VM_HIGH_ARCH_5 is used for riscv

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- include/linux/mm.h | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b1068ddcbb7..1ef231cbc8fe 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -378,6 +378,13 @@ extern unsigned int kobjsize(const void *objp); # define VM_SHADOW_STACK VM_HIGH_ARCH_6 #endif

+#if defined(CONFIG_RISCV_USER_CFI) +/* + * Following x86 and picking up the same bitpos. + */ +# define VM_SHADOW_STACK VM_HIGH_ARCH_5 +#endif + #ifndef VM_SHADOW_STACK # define VM_SHADOW_STACK VM_NONE #endif

Make an entry for cfi extensions in extensions.yaml.

Signed-off-by: Deepak Gupta debug@rivosinc.com Acked-by: Rob Herring (Arm) robh@kernel.org --- Documentation/devicetree/bindings/riscv/extensions.yaml | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml index a63b994e0763..9b9024dbc8d2 100644 --- a/Documentation/devicetree/bindings/riscv/extensions.yaml +++ b/Documentation/devicetree/bindings/riscv/extensions.yaml @@ -426,6 +426,20 @@ properties: The standard Zicboz extension for cache-block zeroing as ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs.

+ - const: zicfilp + description: | + The standard Zicfilp extension for enforcing forward edge + control-flow integrity as ratified in commit 3f8e450 ("merge + pull request #227 from ved-rivos/0709") of riscv-cfi + github repo. + + - const: zicfiss + description: | + The standard Zicfiss extension for enforcing backward edge + control-flow integrity as ratified in commit 3f8e450 ("merge + pull request #227 from ved-rivos/0709") of riscv-cfi + github repo. + - const: zicntr description: The standard Zicntr extension for base counters and timers, as

Carves out space in arch specific thread struct for cfi status and shadow stack in usermode on riscv.

This patch does following - defines a new structure cfi_status with status bit for cfi feature - defines shadow stack pointer, base and size in cfi_status structure - defines offsets to new member fields in thread in asm-offsets.c - Saves and restore shadow stack pointer on trap entry (U --> S) and exit (S --> U)

Shadow stack save/restore is gated on feature availiblity and implemented using alternative. CSR can be context switched in `switch_to` as well but soon as kernel shadow stack support gets rolled in, shadow stack pointer will need to be switched at trap entry/exit point (much like `sp`). It can be argued that kernel using shadow stack deployment scenario may not be as prevalant as user mode using this feature. But even if there is some minimal deployment of kernel shadow stack, that means that it needs to be supported. And thus save/restore of shadow stack pointer in entry.S instead of in `switch_to.h`.

Reviewed-by: Charlie Jenkins charlie@rivosinc.com Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/processor.h | 1 + arch/riscv/include/asm/thread_info.h | 3 +++ arch/riscv/include/asm/usercfi.h | 24 ++++++++++++++++++++++++ arch/riscv/kernel/asm-offsets.c | 4 ++++ arch/riscv/kernel/entry.S | 26 ++++++++++++++++++++++++++ 5 files changed, 58 insertions(+)

diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index e3aba3336e63..d851bb5c6da0 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -14,6 +14,7 @@

#include <asm/ptrace.h> #include <asm/hwcap.h> +#include <asm/usercfi.h>

#define arch_get_mmap_end(addr, len, flags) \ ({ \ diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index f5916a70879a..a0cfe00c2ca6 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -62,6 +62,9 @@ struct thread_info { long user_sp; /* User stack pointer */ int cpu; unsigned long syscall_work; /* SYSCALL_WORK_ flags */ +#ifdef CONFIG_RISCV_USER_CFI + struct cfi_status user_cfi_state; +#endif #ifdef CONFIG_SHADOW_CALL_STACK void *scs_base; void *scs_sp; diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h new file mode 100644 index 000000000000..5f2027c51917 --- /dev/null +++ b/arch/riscv/include/asm/usercfi.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (C) 2024 Rivos, Inc. + * Deepak Gupta debug@rivosinc.com + */ +#ifndef _ASM_RISCV_USERCFI_H +#define _ASM_RISCV_USERCFI_H + +#ifndef __ASSEMBLY__ +#include <linux/types.h> + +#ifdef CONFIG_RISCV_USER_CFI +struct cfi_status { + unsigned long ubcfi_en : 1; /* Enable for backward cfi. */ + unsigned long rsvd : ((sizeof(unsigned long) * 8) - 1); + unsigned long user_shdw_stk; /* Current user shadow stack pointer */ + unsigned long shdw_stk_base; /* Base address of shadow stack */ + unsigned long shdw_stk_size; /* size of shadow stack */ +}; + +#endif /* CONFIG_RISCV_USER_CFI */ + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_RISCV_USERCFI_H */ diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index e89455a6a0e5..0c188aaf3925 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -50,6 +50,10 @@ void asm_offsets(void) #endif

OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu); +#ifdef CONFIG_RISCV_USER_CFI + OFFSET(TASK_TI_CFI_STATUS, task_struct, thread_info.user_cfi_state); + OFFSET(TASK_TI_USER_SSP, task_struct, thread_info.user_cfi_state.user_shdw_stk); +#endif OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]); OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]); OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 33a5a9f2a0d4..68c99124ea55 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -147,6 +147,20 @@ SYM_CODE_START(handle_exception)

REG_L s0, TASK_TI_USER_SP(tp) csrrc s1, CSR_STATUS, t0 + /* + * If previous mode was U, capture shadow stack pointer and save it away + * Zero CSR_SSP at the same time for sanitization. + */ + ALTERNATIVE("nop; nop; nop; nop", + __stringify( \ + andi s2, s1, SR_SPP; \ + bnez s2, skip_ssp_save; \ + csrrw s2, CSR_SSP, x0; \ + REG_S s2, TASK_TI_USER_SSP(tp); \ + skip_ssp_save:), + 0, + RISCV_ISA_EXT_ZICFISS, + CONFIG_RISCV_USER_CFI) csrr s2, CSR_EPC csrr s3, CSR_TVAL csrr s4, CSR_CAUSE @@ -236,6 +250,18 @@ SYM_CODE_START_NOALIGN(ret_from_exception) * structures again. */ csrw CSR_SCRATCH, tp + + /* + * Going back to U mode, restore shadow stack pointer + */ + ALTERNATIVE("nop; nop", + __stringify( \ + REG_L s3, TASK_TI_USER_SSP(tp); \ + csrw CSR_SSP, s3), + 0, + RISCV_ISA_EXT_ZICFISS, + CONFIG_RISCV_USER_CFI) + 1: #ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE move a0, sp

`arch_calc_vm_prot_bits` is implemented on risc-v to return VM_READ | VM_WRITE if PROT_WRITE is specified. Similarly `riscv_sys_mmap` is updated to convert all incoming PROT_WRITE to (PROT_WRITE | PROT_READ). This is to make sure that any existing apps using PROT_WRITE still work.

