From 4330e2c5c04c27bebf89d34e0bc14e6943413067 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 17 Nov 2021 15:15:26 +0000 Subject: arm64: entry.S: Add ventry overflow sanity checks Subsequent patches add even more code to the ventry slots. Ensure kernels that overflow a ventry slot don't get built. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 772ec2ecf488..bd940b2254da 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -37,6 +37,7 @@ .macro kernel_ventry, el:req, ht:req, regsize:req, label:req .align 7 +.Lventry_start\@: #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 .if \el == 0 alternative_if ARM64_UNMAP_KERNEL_AT_EL0 @@ -95,6 +96,7 @@ alternative_else_nop_endif mrs x0, tpidrro_el0 #endif b el\el\ht\()_\regsize\()_\label +.org .Lventry_start\@ + 128 // Did we overflow the ventry slot? .endm .macro tramp_alias, dst, sym @@ -662,6 +664,7 @@ alternative_else_nop_endif add x30, x30, #(1b - tramp_vectors) isb ret +.org 1b + 128 // Did we overflow the ventry slot? .endm .macro tramp_exit, regsize = 64 -- cgit v1.2.3 From 1b33d4860deaecf1d8eec3061b7e7ed7ab0bae8d Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 16 Nov 2021 15:00:51 +0000 Subject: arm64: spectre: Rename spectre_v4_patch_fw_mitigation_conduit The spectre-v4 sequence includes an SMC from the assembly entry code. spectre_v4_patch_fw_mitigation_conduit is the patching callback that generates an HVC or SMC depending on the SMCCC conduit type. As this isn't specific to spectre-v4, rename it smccc_patch_fw_mitigation_conduit so it can be re-used. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 2 +- arch/arm64/kernel/proton-pack.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index bd940b2254da..d97eb024adec 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -118,7 +118,7 @@ alternative_cb_end tbnz \tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 mov w1, #\state -alternative_cb spectre_v4_patch_fw_mitigation_conduit +alternative_cb smccc_patch_fw_mitigation_conduit nop // Patched to SMC/HVC #0 alternative_cb_end .L__asm_ssbd_skip\@: diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 902e4084c477..9394f21d7566 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -554,9 +554,9 @@ void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt, * Patch a NOP in the Spectre-v4 mitigation code with an SMC/HVC instruction * to call into firmware to adjust the mitigation state. */ -void __init spectre_v4_patch_fw_mitigation_conduit(struct alt_instr *alt, - __le32 *origptr, - __le32 *updptr, int nr_inst) +void __init smccc_patch_fw_mitigation_conduit(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) { u32 insn; -- cgit v1.2.3 From d739da1694a0eaef0358a42b76904b611539b77b Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 24 Nov 2021 15:36:12 +0000 Subject: arm64: entry: Make the trampoline cleanup optional Subsequent patches will add additional sets of vectors that use the same tricks as the kpti vectors to reach the full-fat vectors. The full-fat vectors contain some cleanup for kpti that is patched in by alternatives when kpti is in use. Once there are additional vectors, the cleanup will be needed in more cases. But on big/little systems, the cleanup would be harmful if no trampoline vector were in use. Instead of forcing CPUs that don't need a trampoline vector to use one, make the trampoline cleanup optional. Entry at the top of the vectors will skip the cleanup. The trampoline vectors can then skip the first instruction, triggering the cleanup to run. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index d97eb024adec..bdbdb92b5f77 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -40,14 +40,18 @@ .Lventry_start\@: #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 .if \el == 0 -alternative_if ARM64_UNMAP_KERNEL_AT_EL0 + /* + * This must be the first instruction of the EL0 vector entries. It is + * skipped by the trampoline vectors, to trigger the cleanup. + */ + b .Lskip_tramp_vectors_cleanup\@ .if \regsize == 64 mrs x30, tpidrro_el0 msr tpidrro_el0, xzr .else mov x30, xzr .endif -alternative_else_nop_endif +.Lskip_tramp_vectors_cleanup\@: .endif #endif @@ -661,7 +665,7 @@ alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM prfm plil1strm, [x30, #(1b - tramp_vectors)] alternative_else_nop_endif msr vbar_el1, x30 - add x30, x30, #(1b - tramp_vectors) + add x30, x30, #(1b - tramp_vectors + 4) isb ret .org 1b + 128 // Did we overflow the ventry slot? -- cgit v1.2.3 From 03aff3a77a58b5b52a77e00537a42090ad57b80b Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 23 Nov 2021 18:41:43 +0000 Subject: arm64: entry: Free up another register on kpti's tramp_exit path Kpti stashes x30 in far_el1 while it uses x30 for all its work. Making the vectors a per-cpu data structure will require a second register. Allow tramp_exit two registers before it unmaps the kernel, by leaving x30 on the stack, and stashing x29 in far_el1. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index bdbdb92b5f77..45e89135dc11 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -419,14 +419,16 @@ alternative_else_nop_endif ldp x24, x25, [sp, #16 * 12] ldp x26, x27, [sp, #16 * 13] ldp x28, x29, [sp, #16 * 14] - ldr lr, [sp, #S_LR] - add sp, sp, #PT_REGS_SIZE // restore sp .if \el == 0 -alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 +alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 + ldr lr, [sp, #S_LR] + add sp, sp, #PT_REGS_SIZE // restore sp + eret +alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 bne 4f - msr far_el1, x30 + msr far_el1, x29 tramp_alias x30, tramp_exit_native br x30 4: @@ -434,6 +436,9 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 br x30 #endif .else + ldr lr, [sp, #S_LR] + add sp, sp, #PT_REGS_SIZE // restore sp + /* Ensure any device/NC reads complete */ alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412 @@ -674,10 +679,12 @@ alternative_else_nop_endif .macro tramp_exit, regsize = 64 adr x30, tramp_vectors msr vbar_el1, x30 - tramp_unmap_kernel x30 + ldr lr, [sp, #S_LR] + tramp_unmap_kernel x29 .if \regsize == 64 - mrs x30, far_el1 + mrs x29, far_el1 .endif + add sp, sp, #PT_REGS_SIZE // restore sp eret sb .endm -- cgit v1.2.3 From c091fb6ae059cda563b2a4d93fdbc548ef34e1d6 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 23 Nov 2021 15:43:31 +0000 Subject: arm64: entry: Move the trampoline data page before the text page The trampoline code has a data page that holds the address of the vectors, which is unmapped when running in user-space. This ensures that with CONFIG_RANDOMIZE_BASE, the randomised address of the kernel can't be discovered until after the kernel has been mapped. If the trampoline text page is extended to include multiple sets of vectors, it will be larger than a single page, making it tricky to find the data page without knowing the size of the trampoline text pages, which will vary with PAGE_SIZE. Move the data page to appear before the text page. This allows the data page to be found without knowing the size of the trampoline text pages. 'tramp_vectors' is used to refer to the beginning of the .entry.tramp.text section, do that explicitly. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/include/asm/fixmap.h | 2 +- arch/arm64/kernel/entry.S | 9 +++++++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 4335800201c9..0aabc0253b18 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -62,8 +62,8 @@ enum fixed_addresses { #endif /* CONFIG_ACPI_APEI_GHES */ #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - FIX_ENTRY_TRAMP_DATA, FIX_ENTRY_TRAMP_TEXT, + FIX_ENTRY_TRAMP_DATA, #define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT)) #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ __end_of_permanent_fixed_addresses, diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 45e89135dc11..d8a76869e873 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -644,6 +644,11 @@ alternative_else_nop_endif */ .endm + .macro tramp_data_page dst + adr \dst, .entry.tramp.text + sub \dst, \dst, PAGE_SIZE + .endm + .macro tramp_ventry, regsize = 64 .align 7 1: @@ -660,7 +665,7 @@ alternative_else_nop_endif 2: tramp_map_kernel x30 #ifdef CONFIG_RANDOMIZE_BASE - adr x30, tramp_vectors + PAGE_SIZE + tramp_data_page x30 alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 ldr x30, [x30] #else @@ -851,7 +856,7 @@ SYM_CODE_START(__sdei_asm_entry_trampoline) 1: str x4, [x1, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)] #ifdef CONFIG_RANDOMIZE_BASE - adr x4, tramp_vectors + PAGE_SIZE + tramp_data_page x4 add x4, x4, #:lo12:__sdei_asm_trampoline_next_handler ldr x4, [x4] #else -- cgit v1.2.3 From 6c5bf79b69f911560fbf82214c0971af6e58e682 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 24 Nov 2021 11:40:18 +0000 Subject: arm64: entry: Allow tramp_alias to access symbols after the 4K boundary Systems using kpti enter and exit the kernel through a trampoline mapping that is always mapped, even when the kernel is not. tramp_valias is a macro to find the address of a symbol in the trampoline mapping. Adding extra sets of vectors will expand the size of the entry.tramp.text section to beyond 4K. tramp_valias will be unable to generate addresses for symbols beyond 4K as it uses the 12 bit immediate of the add instruction. As there are now two registers available when tramp_alias is called, use the extra register to avoid the 4K limit of the 12 bit immediate. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index d8a76869e873..192cf77bd374 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -103,9 +103,12 @@ .org .Lventry_start\@ + 128 // Did we overflow the ventry slot? .endm - .macro tramp_alias, dst, sym + .macro tramp_alias, dst, sym, tmp mov_q \dst, TRAMP_VALIAS - add \dst, \dst, #(\sym - .entry.tramp.text) + adr_l \tmp, \sym + add \dst, \dst, \tmp + adr_l \tmp, .entry.tramp.text + sub \dst, \dst, \tmp .endm /* @@ -429,10 +432,10 @@ alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 bne 4f msr far_el1, x29 - tramp_alias x30, tramp_exit_native + tramp_alias x30, tramp_exit_native, x29 br x30 4: - tramp_alias x30, tramp_exit_compat + tramp_alias x30, tramp_exit_compat, x29 br x30 #endif .else @@ -1000,7 +1003,7 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline + tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline, tmp=x3 br x5 #endif SYM_CODE_END(__sdei_asm_handler) -- cgit v1.2.3 From ed50da7764535f1e24432ded289974f2bf2b0c5a Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 24 Nov 2021 13:40:09 +0000 Subject: arm64: entry: Don't assume tramp_vectors is the start of the vectors The tramp_ventry macro uses tramp_vectors as the address of the vectors when calculating which ventry in the 'full fat' vectors to branch to. While there is one set of tramp_vectors, this will be true. Adding multiple sets of vectors will break this assumption. Move the generation of the vectors to a macro, and pass the start of the vectors as an argument to tramp_ventry. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 192cf77bd374..4e6b8d97d941 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -652,7 +652,7 @@ alternative_else_nop_endif sub \dst, \dst, PAGE_SIZE .endm - .macro tramp_ventry, regsize = 64 + .macro tramp_ventry, vector_start, regsize .align 7 1: .if \regsize == 64 @@ -675,10 +675,10 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 ldr x30, =vectors #endif alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM - prfm plil1strm, [x30, #(1b - tramp_vectors)] + prfm plil1strm, [x30, #(1b - \vector_start)] alternative_else_nop_endif msr vbar_el1, x30 - add x30, x30, #(1b - tramp_vectors + 4) + add x30, x30, #(1b - \vector_start + 4) isb ret .org 1b + 128 // Did we overflow the ventry slot? @@ -697,19 +697,21 @@ alternative_else_nop_endif sb .endm - .align 11 -SYM_CODE_START_NOALIGN(tramp_vectors) + .macro generate_tramp_vector +.Lvector_start\@: .space 0x400 - tramp_ventry - tramp_ventry - tramp_ventry - tramp_ventry + .rept 4 + tramp_ventry .Lvector_start\@, 64 + .endr + .rept 4 + tramp_ventry .Lvector_start\@, 32 + .endr + .endm - tramp_ventry 32 - tramp_ventry 32 - tramp_ventry 32 - tramp_ventry 32 + .align 11 +SYM_CODE_START_NOALIGN(tramp_vectors) + generate_tramp_vector SYM_CODE_END(tramp_vectors) SYM_CODE_START(tramp_exit_native) -- cgit v1.2.3 From 13d7a08352a83ef2252aeb464a5e08dfc06b5dfd Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 18 Nov 2021 14:02:30 +0000 Subject: arm64: entry: Move trampoline macros out of ifdef'd section The macros for building the kpti trampoline are all behind CONFIG_UNMAP_KERNEL_AT_EL0, and in a region that outputs to the .entry.tramp.text section. Move the macros out so they can be used to generate other kinds of trampoline. Only the symbols need to be guarded by CONFIG_UNMAP_KERNEL_AT_EL0 and appear in the .entry.tramp.text section. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 4e6b8d97d941..2735c8941c2d 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -608,12 +608,6 @@ SYM_CODE_END(ret_to_user) .popsection // .entry.text -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -/* - * Exception vectors trampoline. - */ - .pushsection ".entry.tramp.text", "ax" - // Move from tramp_pg_dir to swapper_pg_dir .macro tramp_map_kernel, tmp mrs \tmp, ttbr1_el1 @@ -709,6 +703,11 @@ alternative_else_nop_endif .endr .endm +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +/* + * Exception vectors trampoline. + */ + .pushsection ".entry.tramp.text", "ax" .align 11 SYM_CODE_START_NOALIGN(tramp_vectors) generate_tramp_vector -- cgit v1.2.3 From c47e4d04ba0f1ea17353d85d45f611277507e07a Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 18 Nov 2021 13:16:23 +0000 Subject: arm64: entry: Make the kpti trampoline's kpti sequence optional Spectre-BHB needs to add sequences to the vectors. Having one global set of vectors is a problem for big/little systems where the sequence is costly on cpus that are not vulnerable. Making the vectors per-cpu in the style of KVM's bh_harden_hyp_vecs requires the vectors to be generated by macros. Make the kpti re-mapping of the kernel optional, so the macros can be used without kpti. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2735c8941c2d..23e85c94ea36 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -646,9 +646,10 @@ alternative_else_nop_endif sub \dst, \dst, PAGE_SIZE .endm - .macro tramp_ventry, vector_start, regsize + .macro tramp_ventry, vector_start, regsize, kpti .align 7 1: + .if \kpti == 1 .if \regsize == 64 msr tpidrro_el0, x30 // Restored in kernel_ventry .endif @@ -671,9 +672,14 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM prfm plil1strm, [x30, #(1b - \vector_start)] alternative_else_nop_endif + msr vbar_el1, x30 - add x30, x30, #(1b - \vector_start + 4) isb + .else + ldr x30, =vectors + .endif // \kpti == 1 + + add x30, x30, #(1b - \vector_start + 4) ret .org 1b + 128 // Did we overflow the ventry slot? .endm @@ -691,15 +697,15 @@ alternative_else_nop_endif sb .endm - .macro generate_tramp_vector + .macro generate_tramp_vector, kpti .Lvector_start\@: .space 0x400 .rept 4 - tramp_ventry .Lvector_start\@, 64 + tramp_ventry .Lvector_start\@, 64, \kpti .endr .rept 4 - tramp_ventry .Lvector_start\@, 32 + tramp_ventry .Lvector_start\@, 32, \kpti .endr .endm @@ -710,7 +716,7 @@ alternative_else_nop_endif .pushsection ".entry.tramp.text", "ax" .align 11 SYM_CODE_START_NOALIGN(tramp_vectors) - generate_tramp_vector + generate_tramp_vector kpti=1 SYM_CODE_END(tramp_vectors) SYM_CODE_START(tramp_exit_native) -- cgit v1.2.3 From a9c406e6462ff14956d690de7bbe5131a5677dc9 Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 18 Nov 2021 15:04:32 +0000 Subject: arm64: entry: Allow the trampoline text to occupy multiple pages Adding a second set of vectors to .entry.tramp.text will make it larger than a single 4K page. Allow the trampoline text to occupy up to three pages by adding two more fixmap slots. Previous changes to tramp_valias allowed it to reach beyond a single page. Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/include/asm/fixmap.h | 6 ++++-- arch/arm64/include/asm/sections.h | 5 +++++ arch/arm64/kernel/entry.S | 2 +- arch/arm64/kernel/vmlinux.lds.S | 2 +- arch/arm64/mm/mmu.c | 12 +++++++++--- 5 files changed, 20 insertions(+), 7 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 0aabc0253b18..daff882883f9 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -62,9 +62,11 @@ enum fixed_addresses { #endif /* CONFIG_ACPI_APEI_GHES */ #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - FIX_ENTRY_TRAMP_TEXT, + FIX_ENTRY_TRAMP_TEXT3, + FIX_ENTRY_TRAMP_TEXT2, + FIX_ENTRY_TRAMP_TEXT1, FIX_ENTRY_TRAMP_DATA, -#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT)) +#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT1)) #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ __end_of_permanent_fixed_addresses, diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 152cb35bf9df..40971ac1303f 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -23,4 +23,9 @@ extern char __mmuoff_data_start[], __mmuoff_data_end[]; extern char __entry_tramp_text_start[], __entry_tramp_text_end[]; extern char __relocate_new_kernel_start[], __relocate_new_kernel_end[]; +static inline size_t entry_tramp_text_size(void) +{ + return __entry_tramp_text_end - __entry_tramp_text_start; +} + #endif /* __ASM_SECTIONS_H */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 23e85c94ea36..e0a0c1da5db8 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -642,7 +642,7 @@ alternative_else_nop_endif .endm .macro tramp_data_page dst - adr \dst, .entry.tramp.text + adr_l \dst, .entry.tramp.text sub \dst, \dst, PAGE_SIZE .endm diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 50bab186c49b..edaf0faf766f 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -341,7 +341,7 @@ ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1)) <= SZ_4K, "Hibernate exit text too big or misaligned") #endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE, +ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE, "Entry trampoline text too big") #endif #ifdef CONFIG_KVM diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index acfae9b41cc8..49abbf43bf35 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -617,6 +617,8 @@ early_param("rodata", parse_rodata); #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static int __init map_entry_trampoline(void) { + int i; + pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC; phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start); @@ -625,11 +627,15 @@ static int __init map_entry_trampoline(void) /* 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); + __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, + entry_tramp_text_size(), prot, + __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS); /* Map both the text and data into the kernel page table */ - __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot); + for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++) + __set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i, + pa_start + i * PAGE_SIZE, prot); + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern char __entry_tramp_data_start[]; -- cgit v1.2.3 From aff65393fa1401e034656e349abd655cfe272de0 Mon Sep 17 00:00:00 2001 From: James Morse Date: Wed, 24 Nov 2021 15:03:15 +0000 Subject: arm64: entry: Add non-kpti __bp_harden_el1_vectors for mitigations kpti is an optional feature, for systems not using kpti a set of vectors for the spectre-bhb mitigations is needed. Add another set of vectors, __bp_harden_el1_vectors, that will be used if a mitigation is needed and kpti is not in use. The EL1 ventries are repeated verbatim as there is no additional work needed for entry from EL1. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index e0a0c1da5db8..9c4ff75f983e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -649,10 +649,11 @@ alternative_else_nop_endif .macro tramp_ventry, vector_start, regsize, kpti .align 7 1: - .if \kpti == 1 .if \regsize == 64 msr tpidrro_el0, x30 // Restored in kernel_ventry .endif + + .if \kpti == 1 /* * Defend against branch aliasing attacks by pushing a dummy * entry onto the return stack and using a RET instruction to @@ -739,6 +740,38 @@ SYM_DATA_END(__entry_tramp_data_start) #endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ +/* + * Exception vectors for spectre mitigations on entry from EL1 when + * kpti is not in use. + */ + .macro generate_el1_vector +.Lvector_start\@: + kernel_ventry 1, t, 64, sync // Synchronous EL1t + kernel_ventry 1, t, 64, irq // IRQ EL1t + kernel_ventry 1, t, 64, fiq // FIQ EL1h + kernel_ventry 1, t, 64, error // Error EL1t + + kernel_ventry 1, h, 64, sync // Synchronous EL1h + kernel_ventry 1, h, 64, irq // IRQ EL1h + kernel_ventry 1, h, 64, fiq // FIQ EL1h + kernel_ventry 1, h, 64, error // Error EL1h + + .rept 4 + tramp_ventry .Lvector_start\@, 64, kpti=0 + .endr + .rept 4 + tramp_ventry .Lvector_start\@, 32, kpti=0 + .endr + .endm + + .pushsection ".entry.text", "ax" + .align 11 +SYM_CODE_START(__bp_harden_el1_vectors) + generate_el1_vector +SYM_CODE_END(__bp_harden_el1_vectors) + .popsection + + /* * Register switch for AArch64. The callee-saved registers need to be saved * and restored. On entry: -- cgit v1.2.3 From ba2689234be92024e5635d30fe744f4853ad97db Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 18 Nov 2021 13:59:46 +0000 Subject: arm64: entry: Add vectors that have the bhb mitigation sequences Some CPUs affected by Spectre-BHB need a sequence of branches, or a firmware call to be run before any indirect branch. This needs to go in the vectors. No CPU needs both. While this can be patched in, it would run on all CPUs as there is a single set of vectors. If only one part of a big/little combination is affected, the unaffected CPUs have to run the mitigation too. Create extra vectors that include the sequence. Subsequent patches will allow affected CPUs to select this set of vectors. Later patches will modify the loop count to match what the CPU requires. Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/include/asm/assembler.h | 24 +++++++++++++++++ arch/arm64/include/asm/vectors.h | 34 ++++++++++++++++++++++++ arch/arm64/kernel/entry.S | 53 +++++++++++++++++++++++++++++++------- arch/arm64/kernel/proton-pack.c | 16 ++++++++++++ include/linux/arm-smccc.h | 5 ++++ 5 files changed, 123 insertions(+), 9 deletions(-) create mode 100644 arch/arm64/include/asm/vectors.h (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index e8bd0af0141c..046c38ee2841 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -850,4 +850,28 @@ alternative_endif #endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */ + .macro __mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + mov \tmp, #32 +.Lspectre_bhb_loop\@: + b . + 4 + subs \tmp, \tmp, #1 + b.ne .Lspectre_bhb_loop\@ + sb +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + /* Save/restores x0-x3 to the stack */ + .macro __mitigate_spectre_bhb_fw +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + stp x0, x1, [sp, #-16]! + stp x2, x3, [sp, #-16]! + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_3 +alternative_cb smccc_patch_fw_mitigation_conduit + nop // Patched to SMC/HVC #0 +alternative_cb_end + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h new file mode 100644 index 000000000000..bac53fad037d --- /dev/null +++ b/arch/arm64/include/asm/vectors.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 ARM Ltd. + */ +#ifndef __ASM_VECTORS_H +#define __ASM_VECTORS_H + +/* + * Note: the order of this enum corresponds to two arrays in entry.S: + * tramp_vecs and __bp_harden_el1_vectors. By default the canonical + * 'full fat' vectors are used directly. + */ +enum arm64_bp_harden_el1_vectors { +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + /* + * Perform the BHB loop mitigation, before branching to the canonical + * vectors. + */ + EL1_VECTOR_BHB_LOOP, + + /* + * Make the SMC call for firmware mitigation, before branching to the + * canonical vectors. + */ + EL1_VECTOR_BHB_FW, +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + + /* + * Remap the kernel before branching to the canonical vectors. + */ + EL1_VECTOR_KPTI, ++}; + +#endif /* __ASM_VECTORS_H */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 9c4ff75f983e..2ceb0c3647b4 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -646,13 +646,26 @@ alternative_else_nop_endif sub \dst, \dst, PAGE_SIZE .endm - .macro tramp_ventry, vector_start, regsize, kpti + +#define BHB_MITIGATION_NONE 0 +#define BHB_MITIGATION_LOOP 1 +#define BHB_MITIGATION_FW 2 + + .macro tramp_ventry, vector_start, regsize, kpti, bhb .align 7 1: .if \regsize == 64 msr tpidrro_el0, x30 // Restored in kernel_ventry .endif + .if \bhb == BHB_MITIGATION_LOOP + /* + * This sequence must appear before the first indirect branch. i.e. the + * ret out of tramp_ventry. It appears here because x30 is free. + */ + __mitigate_spectre_bhb_loop x30 + .endif // \bhb == BHB_MITIGATION_LOOP + .if \kpti == 1 /* * Defend against branch aliasing attacks by pushing a dummy @@ -680,6 +693,15 @@ alternative_else_nop_endif ldr x30, =vectors .endif // \kpti == 1 + .if \bhb == BHB_MITIGATION_FW + /* + * The firmware sequence must appear before the first indirect branch. + * i.e. the ret out of tramp_ventry. But it also needs the stack to be + * mapped to save/restore the registers the SMC clobbers. + */ + __mitigate_spectre_bhb_fw + .endif // \bhb == BHB_MITIGATION_FW + add x30, x30, #(1b - \vector_start + 4) ret .org 1b + 128 // Did we overflow the ventry slot? @@ -687,6 +709,9 @@ alternative_else_nop_endif .macro tramp_exit, regsize = 64 adr x30, tramp_vectors +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + add x30, x30, SZ_4K +#endif msr vbar_el1, x30 ldr lr, [sp, #S_LR] tramp_unmap_kernel x29 @@ -698,26 +723,32 @@ alternative_else_nop_endif sb .endm - .macro generate_tramp_vector, kpti + .macro generate_tramp_vector, kpti, bhb .Lvector_start\@: .space 0x400 .rept 4 - tramp_ventry .Lvector_start\@, 64, \kpti + tramp_ventry .Lvector_start\@, 64, \kpti, \bhb .endr .rept 4 - tramp_ventry .Lvector_start\@, 32, \kpti + tramp_ventry .Lvector_start\@, 32, \kpti, \bhb .endr .endm #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 /* * Exception vectors trampoline. + * The order must match __bp_harden_el1_vectors and the + * arm64_bp_harden_el1_vectors enum. */ .pushsection ".entry.tramp.text", "ax" .align 11 SYM_CODE_START_NOALIGN(tramp_vectors) - generate_tramp_vector kpti=1 +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_LOOP + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_FW +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_NONE SYM_CODE_END(tramp_vectors) SYM_CODE_START(tramp_exit_native) @@ -744,7 +775,7 @@ SYM_DATA_END(__entry_tramp_data_start) * Exception vectors for spectre mitigations on entry from EL1 when * kpti is not in use. */ - .macro generate_el1_vector + .macro generate_el1_vector, bhb .Lvector_start\@: kernel_ventry 1, t, 64, sync // Synchronous EL1t kernel_ventry 1, t, 64, irq // IRQ EL1t @@ -757,17 +788,21 @@ SYM_DATA_END(__entry_tramp_data_start) kernel_ventry 1, h, 64, error // Error EL1h .rept 4 - tramp_ventry .Lvector_start\@, 64, kpti=0 + tramp_ventry .Lvector_start\@, 64, 0, \bhb .endr .rept 4 - tramp_ventry .Lvector_start\@, 32, kpti=0 + tramp_ventry .Lvector_start\@, 32, 0, \bhb .endr .endm +/* The order must match tramp_vecs and the arm64_bp_harden_el1_vectors enum. */ .pushsection ".entry.text", "ax" .align 11 SYM_CODE_START(__bp_harden_el1_vectors) - generate_el1_vector +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + generate_el1_vector bhb=BHB_MITIGATION_LOOP + generate_el1_vector bhb=BHB_MITIGATION_FW +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ SYM_CODE_END(__bp_harden_el1_vectors) .popsection diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 9394f21d7566..6a5eeb8beea3 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -770,3 +770,19 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) return -ENODEV; } } + +/* Patched to NOP when enabled */ +void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 1); +} + +/* Patched to NOP when enabled */ +void noinstr spectre_bhb_patch_fw_mitigation_enabled(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 