arm64: Add support for FEAT_HAFT

Armv8.9/v9.4 introduces the feature Hardware managed Access Flag
for Table descriptors (FEAT_HAFT). The feature is indicated by
ID_AA64MMFR1_EL1.HAFDBS == 0b0011 and can be enabled by
TCR2_EL1.HAFT so it has a dependency on FEAT_TCR2.

Adds the Kconfig for FEAT_HAFT and support detecting and enabling
the feature. The feature is enabled in __cpu_setup() before MMU on
just like HA. A CPU capability is added to notify the user of the
feature.

Add definition of P{G,4,U,M}D_TABLE_AF bit and set the AF bit
when creating the page table, which will save the hardware
from having to update them at runtime. This will be ignored if
FEAT_HAFT is not enabled.

The AF bit of table descriptors cannot be managed by the software
per spec, unlike the HA. So this should be used only if it's supported
system wide by system_supports_haft().

Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Link: https://lore.kernel.org/r/20241102104235.62560-4-yangyicong@huawei.com
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
[catalin.marinas@arm.com: added the ID check back to __cpu_setup in case of future CPU errata]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3e29b44..b90f92f 100644 (file)
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2176,6 +2176,21 @@ config ARCH_PKEY_BITS
        int
        default 3
 
+config ARM64_HAFT
+       bool "Support for Hardware managed Access Flag for Table Descriptors"
+       depends on ARM64_HW_AFDBM
+       default y
+       help
+         The ARMv8.9/ARMv9.5 introduces the feature Hardware managed Access
+         Flag for Table descriptors. When enabled an architectural executed
+         memory access will update the Access Flag in each Table descriptor
+         which is accessed during the translation table walk and for which
+         the Access Flag is 0. The Access Flag of the Table descriptor use
+         the same bit of PTE_AF.
+
+         The feature will only be enabled if all the CPUs in the system
+         support this feature. If unsure, say Y.
+
 endmenu # "ARMv8.9 architectural features"
 
 config ARM64_SVE

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 3d261cc..ed8c784 100644 (file)
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -838,6 +838,12 @@ static inline bool system_supports_poe(void)
                alternative_has_cap_unlikely(ARM64_HAS_S1POE);
 }
 
+static inline bool system_supports_haft(void)
+{
+       return IS_ENABLED(CONFIG_ARM64_HAFT) &&
+               cpus_have_final_cap(ARM64_HAFT);
+}
+
 int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
 

diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 8ff5f2a..e754228 100644 (file)
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -28,7 +28,7 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
 {
-       pudval_t pudval = PUD_TYPE_TABLE;
+       pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_AF;
 
        pudval |= (mm == &init_mm) ? PUD_TABLE_UXN : PUD_TABLE_PXN;
        __pud_populate(pudp, __pa(pmdp), pudval);
@@ -50,7 +50,7 @@ static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
 
 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
 {
-       p4dval_t p4dval = P4D_TYPE_TABLE;
+       p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_AF;
 
        p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN;
        __p4d_populate(p4dp, __pa(pudp), p4dval);
@@ -79,7 +79,7 @@ static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot)
 
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp)
 {
-       pgdval_t pgdval = PGD_TYPE_TABLE;
+       pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_AF;
 
        pgdval |= (mm == &init_mm) ? PGD_TABLE_UXN : PGD_TABLE_PXN;
        __pgd_populate(pgdp, __pa(p4dp), pgdval);
@@ -127,14 +127,16 @@ static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
 {
        VM_BUG_ON(mm && mm != &init_mm);
-       __pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN);
+       __pmd_populate(pmdp, __pa(ptep),
+                      PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_UXN);
 }
 
 static inline void
 pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
 {
        VM_BUG_ON(mm == &init_mm);
-       __pmd_populate(pmdp, page_to_phys(ptep), PMD_TYPE_TABLE | PMD_TABLE_PXN);
+       __pmd_populate(pmdp, page_to_phys(ptep),
+                      PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_PXN);
 }
 
 #endif

diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index fd330c1..c78a988 100644 (file)
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -99,6 +99,7 @@
 #define PGD_TYPE_TABLE         (_AT(pgdval_t, 3) << 0)
 #define PGD_TABLE_BIT          (_AT(pgdval_t, 1) << 1)
 #define PGD_TYPE_MASK          (_AT(pgdval_t, 3) << 0)
+#define PGD_TABLE_AF           (_AT(pgdval_t, 1) << 10)        /* Ignored if no FEAT_HAFT */
 #define PGD_TABLE_PXN          (_AT(pgdval_t, 1) << 59)
 #define PGD_TABLE_UXN          (_AT(pgdval_t, 1) << 60)
 
@@ -110,6 +111,7 @@
 #define P4D_TYPE_MASK          (_AT(p4dval_t, 3) << 0)
 #define P4D_TYPE_SECT          (_AT(p4dval_t, 1) << 0)
 #define P4D_SECT_RDONLY                (_AT(p4dval_t, 1) << 7)         /* AP[2] */
+#define P4D_TABLE_AF           (_AT(p4dval_t, 1) << 10)        /* Ignored if no FEAT_HAFT */
 #define P4D_TABLE_PXN          (_AT(p4dval_t, 1) << 59)
 #define P4D_TABLE_UXN          (_AT(p4dval_t, 1) << 60)
 