Earlier `protection_map[VM_WRITE]` used to pick read-write PTE encodings. Now `protection_map[VM_WRITE]` will always pick PAGE_SHADOWSTACK PTE encodings for shadow stack. Above changes ensure that existing apps continue to work because underneath kernel will be picking `protection_map[VM_WRITE|VM_READ]` PTE encodings.

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/mman.h | 25 +++++++++++++++++++++++++ arch/riscv/include/asm/pgtable.h | 1 + arch/riscv/kernel/sys_riscv.c | 10 ++++++++++ arch/riscv/mm/init.c | 2 +- 4 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/mman.h b/arch/riscv/include/asm/mman.h new file mode 100644 index 000000000000..392c9c2d2e78 --- /dev/null +++ b/arch/riscv/include/asm/mman.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include <linux/compiler.h> +#include <linux/types.h> +#include <uapi/asm/mman.h> + +static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, + unsigned long pkey __always_unused) +{ + unsigned long ret = 0; + + /* + * If PROT_WRITE was specified, force it to VM_READ | VM_WRITE. + * Only VM_WRITE means shadow stack. + */ + if (prot & PROT_WRITE) + ret = (VM_READ | VM_WRITE); + return ret; +} + +#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) + +#endif /* ! __ASM_MMAN_H__ */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 050fdc49b5ad..8c528cd7347a 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -178,6 +178,7 @@ extern struct pt_alloc_ops pt_ops __meminitdata; #define PAGE_READ_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) #define PAGE_WRITE_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | \ _PAGE_EXEC | _PAGE_WRITE) +#define PAGE_SHADOWSTACK __pgprot(_PAGE_BASE | _PAGE_WRITE)

#define PAGE_COPY PAGE_READ #define PAGE_COPY_EXEC PAGE_READ_EXEC diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index d77afe05578f..43a448bf254b 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -7,6 +7,7 @@

#include <linux/syscalls.h> #include <asm/cacheflush.h> +#include <asm-generic/mman-common.h>

static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -16,6 +17,15 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL;

+ /* + * If PROT_WRITE is specified then extend that to PROT_READ + * protection_map[VM_WRITE] is now going to select shadow stack encodings. + * So specifying PROT_WRITE actually should select protection_map [VM_WRITE | VM_READ] + * If user wants to create shadow stack then they should use `map_shadow_stack` syscall. + */ + if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ))) + prot |= PROT_READ; + return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 15b2eda4c364..9d6661638d0b 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -342,7 +342,7 @@ pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); static const pgprot_t protection_map[16] = { [VM_NONE] = PAGE_NONE, [VM_READ] = PAGE_READ, - [VM_WRITE] = PAGE_COPY, + [VM_WRITE] = PAGE_SHADOWSTACK, [VM_WRITE | VM_READ] = PAGE_COPY, [VM_EXEC] = PAGE_EXEC, [VM_EXEC | VM_READ] = PAGE_READ_EXEC,

This patch implements creating shadow stack pte (on riscv). Creating shadow stack PTE on riscv means that clearing RWX and then setting W=1.

Reviewed-by: Alexandre Ghiti alexghiti@rivosinc.com Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/pgtable.h | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 8c528cd7347a..ede43185ffdf 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -421,6 +421,11 @@ static inline pte_t pte_mkwrite_novma(pte_t pte) return __pte(pte_val(pte) | _PAGE_WRITE); }

+static inline pte_t pte_mkwrite_shstk(pte_t pte) +{ + return __pte((pte_val(pte) & ~(_PAGE_LEAF)) | _PAGE_WRITE); +} + /* static inline pte_t pte_mkexec(pte_t pte) */

static inline pte_t pte_mkdirty(pte_t pte) @@ -749,6 +754,11 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) return pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))); }

+static inline pmd_t pmd_mkwrite_shstk(pmd_t pte) +{ + return __pmd((pmd_val(pte) & ~(_PAGE_LEAF)) | _PAGE_WRITE); +} + static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pte_pmd(pte_wrprotect(pmd_pte(pmd)));

`fork` implements copy on write (COW) by making pages readonly in child and parent both.

ptep_set_wrprotect and pte_wrprotect clears _PAGE_WRITE in PTE. Assumption is that page is readable and on fault copy on write happens.

To implement COW on shadow stack pages, clearing up W bit makes them XWR = 000. This will result in wrong PTE setting which says no perms but V=1 and PFN field pointing to final page. Instead desired behavior is to turn it into a readable page, take an access (load/store) fault on sspush/sspop (shadow stack) and then perform COW on such pages. This way regular reads would still be allowed and not lead to COW maintaining current behavior of COW on non-shadow stack but writeable memory.

On the other hand it doesn't interfere with existing COW for read-write memory. Assumption is always that _PAGE_READ must have been set and thus setting _PAGE_READ is harmless.

Reviewed-by: Alexandre Ghiti alexghiti@rivosinc.com Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/pgtable.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index ccd2fa34afb8..54707686f042 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -411,7 +411,7 @@ static inline int pte_devmap(pte_t pte)

static inline pte_t pte_wrprotect(pte_t pte) { - return __pte(pte_val(pte) & ~(_PAGE_WRITE)); + return __pte((pte_val(pte) & ~(_PAGE_WRITE)) | (_PAGE_READ)); }

/* static inline pte_t pte_mkread(pte_t pte) */ @@ -612,7 +612,15 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { - atomic_long_and(~(unsigned long)_PAGE_WRITE, (atomic_long_t *)ptep); + pte_t read_pte = READ_ONCE(*ptep); + /* + * ptep_set_wrprotect can be called for shadow stack ranges too. + * shadow stack memory is XWR = 010 and thus clearing _PAGE_WRITE will lead to + * encoding 000b which is wrong encoding with V = 1. This should lead to page fault + * but we dont want this wrong configuration to be set in page tables. + */ + atomic_long_set((atomic_long_t *)ptep, + ((pte_val(read_pte) & ~(unsigned long)_PAGE_WRITE) | _PAGE_READ)); }

#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH

prctls implemented are: PR_SET_INDIR_BR_LP_STATUS, PR_GET_INDIR_BR_LP_STATUS and PR_LOCK_INDIR_BR_LP_STATUS

