summaryrefslogtreecommitdiffstats
path: root/arch/arm64/mm/proc.S
diff options
context:
space:
mode:
authorArd Biesheuvel <ardb@kernel.org>2022-06-09 19:43:20 +0200
committerWill Deacon <will@kernel.org>2022-06-23 18:26:13 +0100
commit47546a1912fc4a037035746998c3cfa740beed70 (patch)
treebc1350dbf70d01bd9deab448f1f9e69704dc7386 /arch/arm64/mm/proc.S
parentc7eff738cf45ef149060939f3be65816eea461c8 (diff)
downloadlinux-stable-47546a1912fc4a037035746998c3cfa740beed70.tar.gz
linux-stable-47546a1912fc4a037035746998c3cfa740beed70.tar.bz2
linux-stable-47546a1912fc4a037035746998c3cfa740beed70.zip
arm64: mm: install KPTI nG mappings with MMU enabled
In cases where we unmap the kernel while running in user space, we rely on ASIDs to distinguish the minimal trampoline from the full kernel mapping, and this means we must use non-global attributes for those mappings, to ensure they are scoped by ASID and will not hit in the TLB inadvertently. We only do this when needed, as this is generally more costly in terms of TLB pressure, and so we boot without these non-global attributes, and apply them to all existing kernel mappings once all CPUs are up and we know whether or not the non-global attributes are needed. At this point, we cannot simply unmap and remap the entire address space, so we have to update all existing block and page descriptors in place. Currently, we go through a lot of trouble to perform these updates with the MMU and caches off, to avoid violating break before make (BBM) rules imposed by the architecture. Since we make changes to page tables that are not covered by the ID map, we gain access to those descriptors by disabling translations altogether. This means that the stores to memory are issued with device attributes, and require extra care in terms of coherency, which is costly. We also rely on the ID map to access a shared flag, which requires the ID map to be executable and writable at the same time, which is another thing we'd prefer to avoid. So let's switch to an approach where we replace the kernel mapping with a minimal mapping of a few pages that can be used for a minimal, ad-hoc fixmap that we can use to map each page table in turn as we traverse the hierarchy. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20220609174320.4035379-3-ardb@kernel.org Signed-off-by: Will Deacon <will@kernel.org>
Diffstat (limited to 'arch/arm64/mm/proc.S')
-rw-r--r--arch/arm64/mm/proc.S81
1 files changed, 55 insertions, 26 deletions
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 660887152dba..972ce8d7f2c5 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -14,6 +14,7 @@
#include <asm/asm-offsets.h>
#include <asm/asm_pointer_auth.h>
#include <asm/hwcap.h>
+#include <asm/kernel-pgtable.h>
#include <asm/pgtable-hwdef.h>
#include <asm/cpufeature.h>
#include <asm/alternative.h>
@@ -200,20 +201,19 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1)
.popsection
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+
+#define KPTI_NG_PTE_FLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS)
+
.pushsection ".idmap.text", "awx"
.macro kpti_mk_tbl_ng, type, num_entries
add end_\type\()p, cur_\type\()p, #\num_entries * 8
.Ldo_\type:
- dc cvac, cur_\type\()p // Ensure any existing dirty
- dmb sy // lines are written back before
- ldr \type, [cur_\type\()p] // loading the entry
+ ldr \type, [cur_\type\()p] // Load the entry
tbz \type, #0, .Lnext_\type // Skip invalid and
tbnz \type, #11, .Lnext_\type // non-global entries
orr \type, \type, #PTE_NG // Same bit for blocks and pages
- str \type, [cur_\type\()p] // Update the entry and ensure
- dmb sy // that it is visible to all
- dc civac, cur_\()\type\()p // CPUs.
+ str \type, [cur_\type\()p] // Update the entry
.ifnc \type, pte
tbnz \type, #1, .Lderef_\type
.endif
@@ -223,8 +223,29 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1)
b.ne .Ldo_\type
.endm
+ /*
+ * Dereference the current table entry and map it into the temporary
+ * fixmap slot associated with the current level.
+ */
+ .macro kpti_map_pgtbl, type, level
+ str xzr, [temp_pte, #8 * (\level + 1)] // break before make
+ dsb nshst
+ add pte, temp_pte, #PAGE_SIZE * (\level + 1)
+ lsr pte, pte, #12
+ tlbi vaae1, pte
+ dsb nsh
+ isb
+
+ phys_to_pte pte, cur_\type\()p
+ add cur_\type\()p, temp_pte, #PAGE_SIZE * (\level + 1)
+ orr pte, pte, pte_flags
+ str pte, [temp_pte, #8 * (\level + 1)]
+ dsb nshst
+ .endm
+
/*
- * void __kpti_install_ng_mappings(int cpu, int num_cpus, phys_addr_t swapper)
+ * void __kpti_install_ng_mappings(int cpu, int num_secondaries, phys_addr_t temp_pgd,
+ * unsigned long temp_pte_va)
*
* Called exactly once from stop_machine context by each CPU found during boot.
