summaryrefslogtreecommitdiffstats
path: root/arch/arm64/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/mm')
-rw-r--r--arch/arm64/mm/cache.S4
-rw-r--r--arch/arm64/mm/context.c67
-rw-r--r--arch/arm64/mm/fault.c17
-rw-r--r--arch/arm64/mm/init.c46
-rw-r--r--arch/arm64/mm/mmu.c47
-rw-r--r--arch/arm64/mm/pgd.c8
-rw-r--r--arch/arm64/mm/proc.S66
7 files changed, 142 insertions, 113 deletions
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 7f1dbe9..91464e7 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -49,7 +49,7 @@ ENTRY(flush_icache_range)
* - end - virtual end address of region
*/
ENTRY(__flush_cache_user_range)
- uaccess_ttbr0_enable x2, x3
+ uaccess_ttbr0_enable x2, x3, x4
dcache_line_size x2, x3
sub x3, x2, #1
bic x4, x0, x3
@@ -72,7 +72,7 @@ USER(9f, ic ivau, x4 ) // invalidate I line PoU
isb
mov x0, #0
1:
- uaccess_ttbr0_disable x1
+ uaccess_ttbr0_disable x1, x2
ret
9:
mov x0, #-EFAULT
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 6f40170..301417a 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -39,7 +39,16 @@ static cpumask_t tlb_flush_pending;
#define ASID_MASK (~GENMASK(asid_bits - 1, 0))
#define ASID_FIRST_VERSION (1UL << asid_bits)
-#define NUM_USER_ASIDS ASID_FIRST_VERSION
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define NUM_USER_ASIDS (ASID_FIRST_VERSION >> 1)
+#define asid2idx(asid) (((asid) & ~ASID_MASK) >> 1)
+#define idx2asid(idx) (((idx) << 1) & ~ASID_MASK)
+#else
+#define NUM_USER_ASIDS (ASID_FIRST_VERSION)
+#define asid2idx(asid) ((asid) & ~ASID_MASK)
+#define idx2asid(idx) asid2idx(idx)
+#endif
/* Get the ASIDBits supported by the current CPU */
static u32 get_cpu_asid_bits(void)
@@ -79,13 +88,6 @@ void verify_cpu_asid_bits(void)
}
}
-static void set_reserved_asid_bits(void)
-{
- if (IS_ENABLED(CONFIG_QCOM_FALKOR_ERRATUM_1003) &&
- cpus_have_const_cap(ARM64_WORKAROUND_QCOM_FALKOR_E1003))
- __set_bit(FALKOR_RESERVED_ASID, asid_map);
-}
-
static void flush_context(unsigned int cpu)
{
int i;
@@ -94,8 +96,6 @@ static void flush_context(unsigned int cpu)
/* Update the list of reserved ASIDs and the ASID bitmap. */
bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
- set_reserved_asid_bits();
-
for_each_possible_cpu(i) {
asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
/*
@@ -107,7 +107,7 @@ static void flush_context(unsigned int cpu)
*/
if (asid == 0)
asid = per_cpu(reserved_asids, i);
- __set_bit(asid & ~ASID_MASK, asid_map);
+ __set_bit(asid2idx(asid), asid_map);
per_cpu(reserved_asids, i) = asid;
}
@@ -162,16 +162,16 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
* We had a valid ASID in a previous life, so try to re-use
* it if possible.
*/
- asid &= ~ASID_MASK;
- if (!__test_and_set_bit(asid, asid_map))
+ if (!__test_and_set_bit(asid2idx(asid), asid_map))
return newasid;
}
/*
* Allocate a free ASID. If we can't find one, take a note of the
- * currently active ASIDs and mark the TLBs as requiring flushes.
- * We always count from ASID #1, as we use ASID #0 when setting a
- * reserved TTBR0 for the init_mm.
+ * currently active ASIDs and mark the TLBs as requiring flushes. We
+ * always count from ASID #2 (index 1), as we use ASID #0 when setting
+ * a reserved TTBR0 for the init_mm and we allocate ASIDs in even/odd
+ * pairs.
*/
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
if (asid != NUM_USER_ASIDS)
@@ -188,32 +188,35 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
set_asid:
__set_bit(asid, asid_map);
cur_idx = asid;
- return asid | generation;
+ return idx2asid(asid) | generation;
}
void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
{
unsigned long flags;
- u64 asid;
+ u64 asid, old_active_asid;
asid = atomic64_read(&mm->context.id);
/*
* The memory ordering here is subtle.