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/usercfi.h | 16 +++++++- arch/riscv/kernel/entry.S | 2 +- arch/riscv/kernel/process.c | 5 +++ arch/riscv/kernel/usercfi.c | 79 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 100 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index c4dcd256f19a..a8cec7c14d1d 100644 --- a/arch/riscv/include/asm/usercfi.h +++ b/arch/riscv/include/asm/usercfi.h @@ -16,7 +16,9 @@ struct kernel_clone_args; struct cfi_status { unsigned long ubcfi_en : 1; /* Enable for backward cfi. */ unsigned long ubcfi_locked : 1; - unsigned long rsvd : ((sizeof(unsigned long) * 8) - 2); + unsigned long ufcfi_en : 1; /* Enable for forward cfi. Note that ELP goes in sstatus */ + unsigned long ufcfi_locked : 1; + unsigned long rsvd : ((sizeof(unsigned long) * 8) - 4); unsigned long user_shdw_stk; /* Current user shadow stack pointer */ unsigned long shdw_stk_base; /* Base address of shadow stack */ unsigned long shdw_stk_size; /* size of shadow stack */ @@ -33,6 +35,10 @@ bool is_shstk_locked(struct task_struct *task); bool is_shstk_allocated(struct task_struct *task); void set_shstk_lock(struct task_struct *task); void set_shstk_status(struct task_struct *task, bool enable); +bool is_indir_lp_enabled(struct task_struct *task); +bool is_indir_lp_locked(struct task_struct *task); +void set_indir_lp_status(struct task_struct *task, bool enable); +void set_indir_lp_lock(struct task_struct *task);

#define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK (PR_SHADOW_STACK_ENABLE)

@@ -58,6 +64,14 @@ void set_shstk_status(struct task_struct *task, bool enable);

#define set_shstk_status(task, enable)

+#define is_indir_lp_enabled(task) false + +#define is_indir_lp_locked(task) false + +#define set_indir_lp_status(task, enable) + +#define set_indir_lp_lock(task) + #endif /* CONFIG_RISCV_USER_CFI */

#endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 68c99124ea55..00494b54ff4a 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -143,7 +143,7 @@ SYM_CODE_START(handle_exception) * Disable the FPU/Vector to detect illegal usage of floating point * or vector in kernel space. */ - li t0, SR_SUM | SR_FS_VS + li t0, SR_SUM | SR_FS_VS | SR_ELP

REG_L s0, TASK_TI_USER_SP(tp) csrrc s1, CSR_STATUS, t0 diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index cd11667593fe..4587201dd81d 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -160,6 +160,11 @@ void start_thread(struct pt_regs *regs, unsigned long pc, set_shstk_status(current, false); set_shstk_base(current, 0, 0); set_active_shstk(current, 0); + /* + * disable indirect branch tracking on exec. + * libc will enable it later via prctl. + */ + set_indir_lp_status(current, false);

#ifdef CONFIG_64BIT regs->status &= ~SR_UXL; diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index b93b324eed26..7937bcef9271 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -72,6 +72,35 @@ void set_shstk_lock(struct task_struct *task) task->thread_info.user_cfi_state.ubcfi_locked = 1; }

+bool is_indir_lp_enabled(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.ufcfi_en ? true : false; +} + +bool is_indir_lp_locked(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.ufcfi_locked ? true : false; +} + +void set_indir_lp_status(struct task_struct *task, bool enable) +{ + if (!cpu_supports_indirect_br_lp_instr()) + return; + + task->thread_info.user_cfi_state.ufcfi_en = enable ? 1 : 0; + + if (enable) + task->thread.envcfg |= ENVCFG_LPE; + else + task->thread.envcfg &= ~ENVCFG_LPE; + + csr_write(CSR_ENVCFG, task->thread.envcfg); +} + +void set_indir_lp_lock(struct task_struct *task) +{ + task->thread_info.user_cfi_state.ufcfi_locked = 1; +} /* * If size is 0, then to be compatible with regular stack we want it to be as big as * regular stack. Else PAGE_ALIGN it and return back @@ -372,3 +401,53 @@ int arch_lock_shadow_stack_status(struct task_struct *task,

return 0; } + +int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status) +{ + unsigned long fcfi_status = 0; + + if (!cpu_supports_indirect_br_lp_instr()) + return -EINVAL; + + /* indirect branch tracking is enabled on the task or not */ + fcfi_status |= (is_indir_lp_enabled(t) ? PR_INDIR_BR_LP_ENABLE : 0); + + return copy_to_user(status, &fcfi_status, sizeof(fcfi_status)) ? -EFAULT : 0; +} + +int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status) +{ + bool enable_indir_lp = false; + + if (!cpu_supports_indirect_br_lp_instr()) + return -EINVAL; + + /* indirect branch tracking is locked and further can't be modified by user */ + if (is_indir_lp_locked(t)) + return -EINVAL; + + /* Reject unknown flags */ + if (status & ~PR_INDIR_BR_LP_ENABLE) + return -EINVAL; + + enable_indir_lp = (status & PR_INDIR_BR_LP_ENABLE) ? true : false; + set_indir_lp_status(t, enable_indir_lp); + + return 0; +} + +int arch_lock_indir_br_lp_status(struct task_struct *task, + unsigned long arg) +{ + /* + * If indirect branch tracking is not supported or not enabled on task, + * nothing to lock here + */ + if (!cpu_supports_indirect_br_lp_instr() || + !is_indir_lp_enabled(task) || arg != 0) + return -EINVAL; + + set_indir_lp_lock(task); + + return 0; +}

zicfiss / zicfilp introduces a new exception to priv isa `software check exception` with cause code = 18. This patch implements software check exception.

Additionally it implements a cfi violation handler which checks for code in xtval. If xtval=2, it means that sw check exception happened because of an indirect branch not landing on 4 byte aligned PC or not landing on `lpad` instruction or label value embedded in `lpad` not matching label value setup in `x7`. If xtval=3, it means that sw check exception happened because of mismatch between link register (x1 or x5) and top of shadow stack (on execution of `sspopchk`).

In case of cfi violation, SIGSEGV is raised with code=SEGV_CPERR. SEGV_CPERR was introduced by x86 shadow stack patches.

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/include/asm/entry-common.h | 2 ++ arch/riscv/kernel/entry.S | 3 +++ arch/riscv/kernel/traps.c | 43 +++++++++++++++++++++++++++++++++ 4 files changed, 49 insertions(+)

diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index cd627ec289f1..5a27cefd7805 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -51,6 +51,7 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_u); DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); +DECLARE_DO_ERROR_INFO(do_trap_software_check);

asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h index b28ccc6cdeea..34ed149af5d1 100644 --- a/arch/riscv/include/asm/entry-common.h +++ b/arch/riscv/include/asm/entry-common.h @@ -40,4 +40,6 @@ static inline int handle_misaligned_store(struct pt_regs *regs) } #endif

+bool handle_user_cfi_violation(struct pt_regs *regs); + #endif /* _ASM_RISCV_ENTRY_COMMON_H */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 00494b54ff4a..9c00cac3f6f2 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -472,6 +472,9 @@ SYM_DATA_START_LOCAL(excp_vect_table) RISCV_PTR do_page_fault /* load page fault */ RISCV_PTR do_trap_unknown RISCV_PTR do_page_fault /* store page fault */ + RISCV_PTR do_trap_unknown /* cause=16 */ + RISCV_PTR do_trap_unknown /* cause=17 */ + RISCV_PTR do_trap_software_check /* cause=18 is sw check exception */ SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end)

