From: Junaid Shahid <junaids@google.com>
To: linux-kernel@vger.kernel.org
Cc: kvm@vger.kernel.org, pbonzini@redhat.com, jmattson@google.com,
pjt@google.com, oweisse@google.com, alexandre.chartre@oracle.com,
rppt@linux.ibm.com, dave.hansen@linux.intel.com,
peterz@infradead.org, tglx@linutronix.de, luto@kernel.org,
linux-mm@kvack.org
Subject: [RFC PATCH 10/47] mm: asi: Support for global non-sensitive direct map allocations
Date: Tue, 22 Feb 2022 21:21:46 -0800 [thread overview]
Message-ID: <20220223052223.1202152-11-junaids@google.com> (raw)
In-Reply-To: <20220223052223.1202152-1-junaids@google.com>
A new GFP flag is added to specify that an allocation should be
considered globally non-sensitive. The pages will be mapped into the
ASI global non-sensitive pseudo-PGD, which is shared between all
standard ASI instances. A new page flag is also added so that when
these pages are freed, they can also be unmapped from the ASI page
tables.
Signed-off-by: Junaid Shahid <junaids@google.com>
---
include/linux/gfp.h | 10 ++-
include/linux/mm_types.h | 5 ++
include/linux/page-flags.h | 9 ++
include/trace/events/mmflags.h | 12 ++-
mm/page_alloc.c | 145 ++++++++++++++++++++++++++++++++-
tools/perf/builtin-kmem.c | 1 +
6 files changed, 178 insertions(+), 4 deletions(-)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 8fcc38467af6..07a99a463a34 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -60,6 +60,11 @@ struct vm_area_struct;
#else
#define ___GFP_NOLOCKDEP 0
#endif
+#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
+#define ___GFP_GLOBAL_NONSENSITIVE 0x4000000u
+#else
+#define ___GFP_GLOBAL_NONSENSITIVE 0
+#endif
/* If the above are modified, __GFP_BITS_SHIFT may need updating */
/*
@@ -248,8 +253,11 @@ struct vm_area_struct;
/* Disable lockdep for GFP context tracking */
#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
+/* Allocate non-sensitive memory */
+#define __GFP_GLOBAL_NONSENSITIVE ((__force gfp_t)___GFP_GLOBAL_NONSENSITIVE)
+
/* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_SHIFT 27
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
/**
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3de1afa57289..5b8028fcfe67 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -191,6 +191,11 @@ struct page {
/** @rcu_head: You can use this to free a page by RCU. */
struct rcu_head rcu_head;
+
+#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
+ /* Links the pages_to_free_async list */
+ struct llist_node async_free_node;
+#endif
};
union { /* This union is 4 bytes in size. */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index b90a17e9796d..a07434cc679c 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -140,6 +140,9 @@ enum pageflags {
#endif
#ifdef CONFIG_KASAN_HW_TAGS
PG_skip_kasan_poison,
+#endif
+#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
+ PG_global_nonsensitive,
#endif
__NR_PAGEFLAGS,
@@ -542,6 +545,12 @@ TESTCLEARFLAG(Young, young, PF_ANY)
PAGEFLAG(Idle, idle, PF_ANY)
#endif
+#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
+__PAGEFLAG(GlobalNonSensitive, global_nonsensitive, PF_ANY);
+#else
+__PAGEFLAG_FALSE(GlobalNonSensitive, global_nonsensitive);
+#endif
+
#ifdef CONFIG_KASAN_HW_TAGS
PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD)
#else
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 116ed4d5d0f8..73a49197ef54 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -50,7 +50,8 @@