1); +} diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 63ccb5252190..220c8c60e021 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -92,6 +92,11 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +#define ARM_SMCCC_ARCH_WORKAROUND_3 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x3fff) + #define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ -- cgit v1.2.3 From b28a8eebe81c186fdb1a0078263b30576c8e1f42 Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 25 Nov 2021 14:25:34 +0000 Subject: arm64: entry: Add macro for reading symbol addresses from the trampoline The trampoline code needs to use the address of symbols in the wider kernel, e.g. vectors. PC-relative addressing wouldn't work as the trampoline code doesn't run at the address the linker expected. tramp_ventry uses a literal pool, unless CONFIG_RANDOMIZE_BASE is set, in which case it uses the data page as a literal pool because the data page can be unmapped when running in user-space, which is required for CPUs vulnerable to meltdown. Pull this logic out as a macro, instead of adding a third copy of it. Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/kernel/entry.S | 37 ++++++++++++++++--------------------- 1 file changed, 16 insertions(+), 21 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2ceb0c3647b4..8da732fefd8f 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -646,6 +646,15 @@ alternative_else_nop_endif sub \dst, \dst, PAGE_SIZE .endm + .macro tramp_data_read_var dst, var +#ifdef CONFIG_RANDOMIZE_BASE + tramp_data_page \dst + add \dst, \dst, #:lo12:__entry_tramp_data_\var + ldr \dst, [\dst] +#else + ldr \dst, =\var +#endif + .endm #define BHB_MITIGATION_NONE 0 #define BHB_MITIGATION_LOOP 1 @@ -676,13 +685,8 @@ alternative_else_nop_endif b . 2: tramp_map_kernel x30 -#ifdef CONFIG_RANDOMIZE_BASE - tramp_data_page x30 alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 - ldr x30, [x30] -#else - ldr x30, =vectors -#endif + tramp_data_read_var x30, vectors alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM prfm plil1strm, [x30, #(1b - \vector_start)] alternative_else_nop_endif @@ -765,7 +769,12 @@ SYM_CODE_END(tramp_exit_compat) .pushsection ".rodata", "a" .align PAGE_SHIFT SYM_DATA_START(__entry_tramp_data_start) +__entry_tramp_data_vectors: .quad vectors +#ifdef CONFIG_ARM_SDE_INTERFACE +__entry_tramp_data___sdei_asm_handler: + .quad __sdei_asm_handler +#endif /* CONFIG_ARM_SDE_INTERFACE */ SYM_DATA_END(__entry_tramp_data_start) .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ @@ -932,14 +941,7 @@ SYM_CODE_START(__sdei_asm_entry_trampoline) * Remember whether to unmap the kernel on exit. */ 1: str x4, [x1, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)] - -#ifdef CONFIG_RANDOMIZE_BASE - tramp_data_page x4 - add x4, x4, #:lo12:__sdei_asm_trampoline_next_handler - ldr x4, [x4] -#else - ldr x4, =__sdei_asm_handler -#endif + tramp_data_read_var x4, __sdei_asm_handler br x4 SYM_CODE_END(__sdei_asm_entry_trampoline) NOKPROBE(__sdei_asm_entry_trampoline) @@ -962,13 +964,6 @@ SYM_CODE_END(__sdei_asm_exit_trampoline) NOKPROBE(__sdei_asm_exit_trampoline) .ltorg .popsection // .entry.tramp.text -#ifdef CONFIG_RANDOMIZE_BASE -.pushsection ".rodata", "a" -SYM_DATA_START(__sdei_asm_trampoline_next_handler) - .quad __sdei_asm_handler -SYM_DATA_END(__sdei_asm_trampoline_next_handler) -.popsection // .rodata -#endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ /* -- cgit v1.2.3 From bd09128d16fac3c34b80bd6a29088ac632e8ce09 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 23 Nov 2021 18:29:25 +0000 Subject: arm64: Add percpu vectors for EL1 The Spectre-BHB workaround adds a firmware call to the vectors. This is needed on some CPUs, but not others. To avoid the unaffected CPU in a big/little pair from making the firmware call, create per cpu vectors. The per-cpu vectors only apply when returning from EL0. Systems using KPTI can use the canonical 'full-fat' vectors directly at EL1, the trampoline exit code will switch to this_cpu_vector on exit to EL0. Systems not using KPTI should always use this_cpu_vector. this_cpu_vector will point at a vector in tramp_vecs or __bp_harden_el1_vectors, depending on whether KPTI is in use. Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/include/asm/vectors.h | 29 ++++++++++++++++++++++++++++- arch/arm64/kernel/cpufeature.c | 11 +++++++++++ arch/arm64/kernel/entry.S | 12 ++++++------ arch/arm64/kvm/hyp/vhe/switch.c | 10 ++++++++-- 4 files changed, 53 insertions(+), 9 deletions(-) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h index bac53fad037d..3f76dfd9e074 100644 --- a/arch/arm64/include/asm/vectors.h +++ b/arch/arm64/include/asm/vectors.h @@ -5,6 +5,15 @@ #ifndef __ASM_VECTORS_H #define __ASM_VECTORS_H +#include +#include + +#include + +extern char vectors[]; +extern char tramp_vectors[]; +extern char __bp_harden_el1_vectors[]; + /* * Note: the order of this enum corresponds to two arrays in entry.S: * tramp_vecs and __bp_harden_el1_vectors. By default the canonical @@ -29,6 +38,24 @@ enum arm64_bp_harden_el1_vectors { * Remap the kernel before branching to the canonical vectors. */ EL1_VECTOR_KPTI, -+}; +}; + +/* The vectors to use on return from EL0. e.g. to remap the kernel */ +DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector); + +#ifndef CONFIG_UNMAP_KERNEL_AT_EL0 +#define TRAMP_VALIAS 0 +#endif + +static inline const char * +arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot) +{ + if (arm64_kernel_unmapped_at_el0()) + return (char *)TRAMP_VALIAS + SZ_2K * slot; + + WARN_ON_ONCE(slot == EL1_VECTOR_KPTI); + + return __bp_harden_el1_vectors + SZ_2K * slot; +} #endif /* __ASM_VECTORS_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index e5f23dab1c8d..45fed4974c44 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -73,6 +73,8 @@ #include #include #include +#include + #include #include #include @@ -85,6 +87,7 @@ #include #include #include +#include #include /* Kernel representation of AT_HWCAP and AT_HWCAP2 */ @@ -110,6 +113,8 @@ DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE); bool arm64_use_ng_mappings = false; EXPORT_SYMBOL(arm64_use_ng_mappings); +DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors; + /* * Permit PER_LINUX32 and execve() of 32-bit binaries even if not all CPUs * support it? @@ -1590,6 +1595,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) int cpu = smp_processor_id(); + if (__this_cpu_read(this_cpu_vector) == vectors) { + const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI); + + __this_cpu_write(this_cpu_vector, v); + } + /* * We don't need to rewrite the page-tables if either we've done * it already or we have KASLR enabled and therefore have not diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 8da732fefd8f..a62fee121138 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -38,7 +38,6 @@ .macro kernel_ventry, el:req, ht:req, regsize:req, label:req .align 7 .Lventry_start\@: -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 .if \el == 0 /* * This must be the first instruction of the EL0 vector entries. It is @@ -53,7 +52,6 @@ .endif .Lskip_tramp_vectors_cleanup\@: .endif -#endif sub sp, sp, #PT_REGS_SIZE #ifdef CONFIG_VMAP_STACK @@ -712,10 +710,10 @@ alternative_else_nop_endif .endm .macro tramp_exit, regsize = 64 - adr x30, tramp_vectors -#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY - add x30, x30, SZ_4K -#endif + tramp_data_read_var x30, this_cpu_vector + get_this_cpu_offset x29 + ldr x30, [x30, x29] + msr vbar_el1, x30 ldr lr, [sp, #S_LR] tramp_unmap_kernel x29 @@ -775,6 +773,8 @@ __entry_tramp_data_vectors: __entry_tramp_data___sdei_asm_handler: .quad __sdei_asm_handler #endif /* CONFIG_ARM_SDE_INTERFACE */ +__entry_tramp_data_this_cpu_vector: + .quad this_cpu_vector SYM_DATA_END(__entry_tramp_data_start) .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 11d053fdd604..54af47005e45 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -24,6 +25,8 @@ #include #include #include +#include +#include /* VHE specific context */ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); @@ -67,7 +70,7 @@ NOKPROBE_SYMBOL(__activate_traps); static void __deactivate_traps(struct kvm_vcpu *vcpu) { - extern char vectors[]; /* kernel exception vectors */ + const char *host_vectors = vectors; ___deactivate_traps(vcpu); @@ -81,7 +84,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); - write_sysreg(vectors, vbar_el1); + + if (!arm64_kernel_unmapped_at_el0()) + host_vectors = __this_cpu_read(this_cpu_vector); + write_sysreg(host_vectors, vbar_el1); } NOKPROBE_SYMBOL(__deactivate_traps); -- cgit v1.2.3 From 228a26b912287934789023b4132ba76065d9491c Mon Sep 17 00:00:00 2001 From: James Morse Date: Fri, 10 Dec 2021 14:32:56 +0000 Subject: arm64: Use the clearbhb instruction in mitigations Future CPUs may implement a clearbhb instruction that is sufficient to mitigate SpectreBHB. CPUs that implement this instruction, but not CSV2.3 must be affected by Spectre-BHB. Add support to use this instruction as the BHB mitigation on CPUs that support it. The instruction is in the hint space, so it will be treated by a NOP as older CPUs. Reviewed-by: Russell King (Oracle) Reviewed-by: Catalin Marinas Signed-off-by: James Morse --- arch/arm64/include/asm/assembler.h | 17 +++++++++++++++++ arch/arm64/include/asm/cpufeature.h | 13 +++++++++++++ arch/arm64/include/asm/insn.h | 1 + arch/arm64/include/asm/sysreg.h | 1 + arch/arm64/include/asm/vectors.h | 7 +++++++ arch/arm64/kernel/cpufeature.c | 1 + arch/arm64/kernel/entry.S | 8 ++++++++ arch/arm64/kernel/image-vars.h | 1 + arch/arm64/kernel/proton-pack.c | 29 +++++++++++++++++++++++++++++ arch/arm64/kvm/hyp/hyp-entry.S | 1 + 10 files changed, 79 insertions(+) (limited to 'arch/arm64/kernel/entry.S') diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 5cc97130843f..6ebdc0f834a7 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -108,6 +108,13 @@ hint #20 .endm +/* + * Clear Branch History instruction + */ + .macro clearbhb + hint #22 + .endm + /* * Speculation barrier */ @@ -884,6 +891,16 @@ alternative_cb smccc_patch_fw_mitigation_conduit alternative_cb_end ldp x2, x3, [sp], #16 ldp x0, x1, [sp], #16 +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_clear_insn +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb spectre_bhb_patch_clearbhb + /* Patched to NOP when not supported */ + clearbhb + isb +alternative_cb_end #endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ .endm #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index b158fd447f3a..a77b5f49b3a6 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -653,6 +653,19 @@ static inline bool supports_csv2p3(int scope) return csv2_val == 3; } +static inline bool supports_clearbhb(int scope) +{ + u64 isar2; + + if (scope == SCOPE_LOCAL_CPU) + isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); + else + isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); + + return cpuid_feature_extract_unsigned_field(isar2, + ID_AA64ISAR2_CLEARBHB_SHIFT); +} + const struct cpumask *system_32bit_el0_cpumask(void); DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 6b776c8667b2..b02f0c328c8e 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -65,6 +65,7 @@ enum aarch64_insn_hint_cr_op { AARCH64_INSN_HINT_PSB = 0x11 << 5, AARCH64_INSN_HINT_TSB = 0x12 << 5, AARCH64_INSN_HINT_CSDB = 0x14 << 5, + AARCH64_INSN_HINT_CLEARBHB = 0x16 << 5, AARCH64_INSN_HINT_BTI = 0x20 << 5, AARCH64_INSN_HINT_BTIC = 0x22 << 5, diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 238b9f6a28fc..932d45b17877 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -773,6 +773,7 @@ #define ID_AA64ISAR1_GPI_IMP_DEF 0x1 /* id_aa64isar2 */ +#define ID_AA64ISAR2_CLEARBHB_SHIFT 28 #define ID_AA64ISAR2_RPRES_SHIFT 4 #define ID_AA64ISAR2_WFXT_SHIFT 0 diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h index 1f65c37dc653..f64613a96d53 100644 --- a/arch/arm64/include/asm/vectors.h +++ b/arch/arm64/include/asm/vectors.h @@ -32,6 +32,12 @@ enum arm64_bp_harden_el1_vectors { * canonical vectors. */ EL1_VECTOR_BHB_FW, + + /* + * Use the ClearBHB instruction, before branching to the canonical + * vectors. + */ + EL1_VECTOR_BHB_CLEAR_INSN, #endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ /* @@ -43,6 +49,7 @@ enum arm64_bp_harden_el1_vectors { #ifndef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY #define EL1_VECTOR_BHB_LOOP -1 #define EL1_VECTOR_BHB_FW -1 +#define EL1_VECTOR_BHB_CLEAR_INSN -1 #endif /* !CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ /* The vectors to use on return from EL0. e.g. to remap the kernel */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 45fed4974c44..d33687673f6b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -231,6 +231,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_CLEARBHB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_RPRES_SHIFT, 4, 0), ARM64_FTR_END, }; diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a62fee121138..4a3a653df07e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -657,6 +657,7 @@ alternative_else_nop_endif #define BHB_MITIGATION_NONE 0 #define BHB_MITIGATION_LOOP 1 #define BHB_MITIGATION_FW 2 +#define BHB_MITIGATION_INSN 3 .macro tramp_ventry, vector_start, regsize, kpti, bhb .align 7 @@ -673,6 +674,11 @@ alternative_else_nop_endif __mitigate_spectre_bhb_loop x30 .endif // \bhb == BHB_MITIGATION_LOOP + .if \bhb == BHB_MITIGATION_INSN + clearbhb + isb + .endif // \bhb == BHB_MITIGATION_INSN + .if \kpti == 1 /* * Defend against branch aliasing attacks by pushing a dummy @@ -749,6 +755,7 @@ SYM_CODE_START_NOALIGN(tramp_vectors) #ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_LOOP generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_FW + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_INSN #endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_NONE SYM_CODE_END(tramp_vectors) @@ -811,6 +818,7 @@ SYM_CODE_START(__bp_harden_el1_vectors) #ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY generate_el1_vector bhb=BHB_MITIGATION_LOOP generate_el1_vector bhb=BHB_MITIGATION_FW + generate_el1_vector bhb=BHB_MITIGATION_INSN #endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ SYM_CODE_END(__bp_harden_el1_vectors) .popsection diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 56db964a4f0c..55a1ced8eb77 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -69,6 +69,7 @@ KVM_NVHE_ALIAS(kvm_compute_final_ctr_el0); KVM_NVHE_ALIAS(spectre_bhb_patch_loop_iter); KVM_NVHE_ALIAS(spectre_bhb_patch_loop_mitigation_enable); KVM_NVHE_ALIAS(spectre_bhb_patch_wa3); +KVM_NVHE_ALIAS(spectre_bhb_patch_clearbhb); /* Global kernel state accessed by nVHE hyp code. */ KVM_NVHE_ALIAS(kvm_vgic_global_state); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index fbbcd1d2eb19..d3fbff00993d 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -805,6 +805,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) * - Mitigated by a branchy loop a CPU specific number of times, and listed * in our "loop mitigated list". * - Mitigated in software by the firmware Spectre v2 call. + * - Has the ClearBHB instruction to perform the mitigation. * - Has the 'Exception Clears Branch History Buffer' (ECBHB) feature, so no * software mitigation in the vectors is needed. * - Has CSV2.3, so is unaffected. @@ -820,6 +821,7 @@ enum bhb_mitigation_bits { BHB_LOOP, BHB_FW, BHB_HW, + BHB_INSN, }; static unsigned long system_bhb_mitigations; @@ -937,6 +939,9 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, if (supports_csv2p3(scope)) return false; + if (supports_clearbhb(scope)) + return true; + if (spectre_bhb_loop_affected(scope)) return true; @@ -984,6 +989,17 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { state = SPECTRE_MITIGATED; set_bit(BHB_HW, &system_bhb_mitigations); + } else if (supports_clearbhb(SCOPE_LOCAL_CPU)) { + /* + * Ensure KVM uses the indirect vector which will have ClearBHB + * added. + */ + if (!data->slot) + data->slot = HYP_VECTOR_INDIRECT; + + this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN); + state = SPECTRE_MITIGATED; + set_bit(BHB_INSN, &system_bhb_mitigations); } else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) { /* * Ensure KVM uses the indirect vector which will have the @@ -1096,3 +1112,16 @@ void noinstr spectre_bhb_patch_wa3(struct alt_instr *alt, *updptr++ = cpu_to_le32(insn); } + +/* Patched to NOP when not supported */ +void __init spectre_bhb_patch_clearbhb(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 2); + + if (test_bit(BHB_INSN, &system_bhb_mitigations)) + return; + + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); +} diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 12aa49324955..7839d075729b 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -213,6 +213,7 @@ SYM_CODE_END(__kvm_hyp_vector) .else stp x0, x1, [sp, #-16]! mitigate_spectre_bhb_loop x0 + mitigate_spectre_bhb_clear_insn .endif .if \indirect != 0 alternative_cb kvm_patch_vector_branch -- cgit v1.2.3