@@ -121,6 +123,7 @@
 #define PUD_TYPE_MASK          (_AT(pudval_t, 3) << 0)
 #define PUD_TYPE_SECT          (_AT(pudval_t, 1) << 0)
 #define PUD_SECT_RDONLY                (_AT(pudval_t, 1) << 7)         /* AP[2] */
+#define PUD_TABLE_AF           (_AT(pudval_t, 1) << 10)        /* Ignored if no FEAT_HAFT */
 #define PUD_TABLE_PXN          (_AT(pudval_t, 1) << 59)
 #define PUD_TABLE_UXN          (_AT(pudval_t, 1) << 60)
 
@@ -131,6 +134,7 @@
 #define PMD_TYPE_TABLE         (_AT(pmdval_t, 3) << 0)
 #define PMD_TYPE_SECT          (_AT(pmdval_t, 1) << 0)
 #define PMD_TABLE_BIT          (_AT(pmdval_t, 1) << 1)
+#define PMD_TABLE_AF           (_AT(pmdval_t, 1) << 10)        /* Ignored if no FEAT_HAFT */
 
 /*
  * Section

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 718728a..878712f 100644 (file)
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2590,6 +2590,21 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
                .cpus = &dbm_cpus,
                ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, DBM)
        },
+#endif
+#ifdef CONFIG_ARM64_HAFT
+       {
+               .desc = "Hardware managed Access Flag for Table Descriptors",
+               /*
+                * Contrary to the page/block access flag, the table access flag
+                * cannot be emulated in software (no access fault will occur).
+                * Therefore this should be used only if it's supported system
+                * wide.
+                */
+               .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+               .capability = ARM64_HAFT,
+               .matches = has_cpuid_feature,
+               ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, HAFT)
+       },
 #endif
        {
                .desc = "CRC32 instructions",

diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c
index de1e09d..c5c5425 100644 (file)
--- a/arch/arm64/mm/fixmap.c
+++ b/arch/arm64/mm/fixmap.c
@@ -47,7 +47,8 @@ static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr)
 
        if (pmd_none(pmd)) {
                ptep = bm_pte[BM_PTE_TABLE_IDX(addr)];
-               __pmd_populate(pmdp, __pa_symbol(ptep), PMD_TYPE_TABLE);
+               __pmd_populate(pmdp, __pa_symbol(ptep),
+                              PMD_TYPE_TABLE | PMD_TABLE_AF);
        }
 }
 
@@ -59,7 +60,8 @@ static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr,
        pmd_t *pmdp;
 
        if (pud_none(pud))
-               __pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE);
+               __pud_populate(pudp, __pa_symbol(bm_pmd),
+                              PUD_TYPE_TABLE | PUD_TABLE_AF);
 
        pmdp = pmd_offset_kimg(pudp, addr);
        do {
@@ -86,7 +88,8 @@ static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr,
        }
 
        if (p4d_none(p4d))
-               __p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE);
+               __p4d_populate(p4dp, __pa_symbol(bm_pud),
+                              P4D_TYPE_TABLE | P4D_TABLE_AF);
 
        pudp = pud_offset_kimg(p4dp, addr);
        early_fixmap_init_pmd(pudp, addr, end);

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e55b02f..6441a45 100644 (file)
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -201,7 +201,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 
        BUG_ON(pmd_sect(pmd));
        if (pmd_none(pmd)) {
-               pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
+               pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN | PMD_TABLE_AF;
                phys_addr_t pte_phys;
 
                if (flags & NO_EXEC_MAPPINGS)
@@ -288,7 +288,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
         */
        BUG_ON(pud_sect(pud));
        if (pud_none(pud)) {
-               pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
+               pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN | PUD_TABLE_AF;
                phys_addr_t pmd_phys;
 
                if (flags & NO_EXEC_MAPPINGS)
@@ -333,7 +333,7 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
        pud_t *pudp;
 
        if (p4d_none(p4d)) {
-               p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN;
+               p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN | P4D_TABLE_AF;
                phys_addr_t pud_phys;
 
                if (flags & NO_EXEC_MAPPINGS)
@@ -391,7 +391,7 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
        p4d_t *p4dp;
 
        if (pgd_none(pgd)) {
-               pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN;
+               pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN | PGD_TABLE_AF;
                phys_addr_t p4d_phys;
 
                if (flags & NO_EXEC_MAPPINGS)

diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index ccbae45..b8edc57 100644 (file)
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -495,9 +495,14 @@ alternative_else_nop_endif
         * via capabilities.
         */
        mrs     x9, ID_AA64MMFR1_EL1
-       and     x9, x9, ID_AA64MMFR1_EL1_HAFDBS_MASK
+       ubfx    x9, x9, ID_AA64MMFR1_EL1_HAFDBS_SHIFT, #4
        cbz     x9, 1f
        orr     tcr, tcr, #TCR_HA               // hardware Access flag update
+#ifdef CONFIG_ARM64_HAFT
+       cmp     x9, ID_AA64MMFR1_EL1_HAFDBS_HAFT
+       b.lt    1f
+       orr     tcr2, tcr2, TCR2_EL1x_HAFT
+#endif /* CONFIG_ARM64_HAFT */
 1:
 #endif /* CONFIG_ARM64_HW_AFDBM */
        msr     mair_el1, mair

diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index eedb5ac..b35004f 100644 (file)
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -56,6 +56,7 @@ HAS_TLB_RANGE
 HAS_VA52
 HAS_VIRT_HOST_EXTN
 HAS_WFXT
+HAFT
 HW_DBM
 KVM_HVHE
 KVM_PROTECTED_MODE