{(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\
{(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\
{(unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"}, \
- {(unsigned long)__GFP_SKIP_KASAN_POISON,"__GFP_SKIP_KASAN_POISON"}\
+ {(unsigned long)__GFP_SKIP_KASAN_POISON,"__GFP_SKIP_KASAN_POISON"},\
+ {(unsigned long)__GFP_GLOBAL_NONSENSITIVE, "__GFP_GLOBAL_NONSENSITIVE"}\
#define show_gfp_flags(flags) \
(flags) ? __print_flags(flags, "|", \
@@ -93,6 +94,12 @@
#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string)
#endif
+#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
+#define IF_HAVE_ASI(flag, string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_ASI(flag, string)
+#endif
+
#define __def_pageflag_names \
{1UL << PG_locked, "locked" }, \
{1UL << PG_waiters, "waiters" }, \
@@ -121,7 +128,8 @@ IF_HAVE_PG_HWPOISON(PG_hwpoison, "hwpoison" ) \
IF_HAVE_PG_IDLE(PG_young, "young" ) \
IF_HAVE_PG_IDLE(PG_idle, "idle" ) \
IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) \
-IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison")
+IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison") \
+IF_HAVE_ASI(PG_global_nonsensitive, "global_nonsensitive")
#define show_page_flags(flags) \
(flags) ? __print_flags(flags, "|", \
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c5952749ad40..a4048fa1868a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -697,7 +697,7 @@ static inline bool pcp_allowed_order(unsigned int order)
return false;
}
-static inline void free_the_page(struct page *page, unsigned int order)
+static inline void __free_the_page(struct page *page, unsigned int order)
{
if (pcp_allowed_order(order)) /* Via pcp? */
free_unref_page(page, order);
@@ -705,6 +705,14 @@ static inline void free_the_page(struct page *page, unsigned int order)
__free_pages_ok(page, order, FPI_NONE);
}
+static bool asi_unmap_freed_pages(struct page *page, unsigned int order);
+
+static inline void free_the_page(struct page *page, unsigned int order)
+{
+ if (asi_unmap_freed_pages(page, order))
+ __free_the_page(page, order);
+}
+
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
@@ -5162,6 +5170,129 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
return true;
}
+#ifdef CONFIG_ADDRESS_SPACE_ISOLATION
+
+static DEFINE_PER_CPU(struct work_struct, async_free_work);
+static DEFINE_PER_CPU(struct llist_head, pages_to_free_async);
+static bool async_free_work_initialized;
+
+static void __free_the_page(struct page *page, unsigned int order);
+
+static void async_free_work_fn(struct work_struct *work)
+{
+ struct page *page, *tmp;
+ struct llist_node *pages_to_free;
+ void *va;
+ size_t len;
+ uint order;
+
+ pages_to_free = llist_del_all(this_cpu_ptr(&pages_to_free_async));
+
+ /* A later patch will do a more optimized TLB flush. */
+
+ llist_for_each_entry_safe(page, tmp, pages_to_free, async_free_node) {
+ va = page_to_virt(page);
+ order = page->private;
+ len = PAGE_SIZE * (1 << order);
+
+ asi_flush_tlb_range(ASI_GLOBAL_NONSENSITIVE, va, len);
+ __free_the_page(page, order);
+ }
+}
+
+static int __init asi_page_alloc_init(void)
+{
+ int cpu;
+
+ if (!static_asi_enabled())
+ return 0;
+
+ for_each_possible_cpu(cpu)
+ INIT_WORK(per_cpu_ptr(&async_free_work, cpu),
+ async_free_work_fn);
+
+ /*
+ * This function is called before SMP is initialized, so we can assume
+ * that this is the only running CPU at this point.
