mod_zone_freepage_state(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE);
+ __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES);
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ if (first)
+ static_branch_inc(&zones_with_unaccepted_pages);
+
+ return true;
+}
+
+#else
+
+static bool page_contains_unaccepted(struct page *page, unsigned int order)
+{
+ return false;
+}
+
+static void accept_page(struct page *page, unsigned int order)
+{
+}
+
+static bool try_to_accept_memory(struct zone *zone, unsigned int order)
+{
+ return false;
+}
+
+static inline bool has_unaccepted_memory(void)
+{
+ return false;
+}
+
+static bool __free_unaccepted(struct page *page)
+{
+ BUILD_BUG();
+ return false;
+}
+
+#endif /* CONFIG_UNACCEPTED_MEMORY */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c28046371b45..282349cabf01 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1180,6 +1180,9 @@ const char * const vmstat_text[] = {
"nr_zspages",
#endif
"nr_free_cma",
+#ifdef CONFIG_UNACCEPTED_MEMORY
+ "nr_unaccepted",
+#endif
/* enum numa_stat_item counters */
#ifdef CONFIG_NUMA