#ifndef CONFIG_MMU diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 8ff8e8b36524..3f7709f4595a 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -354,6 +354,49 @@ void do_trap_ecall_u(struct pt_regs *regs)

}

+#define CFI_TVAL_FCFI_CODE 2 +#define CFI_TVAL_BCFI_CODE 3 +/* handle cfi violations */ +bool handle_user_cfi_violation(struct pt_regs *regs) +{ + bool ret = false; + unsigned long tval = csr_read(CSR_TVAL); + + if ((tval == CFI_TVAL_FCFI_CODE && cpu_supports_indirect_br_lp_instr()) || + (tval == CFI_TVAL_BCFI_CODE && cpu_supports_shadow_stack())) { + do_trap_error(regs, SIGSEGV, SEGV_CPERR, regs->epc, + "Oops - control flow violation"); + ret = true; + } + + return ret; +} + +/* + * software check exception is defined with risc-v cfi spec. Software check + * exception is raised when:- + * a) An indirect branch doesn't land on 4 byte aligned PC or `lpad` + * instruction or `label` value programmed in `lpad` instr doesn't + * match with value setup in `x7`. reported code in `xtval` is 2. + * b) `sspopchk` instruction finds a mismatch between top of shadow stack (ssp) + * and x1/x5. reported code in `xtval` is 3. + */ +asmlinkage __visible __trap_section void do_trap_software_check(struct pt_regs *regs) +{ + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + /* not a cfi violation, then merge into flow of unknown trap handler */ + if (!handle_user_cfi_violation(regs)) + do_trap_unknown(regs); + + irqentry_exit_to_user_mode(regs); + } else { + /* sw check exception coming from kernel is a bug in kernel */ + die(regs, "Kernel BUG"); + } +} + #ifdef CONFIG_MMU asmlinkage __visible noinstr void do_page_fault(struct pt_regs *regs) {

Save shadow stack pointer in sigcontext structure while delivering signal. Restore shadow stack pointer from sigcontext on sigreturn.

As part of save operation, kernel uses `ssamoswap` to save snapshot of current shadow stack on shadow stack itself (can be called as a save token). During restore on sigreturn, kernel retrieves token from top of shadow stack and validates it. This allows that user mode can't arbitrary pivot to any shadow stack address without having a token and thus provide strong security assurance between signaly delivery and sigreturn window.

Use ABI compatible way of saving/restoring shadow stack pointer into signal stack. This follows what Vector extension, where extra registers are placed in a form of extension header + extension body in the stack. The extension header indicates the size of the extra architectural states plus the size of header itself, and a magic identifier of the extension. Then, the extensions body contains the new architectural states in the form defined by uapi.

Signed-off-by: Andy Chiu andy.chiu@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/usercfi.h | 10 ++++ arch/riscv/include/uapi/asm/ptrace.h | 4 ++ arch/riscv/include/uapi/asm/sigcontext.h | 1 + arch/riscv/kernel/signal.c | 80 ++++++++++++++++++++++++++++++++ arch/riscv/kernel/usercfi.c | 56 ++++++++++++++++++++++ 5 files changed, 151 insertions(+)

diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index a8cec7c14d1d..361f59edbdef 100644 --- a/arch/riscv/include/asm/usercfi.h +++ b/arch/riscv/include/asm/usercfi.h @@ -8,6 +8,7 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/prctl.h> +#include <linux/errno.h>

struct task_struct; struct kernel_clone_args; @@ -35,6 +36,9 @@ bool is_shstk_locked(struct task_struct *task); bool is_shstk_allocated(struct task_struct *task); void set_shstk_lock(struct task_struct *task); void set_shstk_status(struct task_struct *task, bool enable); +unsigned long get_active_shstk(struct task_struct *task); +int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr); +int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr); bool is_indir_lp_enabled(struct task_struct *task); bool is_indir_lp_locked(struct task_struct *task); void set_indir_lp_status(struct task_struct *task, bool enable); @@ -72,6 +76,12 @@ void set_indir_lp_lock(struct task_struct *task);

#define set_indir_lp_lock(task)

+#define restore_user_shstk(tsk, shstk_ptr) -EINVAL + +#define save_user_shstk(tsk, saved_shstk_ptr) -EINVAL + +#define get_active_shstk(task) 0UL + #endif /* CONFIG_RISCV_USER_CFI */

#endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index a38268b19c3d..659ea3af5680 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -127,6 +127,10 @@ struct __riscv_v_regset_state { */ #define RISCV_MAX_VLENB (8192)

+struct __sc_riscv_cfi_state { + unsigned long ss_ptr; /* shadow stack pointer */ +}; + #endif /* __ASSEMBLY__ */

#endif /* _UAPI_ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h index cd4f175dc837..f37e4beffe03 100644 --- a/arch/riscv/include/uapi/asm/sigcontext.h +++ b/arch/riscv/include/uapi/asm/sigcontext.h @@ -10,6 +10,7 @@

/* The Magic number for signal context frame header. */ #define RISCV_V_MAGIC 0x53465457 +#define RISCV_ZICFISS_MAGIC 0x9487 #define END_MAGIC 0x0

/* The size of END signal context header. */ diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 80c70dccf09f..a7472a6fcdca 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -22,11 +22,13 @@ #include <asm/vector.h> #include <asm/csr.h> #include <asm/cacheflush.h> +#include <asm/usercfi.h>

unsigned long signal_minsigstksz __ro_after_init;

extern u32 __user_rt_sigreturn[2]; static size_t riscv_v_sc_size __ro_after_init; +static size_t riscv_zicfiss_sc_size __ro_after_init;