+ */
+
+ barrier();
+ async_free_work_initialized = true;
+ barrier();
+
+ if (!llist_empty(this_cpu_ptr(&pages_to_free_async)))
+ queue_work_on(smp_processor_id(), mm_percpu_wq,
+ this_cpu_ptr(&async_free_work));
+
+ return 0;
+}
+early_initcall(asi_page_alloc_init);
+
+static int asi_map_alloced_pages(struct page *page, uint order, gfp_t gfp_mask)
+{
+ uint i;
+
+ if (!static_asi_enabled())
+ return 0;
+
+ if (gfp_mask & __GFP_GLOBAL_NONSENSITIVE) {
+ for (i = 0; i < (1 << order); i++)
+ __SetPageGlobalNonSensitive(page + i);
+
+ return asi_map_gfp(ASI_GLOBAL_NONSENSITIVE, page_to_virt(page),
+ PAGE_SIZE * (1 << order), gfp_mask);
+ }
+
+ return 0;
+}
+
+static bool asi_unmap_freed_pages(struct page *page, unsigned int order)
+{
+ void *va;
+ size_t len;
+ bool async_flush_needed;
+
+ if (!static_asi_enabled())
+ return true;
+
+ if (!PageGlobalNonSensitive(page))
+ return true;
+
+ va = page_to_virt(page);
+ len = PAGE_SIZE * (1 << order);
+ async_flush_needed = irqs_disabled() || in_interrupt();
+
+ asi_unmap(ASI_GLOBAL_NONSENSITIVE, va, len, !async_flush_needed);
+
+ if (!async_flush_needed)
+ return true;
+
+ page->private = order;
+ llist_add(&page->async_free_node, this_cpu_ptr(&pages_to_free_async));
+
+ if (async_free_work_initialized)
+ queue_work_on(smp_processor_id(), mm_percpu_wq,
+ this_cpu_ptr(&async_free_work));
+
+ return false;
+}
+
+#else /* CONFIG_ADDRESS_SPACE_ISOLATION */
+
+static inline
+int asi_map_alloced_pages(struct page *pages, uint order, gfp_t gfp_mask)
+{
+ return 0;
+}
+
+static inline
+bool asi_unmap_freed_pages(struct page *page, unsigned int order)
+{
+ return true;
+}
+
+#endif
+
/*
* __alloc_pages_bulk - Allocate a number of order-0 pages to a list or array
* @gfp: GFP flags for the allocation
@@ -5345,6 +5476,9 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
return NULL;
}
+ if (static_asi_enabled() && (gfp & __GFP_GLOBAL_NONSENSITIVE))
+ gfp |= __GFP_ZERO;
+
gfp &= gfp_allowed_mask;
/*
* Apply scoped allocation constraints. This is mainly about GFP_NOFS
@@ -5388,6 +5522,15 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
page = NULL;
}
+ if (page) {
+ int err = asi_map_alloced_pages(page, order, gfp);
+
+ if (unlikely(err)) {
+ __free_pages(page, order);
+ page = NULL;
+ }
+ }
+
trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype);
return page;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index da03a341c63c..5857953cd5c1 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -660,6 +660,7 @@ static const struct {
{ "__GFP_RECLAIM", "R" },
{ "__GFP_DIRECT_RECLAIM", "DR" },
{ "__GFP_KSWAPD_RECLAIM", "KR" },
+ { "__GFP_GLOBAL_NONSENSITIVE", "GNS" },
};
static size_t max_gfp_len;
--
2.35.1.473.g83b2b277ed-goog
next prev parent reply other threads:[~2022-02-23 5:24 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-23 5:21 [RFC PATCH 00/47] Address Space Isolation for KVM Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 01/47] mm: asi: Introduce ASI core API Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 02/47] mm: asi: Add command-line parameter to enable/disable ASI Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 03/47] mm: asi: Switch to unrestricted address space when entering scheduler Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 04/47] mm: asi: ASI support in interrupts/exceptions Junaid Shahid
2022-03-14 15:50 ` Thomas Gleixner
2022-03-15 2:01 ` Junaid Shahid
2022-03-15 12:55 ` Thomas Gleixner
2022-03-15 22:41 ` Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 05/47] mm: asi: Make __get_current_cr3_fast() ASI-aware Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 06/47] mm: asi: ASI page table allocation and free functions Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 07/47] mm: asi: Functions to map/unmap a memory range into ASI page tables Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 08/47] mm: asi: Add basic infrastructure for global non-sensitive mappings Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 09/47] mm: Add __PAGEFLAG_FALSE Junaid Shahid
2022-02-23 5:21 ` Junaid Shahid [this message]
2022-03-23 21:06 ` [RFC PATCH 10/47] mm: asi: Support for global non-sensitive direct map allocations Matthew Wilcox
2022-03-23 23:48 ` Junaid Shahid