- * If our ASID matches the current generation, then we update
- * our active_asids entry with a relaxed xchg. Racing with a
- * concurrent rollover means that either:
+ * If our active_asids is non-zero and the ASID matches the current
+ * generation, then we update the active_asids entry with a relaxed
+ * cmpxchg. Racing with a concurrent rollover means that either:
*
- * - We get a zero back from the xchg and end up waiting on the
+ * - We get a zero back from the cmpxchg and end up waiting on the
* lock. Taking the lock synchronises with the rollover and so
* we are forced to see the updated generation.
*
- * - We get a valid ASID back from the xchg, which means the
+ * - We get a valid ASID back from the cmpxchg, which means the
* relaxed xchg in flush_context will treat us as reserved
* because atomic RmWs are totally ordered for a given location.
*/
- if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits)
- && atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid))
+ old_active_asid = atomic64_read(&per_cpu(active_asids, cpu));
+ if (old_active_asid &&
+ !((asid ^ atomic64_read(&asid_generation)) >> asid_bits) &&
+ atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu),
+ old_active_asid, asid))
goto switch_mm_fastpath;
raw_spin_lock_irqsave(&cpu_asid_lock, flags);
@@ -231,6 +234,9 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
switch_mm_fastpath:
+
+ arm64_apply_bp_hardening();
+
/*
* Defer TTBR0_EL1 setting for user threads to uaccess_enable() when
* emulating PAN.
@@ -239,6 +245,15 @@ switch_mm_fastpath:
cpu_switch_mm(mm->pgd, mm);
}
+/* Errata workaround post TTBRx_EL1 update. */
+asmlinkage void post_ttbr_update_workaround(void)
+{
+ asm(ALTERNATIVE("nop; nop; nop",
+ "ic iallu; dsb nsh; isb",
+ ARM64_WORKAROUND_CAVIUM_27456,
+ CONFIG_CAVIUM_ERRATUM_27456));
+}
+
static int asids_init(void)
{
asid_bits = get_cpu_asid_bits();
@@ -254,8 +269,6 @@ static int asids_init(void)
panic("Failed to allocate bitmap for %lu ASIDs\n",
NUM_USER_ASIDS);
- set_reserved_asid_bits();
-
pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS);
return 0;
}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 9b7f89d..6c30cf9 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -707,6 +707,23 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
arm64_notify_die("", regs, &info, esr);
}
+asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
+ unsigned int esr,
+ struct pt_regs *regs)
+{
+ /*
+ * We've taken an instruction abort from userspace and not yet
+ * re-enabled IRQs. If the address is a kernel address, apply
+ * BP hardening prior to enabling IRQs and pre-emption.
+ */
+ if (addr > TASK_SIZE)
+ arm64_apply_bp_hardening();
+
+ local_irq_enable();
+ do_mem_abort(addr, esr, regs);
+}
+
+
asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
unsigned int esr,
struct pt_regs *regs)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 00e7b90..c903f7c 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -366,6 +366,9 @@ void __init arm64_memblock_init(void)
/* Handle linux,usable-memory-range property */
fdt_enforce_memory_region();
+ /* Remove memory above our supported physical address size */
+ memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
+
/*
* Ensure that the linear region takes up exactly half of the kernel
* virtual address space. This way, we can distinguish a linear address
@@ -600,49 +603,6 @@ void __init mem_init(void)
mem_init_print_info(NULL);
-#define MLK(b, t) b, t, ((t) - (b)) >> 10
-#define MLM(b, t) b, t, ((t) - (b)) >> 20
-#define MLG(b, t) b, t, ((t) - (b)) >> 30
-#define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
-
- pr_notice("Virtual kernel memory layout:\n");
-#ifdef CONFIG_KASAN
- pr_notice(" kasan : 0x%16lx - 0x%16lx (%6ld GB)\n",
- MLG(KASAN_SHADOW_START, KASAN_SHADOW_END));
-#endif
- pr_notice(" modules : 0x%16lx - 0x%16lx (%6ld MB)\n",
- MLM(MODULES_VADDR, MODULES_END));
- pr_notice(" vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n",
- MLG(VMALLOC_START, VMALLOC_END));
- pr_notice(" .text : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(_text, _etext));
- pr_notice(" .rodata : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(__start_rodata, __init_begin));
- pr_notice(" .init : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(__init_begin, __init_end));
- pr_notice(" .data : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(_sdata, _edata));
- pr_notice(" .bss : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(__bss_start, __bss_stop));
- pr_notice(" fixed : 0x%16lx - 0x%16lx (%6ld KB)\n",
- MLK(FIXADDR_START, FIXADDR_TOP));
- pr_notice(" PCI I/O : 0x%16lx - 0x%16lx (%6ld MB)\n",
- MLM(PCI_IO_START, PCI_IO_END));
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
- pr_notice(" vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n",
- MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE));
- pr_notice(" 0x%16lx - 0x%16lx (%6ld MB actual)\n",
- MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
- (unsigned long)virt_to_page(high_memory)));
-#endif
- pr_notice(" memory : 0x%16lx - 0x%16lx (%6ld MB)\n",
- MLM(__phys_to_virt(memblock_start_of_DRAM()),
- (unsigned long)high_memory));
-
-#undef MLK
-#undef MLM
-#undef MLK_ROUNDUP
-
/*
* Check boundaries twice: Some fundamental inconsistencies can be
* detected at build time already.