#define DEBUG_SIG 0

@@ -140,6 +142,62 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); }

+static long save_cfiss_state(struct pt_regs *regs, void __user *sc_cfi) +{ + struct __sc_riscv_cfi_state __user *state = sc_cfi; + unsigned long ss_ptr = 0; + long err = 0; + + if (!IS_ENABLED(CONFIG_RISCV_USER_CFI) || !is_shstk_enabled(current)) + return 0; + + /* + * Save a pointer to shadow stack itself on shadow stack as a form of token. + * A token on shadow gives following properties + * - Safe save and restore for shadow stack switching. Any save of shadow stack + * must have had saved a token on shadow stack. Similarly any restore of shadow + * stack must check the token before restore. Since writing to shadow stack with + * address of shadow stack itself is not easily allowed. A restore without a save + * is quite difficult for an attacker to perform. + * - A natural break. A token in shadow stack provides a natural break in shadow stack + * So a single linear range can be bucketed into different shadow stack segments. Any + * sspopchk will detect the condition and fault to kernel as sw check exception. + */ + err |= save_user_shstk(current, &ss_ptr); + err |= __put_user(ss_ptr, &state->ss_ptr); + if (unlikely(err)) + return -EFAULT; + + return riscv_zicfiss_sc_size; +} + +static long __restore_cfiss_state(struct pt_regs *regs, void __user *sc_cfi) +{ + struct __sc_riscv_cfi_state __user *state = sc_cfi; + unsigned long ss_ptr = 0; + long err; + + /* + * Restore shadow stack as a form of token stored on shadow stack itself as a safe + * way to restore. + * A token on shadow gives following properties + * - Safe save and restore for shadow stack switching. Any save of shadow stack + * must have had saved a token on shadow stack. Similarly any restore of shadow + * stack must check the token before restore. Since writing to shadow stack with + * address of shadow stack itself is not easily allowed. A restore without a save + * is quite difficult for an attacker to perform. + * - A natural break. A token in shadow stack provides a natural break in shadow stack + * So a single linear range can be bucketed into different shadow stack segments. + * sspopchk will detect the condition and fault to kernel as sw check exception. + */ + err = __copy_from_user(&ss_ptr, &state->ss_ptr, sizeof(unsigned long)); + + if (unlikely(err)) + return err; + + return restore_user_shstk(current, ss_ptr); +} + struct arch_ext_priv { __u32 magic; long (*save)(struct pt_regs *regs, void __user *sc_vec); @@ -150,6 +208,10 @@ struct arch_ext_priv arch_ext_list[] = { .magic = RISCV_V_MAGIC, .save = &save_v_state, }, + { + .magic = RISCV_ZICFISS_MAGIC, + .save = &save_cfiss_state, + }, };

const size_t nr_arch_exts = ARRAY_SIZE(arch_ext_list); @@ -202,6 +264,12 @@ static long restore_sigcontext(struct pt_regs *regs,

err = __restore_v_state(regs, sc_ext_ptr); break; + case RISCV_ZICFISS_MAGIC: + if (!is_shstk_enabled(current) || size != riscv_zicfiss_sc_size) + return -EINVAL; + + err = __restore_cfiss_state(regs, sc_ext_ptr); + break; default: return -EINVAL; } @@ -222,6 +290,10 @@ static size_t get_rt_frame_size(bool cal_all) if (cal_all || riscv_v_vstate_query(task_pt_regs(current))) total_context_size += riscv_v_sc_size; } + + if (is_shstk_enabled(current)) + total_context_size += riscv_zicfiss_sc_size; + /* * Preserved a __riscv_ctx_hdr for END signal context header if an * extension uses __riscv_extra_ext_header @@ -365,6 +437,11 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, #ifdef CONFIG_MMU regs->ra = (unsigned long)VDSO_SYMBOL( current->mm->context.vdso, rt_sigreturn); + + /* if bcfi is enabled x1 (ra) and x5 (t0) must match. not sure if we need this? */ + if (is_shstk_enabled(current)) + regs->t0 = regs->ra; + #else /* * For the nommu case we don't have a VDSO. Instead we push two @@ -493,6 +570,9 @@ void __init init_rt_signal_env(void) { riscv_v_sc_size = sizeof(struct __riscv_ctx_hdr) + sizeof(struct __sc_riscv_v_state) + riscv_v_vsize; + + riscv_zicfiss_sc_size = sizeof(struct __riscv_ctx_hdr) + + sizeof(struct __sc_riscv_cfi_state); /* * Determine the stack space required for guaranteed signal delivery. * The signal_minsigstksz will be populated into the AT_MINSIGSTKSZ entry diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index 7937bcef9271..d31d89618763 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -52,6 +52,11 @@ void set_active_shstk(struct task_struct *task, unsigned long shstk_addr) task->thread_info.user_cfi_state.user_shdw_stk = shstk_addr; }

+unsigned long get_active_shstk(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.user_shdw_stk; +} + void set_shstk_status(struct task_struct *task, bool enable) { if (!cpu_supports_shadow_stack()) @@ -170,6 +175,57 @@ static int create_rstor_token(unsigned long ssp, unsigned long *token_addr) return 0; }

+/* + * Save user shadow stack pointer on shadow stack itself and return pointer to saved location + * returns -EFAULT if operation was unsuccessful + */ +int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr) +{ + unsigned long ss_ptr = 0; + unsigned long token_loc = 0; + int ret = 0; + + if (saved_shstk_ptr == NULL) + return -EINVAL; + + ss_ptr = get_active_shstk(tsk); + ret = create_rstor_token(ss_ptr, &token_loc); + + if (!ret) { + *saved_shstk_ptr = token_loc; + set_active_shstk(tsk, token_loc); + } + + return ret; +} + +/* + * Restores user shadow stack pointer from token on shadow stack for task `tsk` + * returns -EFAULT if operation was unsuccessful + */ +int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr) +{ + unsigned long token = 0; + + token = amo_user_shstk((unsigned long __user *)shstk_ptr, 0); + + if (token == -1) + return -EFAULT; + + /* invalid token, return EINVAL */ + if ((token - shstk_ptr) != SHSTK_ENTRY_SIZE) { + pr_info_ratelimited( + "%s[%d]: bad restore token in %s: pc=%p sp=%p, token=%p, shstk_ptr=%p\n", + tsk->comm, task_pid_nr(tsk), __func__, (void *)(task_pt_regs(tsk)->epc), + (void *)(task_pt_regs(tsk)->sp), (void *)token, (void *)shstk_ptr); + return -EINVAL; + } + + /* all checks passed, set active shstk and return success */ + set_active_shstk(tsk, token); + return 0; +} + static unsigned long allocate_shadow_stack(unsigned long addr, unsigned long size, unsigned long token_offset, bool set_tok) {

Expose a new register type NT_RISCV_USER_CFI for risc-v cfi status and state. Intentionally both landing pad and shadow stack status and state are rolled into cfi state. Creating two different NT_RISCV_USER_XXX would not be useful and wastage of a note type. Enabling or disabling of feature is not allowed via ptrace set interface. However setting `elp` state or setting shadow stack pointer are allowed via ptrace set interface. It is expected `gdb` might have use to fixup `elp` state or `shadow stack` pointer.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/uapi/asm/ptrace.h | 18 ++++++++ arch/riscv/kernel/ptrace.c | 83 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 3 files changed, 102 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index 659ea3af5680..e6571fba8a8a 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -131,6 +131,24 @@ struct __sc_riscv_cfi_state { unsigned long ss_ptr; /* shadow stack pointer */ };

+struct __cfi_status { + /* indirect branch tracking state */ + __u64 lp_en : 1; + __u64 lp_lock : 1; + __u64 elp_state : 1; + + /* shadow stack status */ + __u64 shstk_en : 1; + __u64 shstk_lock : 1; + + __u64 rsvd : sizeof(__u64) - 5; +}; + +struct user_cfi_state { + struct __cfi_status cfi_status; + __u64 shstk_ptr; +}; + #endif /* __ASSEMBLY__ */