*/
@@ -232,8 +253,10 @@ __idmap_kpti_flag:
.long 1
SYM_FUNC_START(idmap_kpti_install_ng_mappings)
cpu .req w0
+ temp_pte .req x0
num_cpus .req w1
- swapper_pa .req x2
+ pte_flags .req x1
+ temp_pgd_phys .req x2
swapper_ttb .req x3
flag_ptr .req x4
cur_pgdp .req x5
@@ -246,9 +269,10 @@ SYM_FUNC_START(idmap_kpti_install_ng_mappings)
cur_ptep .req x14
end_ptep .req x15
pte .req x16
+ valid .req x17
+ mov x5, x3 // preserve temp_pte arg
mrs swapper_ttb, ttbr1_el1
- restore_ttbr1 swapper_ttb
adr flag_ptr, __idmap_kpti_flag
cbnz cpu, __idmap_kpti_secondary
@@ -260,28 +284,28 @@ SYM_FUNC_START(idmap_kpti_install_ng_mappings)
eor w17, w17, num_cpus
cbnz w17, 1b
- /* We need to walk swapper, so turn off the MMU. */
- pre_disable_mmu_workaround
- mrs x17, sctlr_el1
- bic x17, x17, #SCTLR_ELx_M
- msr sctlr_el1, x17
+ /* Switch to the temporary page tables on this CPU only */
+ __idmap_cpu_set_reserved_ttbr1 x8, x9
+ offset_ttbr1 temp_pgd_phys, x8
+ msr ttbr1_el1, temp_pgd_phys
isb
+ mov temp_pte, x5
+ mov pte_flags, #KPTI_NG_PTE_FLAGS
+
/* Everybody is enjoying the idmap, so we can rewrite swapper. */
/* PGD */
- mov cur_pgdp, swapper_pa
+ adrp cur_pgdp, swapper_pg_dir
+ kpti_map_pgtbl pgd, 0
kpti_mk_tbl_ng pgd, PTRS_PER_PGD
- /* Publish the updated tables and nuke all the TLBs */
- dsb sy
- tlbi vmalle1is
- dsb ish
- isb
+ /* Ensure all the updated entries are visible to secondary CPUs */
+ dsb ishst
- /* We're done: fire up the MMU again */
- mrs x17, sctlr_el1
- orr x17, x17, #SCTLR_ELx_M
- set_sctlr_el1 x17
+ /* We're done: fire up swapper_pg_dir again */
+ __idmap_cpu_set_reserved_ttbr1 x8, x9
+ msr ttbr1_el1, swapper_ttb
+ isb
/* Set the flag to zero to indicate that we're all done */
str wzr, [flag_ptr]
@@ -292,6 +316,7 @@ SYM_FUNC_START(idmap_kpti_install_ng_mappings)
.if CONFIG_PGTABLE_LEVELS > 3
pud .req x10
pte_to_phys cur_pudp, pgd
+ kpti_map_pgtbl pud, 1
kpti_mk_tbl_ng pud, PTRS_PER_PUD
b .Lnext_pgd
.else /* CONFIG_PGTABLE_LEVELS <= 3 */
@@ -304,6 +329,7 @@ SYM_FUNC_START(idmap_kpti_install_ng_mappings)
.if CONFIG_PGTABLE_LEVELS > 2
pmd .req x13
pte_to_phys cur_pmdp, pud
+ kpti_map_pgtbl pmd, 2
kpti_mk_tbl_ng pmd, PTRS_PER_PMD
b .Lnext_pud
.else /* CONFIG_PGTABLE_LEVELS <= 2 */
@@ -314,12 +340,15 @@ SYM_FUNC_START(idmap_kpti_install_ng_mappings)
.Lderef_pmd:
/* PTE */
pte_to_phys cur_ptep, pmd
+ kpti_map_pgtbl pte, 3
kpti_mk_tbl_ng pte, PTRS_PER_PTE
b .Lnext_pmd
.unreq cpu
+ .unreq temp_pte
.unreq num_cpus
- .unreq swapper_pa
+ .unreq pte_flags
+ .unreq temp_pgd_phys
.unreq cur_pgdp
.unreq end_pgdp
.unreq pgd
@@ -332,6 +361,7 @@ SYM_FUNC_START(idmap_kpti_install_ng_mappings)
.unreq cur_ptep
.unreq end_ptep
.unreq pte
+ .unreq valid
/* Secondary CPUs end up here */
__idmap_kpti_secondary:
@@ -351,7 +381,6 @@ __idmap_kpti_secondary:
cbnz w16, 1b
/* All done, act like nothing happened */
- offset_ttbr1 swapper_ttb, x16
msr ttbr1_el1, swapper_ttb
isb
ret