[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240712-asi-rfc-24-v1-14-144b319a40d8@google.com>
Date: Fri, 12 Jul 2024 17:00:32 +0000
From: Brendan Jackman <jackmanb@...gle.com>
To: Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>, "H. Peter Anvin" <hpa@...or.com>,
Andy Lutomirski <luto@...nel.org>, Peter Zijlstra <peterz@...radead.org>,
Sean Christopherson <seanjc@...gle.com>, Paolo Bonzini <pbonzini@...hat.com>,
Alexandre Chartre <alexandre.chartre@...cle.com>, Liran Alon <liran.alon@...cle.com>,
Jan Setje-Eilers <jan.setjeeilers@...cle.com>, Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>, Mark Rutland <mark.rutland@....com>,
Andrew Morton <akpm@...ux-foundation.org>, Mel Gorman <mgorman@...e.de>,
Lorenzo Stoakes <lstoakes@...il.com>, David Hildenbrand <david@...hat.com>, Vlastimil Babka <vbabka@...e.cz>,
Michal Hocko <mhocko@...nel.org>, Khalid Aziz <khalid.aziz@...cle.com>,
Juri Lelli <juri.lelli@...hat.com>, Vincent Guittot <vincent.guittot@...aro.org>,
Dietmar Eggemann <dietmar.eggemann@....com>, Steven Rostedt <rostedt@...dmis.org>,
Valentin Schneider <vschneid@...hat.com>, Paul Turner <pjt@...gle.com>, Reiji Watanabe <reijiw@...gle.com>,
Junaid Shahid <junaids@...gle.com>, Ofir Weisse <oweisse@...gle.com>,
Yosry Ahmed <yosryahmed@...gle.com>, Patrick Bellasi <derkling@...gle.com>,
KP Singh <kpsingh@...gle.com>, Alexandra Sandulescu <aesa@...gle.com>,
Matteo Rizzo <matteorizzo@...gle.com>, Jann Horn <jannh@...gle.com>
Cc: x86@...nel.org, linux-kernel@...r.kernel.org, linux-mm@...ck.org,
kvm@...r.kernel.org, Brendan Jackman <jackmanb@...gle.com>
Subject: [PATCH 14/26] mm: asi: Add basic infrastructure for global
non-sensitive mappings
From: Junaid Shahid <junaids@...gle.com>
A pseudo-PGD is added to store global non-sensitive ASI mappings.
Actual ASI PGDs copy entries from this pseudo-PGD during asi_init().
Memory can be mapped as globally non-sensitive by calling asi_map()
with ASI_GLOBAL_NONSENSITIVE.
Page tables allocated for global non-sensitive mappings are never
freed.
While a previous version used init_mm.asi[0] as the special global
nonsensitive domain, here we have tried to avoid special-casing index 0.
So now we have a special global variable for that. For this to work we
need to make sure that nobody assumes that asi is a member of
asi->mm->asi (also that nobody assumes a struct asi is embedded in a
struct mm - but that seems like a weird assumption to make anyway, when
you already have the .mm pointer). I currently believe that this is
worth it for the reduced level of magic in the code.
Signed-off-by: Junaid Shahid <junaids@...gle.com>
Signed-off-by: Brendan Jackman <jackmanb@...gle.com>
---
arch/x86/include/asm/asi.h | 3 +++
arch/x86/mm/asi.c | 37 +++++++++++++++++++++++++++++++++++++
arch/x86/mm/init_64.c | 25 ++++++++++++++++---------
arch/x86/mm/mm_internal.h | 3 +++
include/asm-generic/asi.h | 2 ++
5 files changed, 61 insertions(+), 9 deletions(-)
diff --git a/arch/x86/include/asm/asi.h b/arch/x86/include/asm/asi.h
index 9aad843eb6df..2d86a5c17f2b 100644
--- a/arch/x86/include/asm/asi.h
+++ b/arch/x86/include/asm/asi.h
@@ -78,6 +78,9 @@
*/
#define ASI_MAX_NUM ((1 << ASI_MAX_NUM_ORDER) - 1)
+extern struct asi __asi_global_nonsensitive;
+#define ASI_GLOBAL_NONSENSITIVE (&__asi_global_nonsensitive)
+
struct asi_hooks {
/*
* Both of these functions MUST be idempotent and re-entrant. They will
diff --git a/arch/x86/mm/asi.c b/arch/x86/mm/asi.c
index e43b206450ad..807d51497f43 100644
--- a/arch/x86/mm/asi.c
+++ b/arch/x86/mm/asi.c
@@ -11,6 +11,7 @@
#include <asm/mmu_context.h>
#include <asm/traps.h>
+#include "mm_internal.h"
#include "../../../mm/internal.h"
static struct asi_class asi_class[ASI_MAX_NUM];
@@ -19,6 +20,13 @@ static DEFINE_SPINLOCK(asi_class_lock);
DEFINE_PER_CPU_ALIGNED(struct asi *, curr_asi);
EXPORT_SYMBOL(curr_asi);
+static __aligned(PAGE_SIZE) pgd_t asi_global_nonsensitive_pgd[PTRS_PER_PGD];
+
+struct asi __asi_global_nonsensitive = {
+ .pgd = asi_global_nonsensitive_pgd,
+ .mm = &init_mm,
+};
+
static inline bool asi_class_registered(int index)
{
return asi_class[index].name != NULL;
@@ -154,6 +162,31 @@ void __init asi_check_boottime_disable(void)
pr_info("ASI enablement ignored due to incomplete implementation.\n");
}
+static int __init asi_global_init(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_ASI))
+ return 0;
+
+ /*
+ * Lower-level pagetables for global nonsensitive mappings are shared,
+ * but the PGD has to be copied into each domain during asi_init. To
+ * avoid needing to synchronize new mappings into pre-existing domains
+ * we just pre-allocate all of the relevant level N-1 entries so that
+ * the global nonsensitive PGD already has pointers that can be copied
+ * when new domains get asi_init()ed.