#endif /* _UAPI_ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index ea67e9fb7a58..df8b7c6ab671 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -19,6 +19,7 @@ #include <linux/regset.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> +#include <asm/usercfi.h>

enum riscv_regset { REGSET_X, @@ -31,6 +32,9 @@ enum riscv_regset { #ifdef CONFIG_RISCV_ISA_SUPM REGSET_TAGGED_ADDR_CTRL, #endif +#ifdef CONFIG_RISCV_USER_CFI + REGSET_CFI, +#endif };

static int riscv_gpr_get(struct task_struct *target, @@ -184,6 +188,75 @@ static int tagged_addr_ctrl_set(struct task_struct *target, } #endif

+#ifdef CONFIG_RISCV_USER_CFI +static int riscv_cfi_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_cfi_state user_cfi; + struct pt_regs *regs; + + regs = task_pt_regs(target); + + user_cfi.cfi_status.lp_en = is_indir_lp_enabled(target); + user_cfi.cfi_status.lp_lock = is_indir_lp_locked(target); + user_cfi.cfi_status.elp_state = (regs->status & SR_ELP); + + user_cfi.cfi_status.shstk_en = is_shstk_enabled(target); + user_cfi.cfi_status.shstk_lock = is_shstk_locked(target); + user_cfi.shstk_ptr = get_active_shstk(target); + + return membuf_write(&to, &user_cfi, sizeof(user_cfi)); +} + +/* + * Does it make sense to allowing enable / disable of cfi via ptrace? + * Not allowing enable / disable / locking control via ptrace for now. + * Setting shadow stack pointer is allowed. GDB might use it to unwind or + * some other fixup. Similarly gdb might want to suppress elp and may want + * to reset elp state. + */ +static int riscv_cfi_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct user_cfi_state user_cfi; + struct pt_regs *regs; + + regs = task_pt_regs(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_cfi, 0, -1); + if (ret) + return ret; + + /* + * Not allowing enabling or locking shadow stack or landing pad + * There is no disabling of shadow stack or landing pad via ptrace + * rsvd field should be set to zero so that if those fields are needed in future + */ + if (user_cfi.cfi_status.lp_en || user_cfi.cfi_status.lp_lock || + user_cfi.cfi_status.shstk_en || user_cfi.cfi_status.shstk_lock || + !user_cfi.cfi_status.rsvd) + return -EINVAL; + + /* If lpad is enabled on target and ptrace requests to set / clear elp, do that */ + if (is_indir_lp_enabled(target)) { + if (user_cfi.cfi_status.elp_state) /* set elp state */ + regs->status |= SR_ELP; + else + regs->status &= ~SR_ELP; /* clear elp state */ + } + + /* If shadow stack enabled on target, set new shadow stack pointer */ + if (is_shstk_enabled(target)) + set_active_shstk(target, user_cfi.shstk_ptr); + + return 0; +} +#endif + static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, @@ -224,6 +297,16 @@ static const struct user_regset riscv_user_regset[] = { .set = tagged_addr_ctrl_set, }, #endif +#ifdef CONFIG_RISCV_USER_CFI + [REGSET_CFI] = { + .core_note_type = NT_RISCV_USER_CFI, + .align = sizeof(__u64), + .n = sizeof(struct user_cfi_state) / sizeof(__u64), + .size = sizeof(__u64), + .regset_get = riscv_cfi_get, + .set = riscv_cfi_set, + }, +#endif };

static const struct user_regset_view riscv_user_native_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b44069d29cec..b9daed4ab780 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -452,6 +452,7 @@ typedef struct elf64_shdr { #define NT_RISCV_CSR 0x900 /* RISC-V Control and Status Registers */ #define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ #define NT_RISCV_TAGGED_ADDR_CTRL 0x902 /* RISC-V tagged address control (prctl()) */ +#define NT_RISCV_USER_CFI 0x903 /* RISC-V shadow stack state */ #define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ #define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ #define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */

Adding enumeration of zicfilp and zicfiss extensions in hwprobe syscall.

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/uapi/asm/hwprobe.h | 2 ++ arch/riscv/kernel/sys_hwprobe.c | 2 ++ 2 files changed, 4 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index c3c1cc951cb9..c1b537b50158 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -73,6 +73,8 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_EXT_ZCMOP (1ULL << 47) #define RISCV_HWPROBE_EXT_ZAWRS (1ULL << 48) #define RISCV_HWPROBE_EXT_SUPM (1ULL << 49) +#define RISCV_HWPROBE_EXT_ZICFILP (1ULL << 50) +#define RISCV_HWPROBE_EXT_ZICFISS (1ULL << 51) #define RISCV_HWPROBE_KEY_CPUPERF_0 5 #define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0) #define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0) diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index bcd3b816306c..d802ff707913 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -108,6 +108,8 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, EXT_KEY(ZCB); EXT_KEY(ZCMOP); EXT_KEY(ZICBOZ); + EXT_KEY(ZICFILP); + EXT_KEY(ZICFISS); EXT_KEY(ZICOND); EXT_KEY(ZIHINTNTL); EXT_KEY(ZIHINTPAUSE);

Kernel will have to perform shadow stack operations on user shadow stack. Like during signal delivery and sigreturn, shadow stack token must be created and validated respectively. Thus shadow stack access for kernel must be enabled.

In future when kernel shadow stacks are enabled for linux kernel, it must be enabled as early as possible for better coverage and prevent imbalance between regular stack and shadow stack. After `relocate_enable_mmu` has been done, this is as early as possible it can enabled.

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/kernel/asm-offsets.c | 4 ++++ arch/riscv/kernel/head.S | 12 ++++++++++++ 2 files changed, 16 insertions(+)

diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 0c188aaf3925..21f99d5757b6 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -515,4 +515,8 @@ void asm_offsets(void) DEFINE(FREGS_A6, offsetof(struct __arch_ftrace_regs, a6)); DEFINE(FREGS_A7, offsetof(struct __arch_ftrace_regs, a7)); #endif + DEFINE(SBI_EXT_FWFT, SBI_EXT_FWFT); + DEFINE(SBI_EXT_FWFT_SET, SBI_EXT_FWFT_SET); + DEFINE(SBI_FWFT_SHADOW_STACK, SBI_FWFT_SHADOW_STACK); + DEFINE(SBI_FWFT_SET_FLAG_LOCK, SBI_FWFT_SET_FLAG_LOCK); } diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 356d5397b2a2..6244408ca917 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -164,6 +164,12 @@ secondary_start_sbi: call relocate_enable_mmu #endif call .Lsetup_trap_vector + li a7, SBI_EXT_FWFT + li a6, SBI_EXT_FWFT_SET + li a0, SBI_FWFT_SHADOW_STACK + li a1, 1 /* enable supervisor to access shadow stack access */ + li a2, SBI_FWFT_SET_FLAG_LOCK + ecall scs_load_current call smp_callin #endif /* CONFIG_SMP */ @@ -320,6 +326,12 @@ SYM_CODE_START(_start_kernel) la tp, init_task la sp, init_thread_union + THREAD_SIZE addi sp, sp, -PT_SIZE_ON_STACK + li a7, SBI_EXT_FWFT + li a6, SBI_EXT_FWFT_SET + li a0, SBI_FWFT_SHADOW_STACK + li a1, 1 /* enable supervisor to access shadow stack access */ + li a2, SBI_FWFT_SET_FLAG_LOCK + ecall scs_load_current