2022-03-24 1:54 ` Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 11/47] mm: asi: Global non-sensitive vmalloc/vmap support Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 12/47] mm: asi: Support for global non-sensitive slab caches Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 13/47] asi: Added ASI memory cgroup flag Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 14/47] mm: asi: Disable ASI API when ASI is not enabled for a process Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 15/47] kvm: asi: Restricted address space for VM execution Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 16/47] mm: asi: Support for mapping non-sensitive pcpu chunks Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 17/47] mm: asi: Aliased direct map for local non-sensitive allocations Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 18/47] mm: asi: Support for pre-ASI-init " Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 19/47] mm: asi: Support for locally nonsensitive page allocations Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 20/47] mm: asi: Support for locally non-sensitive vmalloc allocations Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 21/47] mm: asi: Add support for locally non-sensitive VM_USERMAP pages Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 22/47] mm: asi: Added refcounting when initilizing an asi Junaid Shahid
2022-02-23 5:21 ` [RFC PATCH 23/47] mm: asi: Add support for mapping all userspace memory into ASI Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 24/47] mm: asi: Support for local non-sensitive slab caches Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 25/47] mm: asi: Avoid warning from NMI userspace accesses in ASI context Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 26/47] mm: asi: Use separate PCIDs for restricted address spaces Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 27/47] mm: asi: Avoid TLB flushes during ASI CR3 switches when possible Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 28/47] mm: asi: Avoid TLB flush IPIs to CPUs not in ASI context Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 29/47] mm: asi: Reduce TLB flushes when freeing pages asynchronously Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 30/47] mm: asi: Add API for mapping userspace address ranges Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 31/47] mm: asi: Support for non-sensitive SLUB caches Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 32/47] x86: asi: Allocate FPU state separately when ASI is enabled Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 33/47] kvm: asi: Map guest memory into restricted ASI address space Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 34/47] kvm: asi: Unmap guest memory from ASI address space when using nested virt Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 35/47] mm: asi: asi_exit() on PF, skip handling if address is accessible Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 36/47] mm: asi: Adding support for dynamic percpu ASI allocations Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 37/47] mm: asi: ASI annotation support for static variables Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 38/47] mm: asi: ASI annotation support for dynamic modules Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 39/47] mm: asi: Skip conventional L1TF/MDS mitigations Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 40/47] mm: asi: support for static percpu DEFINE_PER_CPU*_ASI Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 41/47] mm: asi: Annotation of static variables to be nonsensitive Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 42/47] mm: asi: Annotation of PERCPU " Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 43/47] mm: asi: Annotation of dynamic " Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 44/47] kvm: asi: Splitting kvm_vcpu_arch into non/sensitive parts Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 45/47] mm: asi: Mapping global nonsensitive areas in asi_global_init Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 46/47] kvm: asi: Do asi_exit() in vcpu_run loop before returning to userspace Junaid Shahid
2022-02-23 5:22 ` [RFC PATCH 47/47] mm: asi: Properly un/mapping task stack from ASI + tlb flush Junaid Shahid
2022-03-05 3:39 ` [RFC PATCH 00/47] Address Space Isolation for KVM Hyeonggon Yoo
2022-03-16 21:34 ` Alexandre Chartre
2022-03-17 23:25 ` Junaid Shahid
2022-03-22 9:46 ` Alexandre Chartre
2022-03-23 19:35 ` Junaid Shahid
2022-04-08 8:52 ` Alexandre Chartre
2022-04-11 3:26 ` junaid_shahid
2022-03-16 22:49 ` Thomas Gleixner
2022-03-17 21:24 ` Junaid Shahid
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220223052223.1202152-11-junaids@google.com \
--to=junaids@google.com \
--cc=alexandre.chartre@oracle.com \
--cc=dave.hansen@linux.intel.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=oweisse@google.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=rppt@linux.ibm.com \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).