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 267d2b7..b44992e 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -50,6 +50,7 @@
#define NO_CONT_MAPPINGS BIT(1)
u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
u64 kimage_voffset __ro_after_init;
EXPORT_SYMBOL(kimage_voffset);
@@ -525,6 +526,35 @@ static int __init parse_rodata(char *arg)
}
early_param("rodata", parse_rodata);
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static int __init map_entry_trampoline(void)
+{
+ pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+ phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
+
+ /* The trampoline is always mapped and can therefore be global */
+ pgprot_val(prot) &= ~PTE_NG;
+
+ /* Map only the text into the trampoline page table */
+ memset(tramp_pg_dir, 0, PGD_SIZE);
+ __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
+ prot, pgd_pgtable_alloc, 0);
+
+ /* Map both the text and data into the kernel page table */
+ __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+ extern char __entry_tramp_data_start[];
+
+ __set_fixmap(FIX_ENTRY_TRAMP_DATA,
+ __pa_symbol(__entry_tramp_data_start),
+ PAGE_KERNEL_RO);
+ }
+
+ return 0;
+}
+core_initcall(map_entry_trampoline);
+#endif
+
/*
* Create fine-grained mappings for the kernel.
*/
@@ -570,8 +600,8 @@ static void __init map_kernel(pgd_t *pgd)
* entry instead.
*/
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
- set_pud(pud_set_fixmap_offset(pgd, FIXADDR_START),
- __pud(__pa_symbol(bm_pmd) | PUD_TYPE_TABLE));
+ pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START),
+ lm_alias(bm_pmd));
pud_clear_fixmap();
} else {
BUG();
@@ -612,7 +642,8 @@ void __init paging_init(void)
* allocated with it.
*/
memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
- SWAPPER_DIR_SIZE - PAGE_SIZE);
+ __pa_symbol(swapper_pg_end) - __pa_symbol(swapper_pg_dir)
+ - PAGE_SIZE);
}
/*
@@ -686,7 +717,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
if (!p)
return -ENOMEM;
- set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL));
+ pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL));
} else
vmemmap_verify((pte_t *)pmd, node, addr, next);
} while (addr = next, addr != end);
@@ -879,15 +910,19 @@ int __init arch_ioremap_pmd_supported(void)
int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
{
+ pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
+ pgprot_val(mk_sect_prot(prot)));
BUG_ON(phys & ~PUD_MASK);
- set_pud(pud, __pud(phys | PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))));
+ set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot));
return 1;
}
int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
{
+ pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
+ pgprot_val(mk_sect_prot(prot)));
BUG_ON(phys & ~PMD_MASK);
- set_pmd(pmd, __pmd(phys | PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))));
+ set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot));
return 1;
}
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 051e71e..289f911 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -49,6 +49,14 @@ void __init pgd_cache_init(void)
if (PGD_SIZE == PAGE_SIZE)
return;
+#ifdef CONFIG_ARM64_PA_BITS_52
+ /*
+ * With 52-bit physical addresses, the architecture requires the
+ * top-level table to be aligned to at least 64 bytes.
+ */
+ BUILD_BUG_ON(PGD_SIZE < 64);
+#endif
+
/*
* Naturally aligned pgds required by the architecture.