#ifdef CONFIG_KASAN

This commit adds a kernel command line option using which user cfi can be disabled.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/kernel/usercfi.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+)

diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index d31d89618763..813162ce4f15 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -17,6 +17,8 @@ #include <asm/csr.h> #include <asm/usercfi.h>

+bool disable_riscv_usercfi; + #define SHSTK_ENTRY_SIZE sizeof(void *)

bool is_shstk_enabled(struct task_struct *task) @@ -396,6 +398,9 @@ int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) unsigned long size = 0, addr = 0; bool enable_shstk = false;

+ if (disable_riscv_usercfi) + return 0; + if (!cpu_supports_shadow_stack()) return -EINVAL;

@@ -475,6 +480,9 @@ int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status) { bool enable_indir_lp = false;

+ if (disable_riscv_usercfi) + return 0; + if (!cpu_supports_indirect_br_lp_instr()) return -EINVAL;

@@ -507,3 +515,16 @@ int arch_lock_indir_br_lp_status(struct task_struct *task,

return 0; } + +static int __init setup_global_riscv_enable(char *str) +{ + if (strcmp(str, "true") == 0) + disable_riscv_usercfi = true; + + pr_info("Setting riscv usercfi to be %s\n", + (disable_riscv_usercfi ? "disabled" : "enabled")); + + return 1; +} + +__setup("disable_riscv_usercfi=", setup_global_riscv_enable);

From: Jim Shu jim.shu@sifive.com

user mode tasks compiled with zicfilp may call indirectly into vdso (like hwprobe indirect calls). Add landing pad compile support in vdso. vdso with landing pad in it will be nop for tasks which have not enabled landing pad. This patch allows to run user mode tasks with cfi eanbled and do no harm.

Future work can be done on this to do below - labeled landing pad on vdso functions (whenever labeling support shows up in gnu-toolchain) - emit shadow stack instructions only in vdso compiled objects as part of kernel compile.

Signed-off-by: Jim Shu jim.shu@sifive.com Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/Makefile | 5 +++- arch/riscv/include/asm/assembler.h | 44 +++++++++++++++++++++++++++++++++++ arch/riscv/kernel/vdso/Makefile | 12 ++++++++++ arch/riscv/kernel/vdso/flush_icache.S | 4 ++++ arch/riscv/kernel/vdso/getcpu.S | 4 ++++ arch/riscv/kernel/vdso/rt_sigreturn.S | 4 ++++ arch/riscv/kernel/vdso/sys_hwprobe.S | 4 ++++ 7 files changed, 76 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 13fbc0f94238..eca94246cda6 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -88,9 +88,12 @@ riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZACAS) := $(riscv-march-y)_zacas # Check if the toolchain supports Zabha riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZABHA) := $(riscv-march-y)_zabha

+KBUILD_BASE_ISA = -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/') +export KBUILD_BASE_ISA + # Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by # matching non-v and non-multi-letter extensions out with the filter ([^v_]*) -KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/') +KBUILD_CFLAGS += $(KBUILD_BASE_ISA)

KBUILD_AFLAGS += -march=$(riscv-march-y)

diff --git a/arch/riscv/include/asm/assembler.h b/arch/riscv/include/asm/assembler.h index 44b1457d3e95..a058ea5e9c58 100644 --- a/arch/riscv/include/asm/assembler.h +++ b/arch/riscv/include/asm/assembler.h @@ -80,3 +80,47 @@ .endm

#endif /* __ASM_ASSEMBLER_H */ + +#if defined(CONFIG_RISCV_USER_CFI) && (__riscv_xlen == 64) +.macro vdso_lpad +lpad 0 +.endm +#else +.macro vdso_lpad +.endm +#endif + +/* + * This macro emits a program property note section identifying + * architecture features which require special handling, mainly for + * use in assembly files included in the VDSO. + */ +#define NT_GNU_PROPERTY_TYPE_0 5 +#define GNU_PROPERTY_RISCV_FEATURE_1_AND 0xc0000000 + +#define GNU_PROPERTY_RISCV_FEATURE_1_ZICFILP (1U << 0) +#define GNU_PROPERTY_RISCV_FEATURE_1_ZICFISS (1U << 1) + +#if defined(CONFIG_RISCV_USER_CFI) && (__riscv_xlen == 64) +#define GNU_PROPERTY_RISCV_FEATURE_1_DEFAULT \ + (GNU_PROPERTY_RISCV_FEATURE_1_ZICFILP) +#endif + +#ifdef GNU_PROPERTY_RISCV_FEATURE_1_DEFAULT +.macro emit_riscv_feature_1_and, feat = GNU_PROPERTY_RISCV_FEATURE_1_DEFAULT + .pushsection .note.gnu.property, "a" + .p2align 3 + .word 4 + .word 16 + .word NT_GNU_PROPERTY_TYPE_0 + .asciz "GNU" + .word GNU_PROPERTY_RISCV_FEATURE_1_AND + .word 4 + .word \feat + .word 0 + .popsection +.endm +#else +.macro emit_riscv_feature_1_and, feat = 0 +.endm +#endif diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 9a1b555e8733..daa10c2b0dd1 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -13,12 +13,18 @@ vdso-syms += flush_icache vdso-syms += hwprobe vdso-syms += sys_hwprobe

+ifdef CONFIG_RISCV_USER_CFI +LPAD_MARCH = _zicfilp +endif + # Files to link into the vdso obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o

ccflags-y := -fno-stack-protector ccflags-y += -DDISABLE_BRANCH_PROFILING ccflags-y += -fno-builtin +ccflags-y += $(KBUILD_BASE_ISA)$(LPAD_MARCH) +asflags-y += $(KBUILD_BASE_ISA)$(LPAD_MARCH)

ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) @@ -40,6 +46,12 @@ endif CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)

+# Disable profiling and instrumentation for VDSO code +GCOV_PROFILE := n +KCOV_INSTRUMENT := n +KASAN_SANITIZE := n +UBSAN_SANITIZE := n + # Force dependency $(obj)/vdso.o: $(obj)/vdso.so

diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S index 8f884227e8bc..e4c56970905e 100644 --- a/arch/riscv/kernel/vdso/flush_icache.S +++ b/arch/riscv/kernel/vdso/flush_icache.S @@ -5,11 +5,13 @@