+ */
+ preallocate_sub_pgd_pages(asi_global_nonsensitive_pgd,
+ PAGE_OFFSET,
+ PAGE_OFFSET + PFN_PHYS(max_pfn) - 1,
+ "ASI Global Non-sensitive direct map");
+ preallocate_sub_pgd_pages(asi_global_nonsensitive_pgd,
+ VMALLOC_START, VMALLOC_END,
+ "ASI Global Non-sensitive vmalloc");
+
+ return 0;
+}
+subsys_initcall(asi_global_init)
+
static void __asi_destroy(struct asi *asi)
{
WARN_ON_ONCE(asi->ref_count <= 0);
@@ -168,6 +201,7 @@ int asi_init(struct mm_struct *mm, int asi_index, struct asi **out_asi)
{
struct asi *asi;
int err = 0;
+ uint i;
*out_asi = NULL;
@@ -203,6 +237,9 @@ int asi_init(struct mm_struct *mm, int asi_index, struct asi **out_asi)
asi->mm = mm;
asi->index = asi_index;
+ for (i = KERNEL_PGD_BOUNDARY; i < PTRS_PER_PGD; i++)
+ set_pgd(asi->pgd + i, asi_global_nonsensitive_pgd[i]);
+
exit_unlock:
if (err)
__asi_destroy(asi);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 7e177856ee4f..f67f4637357c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1278,18 +1278,15 @@ static void __init register_page_bootmem_info(void)
#endif
}
-/*
- * Pre-allocates page-table pages for the vmalloc area in the kernel page-table.
- * Only the level which needs to be synchronized between all page-tables is
- * allocated because the synchronization can be expensive.
- */
-static void __init preallocate_vmalloc_pages(void)
+/* Initialize empty pagetables at the level below PGD. */
+void __init preallocate_sub_pgd_pages(pgd_t *pgd_table, ulong start,
+ ulong end, const char *name)
{
unsigned long addr;
const char *lvl;
- for (addr = VMALLOC_START; addr <= VMEMORY_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
- pgd_t *pgd = pgd_offset_k(addr);
+ for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+ pgd_t *pgd = pgd_offset_pgd(pgd_table, addr);
p4d_t *p4d;
pud_t *pud;
@@ -1325,7 +1322,17 @@ static void __init preallocate_vmalloc_pages(void)
* The pages have to be there now or they will be missing in
* process page-tables later.
*/
- panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl);
+ panic("Failed to pre-allocate %s pages for %s area\n", lvl, name);
+}
+
+/*
+ * Pre-allocates page-table pages for the vmalloc area in the kernel page-table.
+ * Only the level which needs to be synchronized between all page-tables is
+ * allocated because the synchronization can be expensive.
+ */
+static void __init preallocate_vmalloc_pages(void)
+{
+ preallocate_sub_pgd_pages(init_mm.pgd, VMALLOC_START, VMEMORY_END, "vmalloc");
}
void __init mem_init(void)
diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h
index 3f37b5c80bb3..1203a977edcd 100644
--- a/arch/x86/mm/mm_internal.h
+++ b/arch/x86/mm/mm_internal.h
@@ -25,4 +25,7 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache);
extern unsigned long tlb_single_page_flush_ceiling;
+extern void preallocate_sub_pgd_pages(pgd_t *pgd_table, ulong start,
+ ulong end, const char *name);
+
#endif /* __X86_MM_INTERNAL_H */
diff --git a/include/asm-generic/asi.h b/include/asm-generic/asi.h
index 3956f995fe6a..fd5a302e0e09 100644
--- a/include/asm-generic/asi.h
+++ b/include/asm-generic/asi.h
@@ -9,6 +9,8 @@
#define ASI_MAX_NUM_ORDER 0
#define ASI_MAX_NUM 0
+#define ASI_GLOBAL_NONSENSITIVE NULL
+
#ifndef _ASSEMBLY_
struct asi_hooks {};
--
2.45.2.993.g49e7a77208-goog
Powered by blists - more mailing lists