diff options
Diffstat (limited to 'arch/arm64/mm/proc.S')
| -rw-r--r-- | arch/arm64/mm/proc.S | 198 |
1 files changed, 140 insertions, 58 deletions
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 2baeec419f62..01e868116448 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -23,42 +23,50 @@ #include <asm/sysreg.h> #ifdef CONFIG_ARM64_64K_PAGES -#define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K +#define TCR_TG_FLAGS ((TCR_EL1_TG0_64K << TCR_EL1_TG0_SHIFT) |\ + (TCR_EL1_TG1_64K << TCR_EL1_TG1_SHIFT)) #elif defined(CONFIG_ARM64_16K_PAGES) -#define TCR_TG_FLAGS TCR_TG0_16K | TCR_TG1_16K +#define TCR_TG_FLAGS ((TCR_EL1_TG0_16K << TCR_EL1_TG0_SHIFT) |\ + (TCR_EL1_TG1_16K << TCR_EL1_TG1_SHIFT)) #else /* CONFIG_ARM64_4K_PAGES */ -#define TCR_TG_FLAGS TCR_TG0_4K | TCR_TG1_4K +#define TCR_TG_FLAGS ((TCR_EL1_TG0_4K << TCR_EL1_TG0_SHIFT) |\ + (TCR_EL1_TG1_4K << TCR_EL1_TG1_SHIFT)) #endif #ifdef CONFIG_RANDOMIZE_BASE -#define TCR_KASLR_FLAGS TCR_NFD1 +#define TCR_KASLR_FLAGS TCR_EL1_NFD1 #else #define TCR_KASLR_FLAGS 0 #endif -#define TCR_SMP_FLAGS TCR_SHARED - /* PTWs cacheable, inner/outer WBWA */ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA #ifdef CONFIG_KASAN_SW_TAGS -#define TCR_KASAN_SW_FLAGS TCR_TBI1 | TCR_TBID1 +#define TCR_KASAN_SW_FLAGS TCR_EL1_TBI1 | TCR_EL1_TBID1 #else #define TCR_KASAN_SW_FLAGS 0 #endif #ifdef CONFIG_KASAN_HW_TAGS -#define TCR_MTE_FLAGS TCR_TCMA1 | TCR_TBI1 | TCR_TBID1 +#define TCR_MTE_FLAGS TCR_EL1_TCMA1 | TCR_EL1_TBI1 | TCR_EL1_TBID1 #elif defined(CONFIG_ARM64_MTE) /* * The mte_zero_clear_page_tags() implementation uses DC GZVA, which relies on * TBI being enabled at EL1. */ -#define TCR_MTE_FLAGS TCR_TBI1 | TCR_TBID1 +#define TCR_MTE_FLAGS TCR_EL1_TBI1 | TCR_EL1_TBID1 #else #define TCR_MTE_FLAGS 0 #endif +#define TCR_IRGN_WBWA ((TCR_EL1_IRGN0_WBWA << TCR_EL1_IRGN0_SHIFT) |\ + (TCR_EL1_IRGN1_WBWA << TCR_EL1_IRGN1_SHIFT)) +#define TCR_ORGN_WBWA ((TCR_EL1_ORGN0_WBWA << TCR_EL1_ORGN0_SHIFT) |\ + (TCR_EL1_ORGN1_WBWA << TCR_EL1_ORGN1_SHIFT)) +#define TCR_SHARED ((TCR_EL1_SH0_INNER << TCR_EL1_SH0_SHIFT) |\ + (TCR_EL1_SH1_INNER << TCR_EL1_SH1_SHIFT)) + /* * Default MAIR_EL1. MT_NORMAL_TAGGED is initially mapped as Normal memory and * changed during mte_cpu_setup to Normal Tagged if the system supports MTE. @@ -131,18 +139,10 @@ SYM_FUNC_START(cpu_do_resume) /* Don't change t0sz here, mask those bits when restoring */ mrs x7, tcr_el1 - bfi x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH + bfi x8, x7, TCR_EL1_T0SZ_SHIFT, TCR_EL1_T0SZ_WIDTH msr tcr_el1, x8 msr vbar_el1, x9 - - /* - * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking - * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug - * exception. Mask them until local_daif_restore() in cpu_suspend() - * resets them. - */ - disable_daif msr mdscr_el1, x10 msr sctlr_el1, x12 @@ -195,27 +195,36 @@ SYM_TYPED_FUNC_START(idmap_cpu_replace_ttbr1) ret SYM_FUNC_END(idmap_cpu_replace_ttbr1) +SYM_FUNC_ALIAS(__pi_idmap_cpu_replace_ttbr1, idmap_cpu_replace_ttbr1) .popsection #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -#define KPTI_NG_PTE_FLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS | PTE_WRITE) +#define KPTI_NG_PTE_FLAGS (PTE_ATTRINDX(MT_NORMAL) | PTE_TYPE_PAGE | \ + PTE_AF | PTE_SHARED | PTE_UXN | PTE_WRITE) .pushsection ".idmap.text", "a" + .macro pte_to_phys, phys, pte + and \phys, \pte, #PTE_ADDR_LOW +#ifdef CONFIG_ARM64_PA_BITS_52 + and \pte, \pte, #PTE_ADDR_HIGH + orr \phys, \phys, \pte, lsl #PTE_ADDR_HIGH_SHIFT +#endif + .endm + .macro kpti_mk_tbl_ng, type, num_entries add end_\type\()p, cur_\type\()p, #\num_entries * 8 .Ldo_\type: - ldr \type, [cur_\type\()p] // Load the entry + ldr \type, [cur_\type\()p], #8 // Load the entry and advance 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 + str \type, [cur_\type\()p, #-8] // Update the entry .ifnc \type, pte tbnz \type, #1, .Lderef_\type .endif .Lnext_\type: - add cur_\type\()p, cur_\type\()p, #8 cmp cur_\type\()p, end_\type\()p b.ne .Ldo_\type .endm @@ -225,18 +234,18 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1) * fixmap slot associated with the current level. */ .macro kpti_map_pgtbl, type, level - str xzr, [temp_pte, #8 * (\level + 1)] // break before make + str xzr, [temp_pte, #8 * (\level + 2)] // break before make dsb nshst - add pte, temp_pte, #PAGE_SIZE * (\level + 1) + add pte, temp_pte, #PAGE_SIZE * (\level + 2) 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) + add cur_\type\()p, temp_pte, #PAGE_SIZE * (\level + 2) orr pte, pte, pte_flags - str pte, [temp_pte, #8 * (\level + 1)] + str pte, [temp_pte, #8 * (\level + 2)] dsb nshst .endm @@ -246,10 +255,6 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1) * * Called exactly once from stop_machine context by each CPU found during boot. */ - .pushsection ".data", "aw", %progbits -SYM_DATA(__idmap_kpti_flag, .long 1) - .popsection - SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) cpu .req w0 temp_pte .req x0 @@ -269,13 +274,21 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) end_ptep .req x15 pte .req x16 valid .req x17 + cur_p4dp .req x19 + end_p4dp .req x20 mov x5, x3 // preserve temp_pte arg mrs swapper_ttb, ttbr1_el1 - adr_l flag_ptr, __idmap_kpti_flag + adr_l flag_ptr, idmap_kpti_bbml2_flag cbnz cpu, __idmap_kpti_secondary +#if CONFIG_PGTABLE_LEVELS > 4 + stp x29, x30, [sp, #-32]! + mov x29, sp + stp x19, x20, [sp, #16] +#endif + /* We're the boot CPU. Wait for the others to catch up */ sevl 1: wfe @@ -293,9 +306,32 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) mov_q pte_flags, KPTI_NG_PTE_FLAGS /* Everybody is enjoying the idmap, so we can rewrite swapper. */ + +#ifdef CONFIG_ARM64_LPA2 + /* + * If LPA2 support is configured, but 52-bit virtual addressing is not + * enabled at runtime, we will fall back to one level of paging less, + * and so we have to walk swapper_pg_dir as if we dereferenced its + * address from a PGD level entry, and terminate the PGD level loop + * right after. + */ + adrp pgd, swapper_pg_dir // walk &swapper_pg_dir at the next level + mov cur_pgdp, end_pgdp // must be equal to terminate the PGD loop +alternative_if_not ARM64_HAS_VA52 + b .Lderef_pgd // skip to the next level +alternative_else_nop_endif + /* + * LPA2 based 52-bit virtual addressing requires 52-bit physical + * addressing to be enabled as well. In this case, the shareability + * bits are repurposed as physical address bits, and should not be + * set in pte_flags. + */ + bic pte_flags, pte_flags, #PTE_SHARED +#endif + /* PGD */ adrp cur_pgdp, swapper_pg_dir - kpti_map_pgtbl pgd, 0 + kpti_map_pgtbl pgd, -1 kpti_mk_tbl_ng pgd, PTRS_PER_PGD /* Ensure all the updated entries are visible to secondary CPUs */ @@ -308,16 +344,33 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) /* Set the flag to zero to indicate that we're all done */ str wzr, [flag_ptr] +#if CONFIG_PGTABLE_LEVELS > 4 + ldp x19, x20, [sp, #16] + ldp x29, x30, [sp], #32 +#endif ret .Lderef_pgd: + /* P4D */ + .if CONFIG_PGTABLE_LEVELS > 4 + p4d .req x30 + pte_to_phys cur_p4dp, pgd + kpti_map_pgtbl p4d, 0 + kpti_mk_tbl_ng p4d, PTRS_PER_P4D + b .Lnext_pgd + .else /* CONFIG_PGTABLE_LEVELS <= 4 */ + p4d .req pgd + .set .Lnext_p4d, .Lnext_pgd + .endif + +.Lderef_p4d: /* PUD */ .if CONFIG_PGTABLE_LEVELS > 3 pud .req x10 - pte_to_phys cur_pudp, pgd + pte_to_phys cur_pudp, p4d kpti_map_pgtbl pud, 1 kpti_mk_tbl_ng pud, PTRS_PER_PUD - b .Lnext_pgd + b .Lnext_p4d .else /* CONFIG_PGTABLE_LEVELS <= 3 */ pud .req pgd .set .Lnext_pud, .Lnext_pgd @@ -361,12 +414,33 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) .unreq end_ptep .unreq pte .unreq valid + .unreq cur_p4dp + .unreq end_p4dp + .unreq p4d /* Secondary CPUs end up here */ __idmap_kpti_secondary: /* Uninstall swapper before surgery begins */ __idmap_cpu_set_reserved_ttbr1 x16, x17 + b scondary_cpu_wait + + .unreq swapper_ttb + .unreq flag_ptr +SYM_FUNC_END(idmap_kpti_install_ng_mappings) + .popsection +#endif + + .pushsection ".idmap.text", "a" +SYM_TYPED_FUNC_START(wait_linear_map_split_to_ptes) + /* Must be same registers as in idmap_kpti_install_ng_mappings */ + swapper_ttb .req x3 + flag_ptr .req x4 + + mrs swapper_ttb, ttbr1_el1 + adr_l flag_ptr, idmap_kpti_bbml2_flag + __idmap_cpu_set_reserved_ttbr1 x16, x17 +scondary_cpu_wait: /* Increment the flag to let the boot CPU we're ready */ 1: ldxr w16, [flag_ptr] add w16, w16, #1 @@ -386,17 +460,14 @@ __idmap_kpti_secondary: .unreq swapper_ttb .unreq flag_ptr -SYM_FUNC_END(idmap_kpti_install_ng_mappings) +SYM_FUNC_END(wait_linear_map_split_to_ptes) .popsection -#endif /* * __cpu_setup * * Initialise the processor for turning the MMU