*/
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 95233df..9f177aa 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -70,7 +70,11 @@ ENTRY(cpu_do_suspend)
mrs x8, mdscr_el1
mrs x9, oslsr_el1
mrs x10, sctlr_el1
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
mrs x11, tpidr_el1
+alternative_else
+ mrs x11, tpidr_el2
+alternative_endif
mrs x12, sp_el0
stp x2, x3, [x0]
stp x4, xzr, [x0, #16]
@@ -116,7 +120,11 @@ ENTRY(cpu_do_resume)
msr mdscr_el1, x10
msr sctlr_el1, x12
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
msr tpidr_el1, x13
+alternative_else
+ msr tpidr_el2, x13
+alternative_endif
msr sp_el0, x14
/*
* Restore oslsr_el1 by writing oslar_el1
@@ -124,6 +132,11 @@ ENTRY(cpu_do_resume)
ubfx x11, x11, #1, #1
msr oslar_el1, x11
reset_pmuserenr_el0 x0 // Disable PMU access from EL0
+
+alternative_if ARM64_HAS_RAS_EXTN
+ msr_s SYS_DISR_EL1, xzr
+alternative_else_nop_endif
+
isb
ret
ENDPROC(cpu_do_resume)
@@ -138,13 +151,18 @@ ENDPROC(cpu_do_resume)
* - pgd_phys - physical address of new TTB
*/
ENTRY(cpu_do_switch_mm)
- pre_ttbr0_update_workaround x0, x2, x3
+ mrs x2, ttbr1_el1
mmid x1, x1 // get mm->context.id
- bfi x0, x1, #48, #16 // set the ASID
- msr ttbr0_el1, x0 // set TTBR0
+ phys_to_ttbr x0, x3
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ bfi x3, x1, #48, #16 // set the ASID field in TTBR0
+#endif
+ bfi x2, x1, #48, #16 // set the ASID
+ msr ttbr1_el1, x2 // in TTBR1 (since TCR.A1 is set)
isb
- post_ttbr0_update_workaround
- ret
+ msr ttbr0_el1, x3 // now update TTBR0
+ isb
+ b post_ttbr_update_workaround // Back to C code...
ENDPROC(cpu_do_switch_mm)
.pushsection ".idmap.text", "ax"
@@ -158,14 +176,16 @@ ENTRY(idmap_cpu_replace_ttbr1)
save_and_disable_daif flags=x2
adrp x1, empty_zero_page
- msr ttbr1_el1, x1
+ phys_to_ttbr x1, x3
+ msr ttbr1_el1, x3
isb
tlbi vmalle1
dsb nsh
isb
- msr ttbr1_el1, x0
+ phys_to_ttbr x0, x3
+ msr ttbr1_el1, x3
isb
restore_daif x2
@@ -214,25 +234,19 @@ ENTRY(__cpu_setup)
/*
* Prepare SCTLR
*/
- adr x5, crval
- ldp w5, w6, [x5]
- mrs x0, sctlr_el1
- bic x0, x0, x5 // clear bits
- orr x0, x0, x6 // set bits
+ mov_q x0, SCTLR_EL1_SET
/*
* Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
* both user and kernel.
*/
ldr x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
- TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0
+ TCR_TG_FLAGS | TCR_ASID16 | TCR_TBI0 | TCR_A1
tcr_set_idmap_t0sz x10, x9
/*
- * Read the PARange bits from ID_AA64MMFR0_EL1 and set the IPS bits in
- * TCR_EL1.
+ * Set the IPS bits in TCR_EL1.
*/
- mrs x9, ID_AA64MMFR0_EL1
- bfi x10, x9, #32, #3
+ tcr_compute_pa_size x10, #TCR_IPS_SHIFT, x5, x6
#ifdef CONFIG_ARM64_HW_AFDBM
/*
* Hardware update of the Access and Dirty bits.
@@ -249,21 +263,3 @@ ENTRY(__cpu_setup)
msr tcr_el1, x10
ret // return to head.S
ENDPROC(__cpu_setup)
-
- /*
- * We set the desired value explicitly, including those of the
- * reserved bits. The values of bits EE & E0E were set early in
- * el2_setup, which are left untouched below.
- *
- * n n T
- * U E WT T UD US IHBS
- * CE0 XWHW CZ ME TEEA S
- * .... .IEE .... NEAI TE.I ..AD DEN0 ACAM
- * 0011 0... 1101 ..0. ..0. 10.. .0.. .... < hardware reserved
- * .... .1.. .... 01.1 11.1 ..01 0.01 1101 < software settings
- */
- .type crval, #object
-crval:
- .word 0xfcffffff // clear
- .word 0x34d5d91d // set
- .popsection
OpenPOWER on IntegriCloud