on. * - * Input: - * x0 - actual number of VA bits (ignored unless VA_BITS > 48) * Output: * Return in x0 the value of the SCTLR_EL1 register. */ @@ -405,12 +476,9 @@ SYM_FUNC_START(__cpu_setup) tlbi vmalle1 // Invalidate local TLB dsb nsh - mov x1, #3 << 20 - msr cpacr_el1, x1 // Enable FP/ASIMD - mov x1, #1 << 12 // Reset mdscr_el1 and disable + msr cpacr_el1, xzr // Reset cpacr_el1 + mov x1, MDSCR_EL1_TDCC // Reset mdscr_el1 and disable msr mdscr_el1, x1 // access to the DCC from EL0 - isb // Unmask debug exceptions now, - enable_dbg // since this is per-cpu reset_pmuserenr_el0 x1 // Disable PMU access from EL0 reset_amuserenr_el0 x1 // Disable AMU access from EL0 @@ -420,26 +488,29 @@ SYM_FUNC_START(__cpu_setup) */ mair .req x17 tcr .req x16 + tcr2 .req x15 mov_q mair, MAIR_EL1_SET - mov_q tcr, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ - TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ - TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS + mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS_MIN) | TCR_CACHE_FLAGS | \ + TCR_SHARED | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_EL1_AS | \ + TCR_EL1_TBI0 | TCR_EL1_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS + mov tcr2, xzr tcr_clear_errata_bits tcr, x9, x5 #ifdef CONFIG_ARM64_VA_BITS_52 - sub x9, xzr, x0 - add x9, x9, #64 + mov x9, #64 - VA_BITS +alternative_if ARM64_HAS_VA52 tcr_set_t1sz tcr, x9 -#else - idmap_get_t0sz x9 +#ifdef CONFIG_ARM64_LPA2 + orr tcr, tcr, #TCR_EL1_DS +#endif +alternative_else_nop_endif #endif - tcr_set_t0sz tcr, x9 /* * Set the IPS bits in TCR_EL1. */ - tcr_compute_pa_size tcr, #TCR_IPS_SHIFT, x5, x6 + tcr_compute_pa_size tcr, #TCR_EL1_IPS_SHIFT, x5, x6 #ifdef CONFIG_ARM64_HW_AFDBM /* * Enable hardware update of the Access Flags bit. @@ -447,9 +518,14 @@ SYM_FUNC_START(__cpu_setup) * via capabilities. */ mrs x9, ID_AA64MMFR1_EL1 - and x9, x9, #0xf + ubfx x9, x9, ID_AA64MMFR1_EL1_HAFDBS_SHIFT, #4 cbz x9, 1f - orr tcr, tcr, #TCR_HA // hardware Access flag update + orr tcr, tcr, #TCR_EL1_HA // hardware Access flag update +#ifdef CONFIG_ARM64_HAFT + cmp x9, ID_AA64MMFR1_EL1_HAFDBS_HAFT + b.lt 1f + orr tcr2, tcr2, TCR2_EL1_HAFT +#endif /* CONFIG_ARM64_HAFT */ 1: #endif /* CONFIG_ARM64_HW_AFDBM */ msr mair_el1, mair @@ -459,16 +535,21 @@ SYM_FUNC_START(__cpu_setup) ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4 cbz x1, .Lskip_indirection - mov_q x0, PIE_E0 + mov_q x0, PIE_E0_ASM msr REG_PIRE0_EL1, x0 - mov_q x0, PIE_E1 + mov_q x0, PIE_E1_ASM msr REG_PIR_EL1, x0 - mov x0, TCR2_EL1x_PIE - msr REG_TCR2_EL1, x0 + orr tcr2, tcr2, TCR2_EL1_PIE .Lskip_indirection: + mrs_s x1, SYS_ID_AA64MMFR3_EL1 + ubfx x1, x1, #ID_AA64MMFR3_EL1_TCRX_SHIFT, #4 + cbz x1, 1f + msr REG_TCR2_EL1, tcr2 +1: + /* * Prepare SCTLR */ @@ -477,4 +558,5 @@ SYM_FUNC_START(__cpu_setup) .unreq mair .unreq tcr + .unreq tcr2 SYM_FUNC_END(__cpu_setup) |