#include <linux/linkage.h> #include <asm/unistd.h> +#include <asm/assembler.h>

.text /* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */ SYM_FUNC_START(__vdso_flush_icache) .cfi_startproc + vdso_lpad #ifdef CONFIG_SMP li a7, __NR_riscv_flush_icache ecall @@ -20,3 +22,5 @@ SYM_FUNC_START(__vdso_flush_icache) ret .cfi_endproc SYM_FUNC_END(__vdso_flush_icache) + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S index 9c1bd531907f..5c1ecc4e1465 100644 --- a/arch/riscv/kernel/vdso/getcpu.S +++ b/arch/riscv/kernel/vdso/getcpu.S @@ -5,14 +5,18 @@

#include <linux/linkage.h> #include <asm/unistd.h> +#include <asm/assembler.h>

.text /* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */ SYM_FUNC_START(__vdso_getcpu) .cfi_startproc + vdso_lpad /* For now, just do the syscall. */ li a7, __NR_getcpu ecall ret .cfi_endproc SYM_FUNC_END(__vdso_getcpu) + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S index 3dc022aa8931..e82987dc3739 100644 --- a/arch/riscv/kernel/vdso/rt_sigreturn.S +++ b/arch/riscv/kernel/vdso/rt_sigreturn.S @@ -5,12 +5,16 @@

#include <linux/linkage.h> #include <asm/unistd.h> +#include <asm/assembler.h>

.text SYM_FUNC_START(__vdso_rt_sigreturn) .cfi_startproc .cfi_signal_frame + vdso_lpad li a7, __NR_rt_sigreturn ecall .cfi_endproc SYM_FUNC_END(__vdso_rt_sigreturn) + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/sys_hwprobe.S b/arch/riscv/kernel/vdso/sys_hwprobe.S index 77e57f830521..f1694451a60c 100644 --- a/arch/riscv/kernel/vdso/sys_hwprobe.S +++ b/arch/riscv/kernel/vdso/sys_hwprobe.S @@ -3,13 +3,17 @@

#include <linux/linkage.h> #include <asm/unistd.h> +#include <asm/assembler.h>

.text SYM_FUNC_START(riscv_hwprobe) .cfi_startproc + vdso_lpad li a7, __NR_riscv_hwprobe ecall ret

.cfi_endproc SYM_FUNC_END(riscv_hwprobe) + +emit_riscv_feature_1_and

This patch creates a config for shadow stack support and landing pad instr support. Shadow stack support and landing instr support can be enabled by selecting `CONFIG_RISCV_USER_CFI`. Selecting `CONFIG_RISCV_USER_CFI` wires up path to enumerate CPU support and if cpu support exists, kernel will support cpu assisted user mode cfi.

If CONFIG_RISCV_USER_CFI is selected, select `ARCH_USES_HIGH_VMA_FLAGS`, `ARCH_HAS_USER_SHADOW_STACK` and DYNAMIC_SIGFRAME for riscv.

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/Kconfig | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7612c52e9b1e..0a2e50f056e8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -250,6 +250,26 @@ config ARCH_HAS_BROKEN_DWARF5 # https://github.com/llvm/llvm-project/commit/7ffabb61a5569444b5ac9322e22e5471... depends on LD_IS_LLD && LLD_VERSION < 180000

+config RISCV_USER_CFI + def_bool y + bool "riscv userspace control flow integrity" + depends on 64BIT && $(cc-option,-mabi=lp64 -march=rv64ima_zicfiss) + depends on RISCV_ALTERNATIVE + select ARCH_HAS_USER_SHADOW_STACK + select ARCH_USES_HIGH_VMA_FLAGS + select DYNAMIC_SIGFRAME + help + Provides CPU assisted control flow integrity to userspace tasks. + Control flow integrity is provided by implementing shadow stack for + backward edge and indirect branch tracking for forward edge in program. + Shadow stack protection is a hardware feature that detects function + return address corruption. This helps mitigate ROP attacks. + Indirect branch tracking enforces that all indirect branches must land + on a landing pad instruction else CPU will fault. This mitigates against + JOP / COP attacks. Applications must be enabled to use it, and old user- + space does not get protection "for free". + default y + config ARCH_MMAP_RND_BITS_MIN default 18 if 64BIT default 8

Adding documentation on landing pad aka indirect branch tracking on riscv and kernel interfaces exposed so that user tasks can enable it.

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- Documentation/arch/riscv/index.rst | 1 + Documentation/arch/riscv/zicfilp.rst | 115 +++++++++++++++++++++++++++++++++++ 2 files changed, 116 insertions(+)

diff --git a/Documentation/arch/riscv/index.rst b/Documentation/arch/riscv/index.rst index eecf347ce849..be7237b69682 100644 --- a/Documentation/arch/riscv/index.rst +++ b/Documentation/arch/riscv/index.rst @@ -14,6 +14,7 @@ RISC-V architecture uabi vector cmodx + zicfilp

features

diff --git a/Documentation/arch/riscv/zicfilp.rst b/Documentation/arch/riscv/zicfilp.rst new file mode 100644 index 000000000000..a188d78fcde6 --- /dev/null +++ b/Documentation/arch/riscv/zicfilp.rst @@ -0,0 +1,115 @@ +.. SPDX-License-Identifier: GPL-2.0 + +:Author: Deepak Gupta debug@rivosinc.com +:Date: 12 January 2024 + +==================================================== +Tracking indirect control transfers on RISC-V Linux +==================================================== + +This document briefly describes the interface provided to userspace by Linux +to enable indirect branch tracking for user mode applications on RISV-V + +1. Feature Overview +-------------------- + +Memory corruption issues usually result in to crashes, however when in hands of +an adversary and if used creatively can result into variety security issues. + +One of those security issues can be code re-use attacks on program where adversary +can use corrupt function pointers and chain them together to perform jump oriented +programming (JOP) or call oriented programming (COP) and thus compromising control +flow integrity (CFI) of the program. + +Function pointers live in read-write memory and thus are susceptible to corruption +and allows an adversary to reach any program counter (PC) in address space. On +RISC-V zicfilp extension enforces a restriction on such indirect control +transfers: + +- indirect control transfers must land on a landing pad instruction ``lpad``. + There are two exception to this rule: + + - rs1 = x1 or rs1 = x5, i.e. a return from a function and returns are + protected using shadow stack (see zicfiss.rst) + + - rs1 = x7. On RISC-V compiler usually does below to reach function + which is beyond the offset possible J-type instruction:: + + auipc x7, <imm> + jalr (x7) + + Such form of indirect control transfer are still immutable and don't rely + on memory and thus rs1=x7 is exempted from tracking and considered software + guarded jumps. + +``lpad`` instruction is pseudo of ``auipc rd, <imm_20bit>`` with ``rd=x0`` and +is a HINT nop. ``lpad`` instruction must be aligned on 4 byte boundary and +compares 20 bit immediate withx7. If ``imm_20bit`` == 0, CPU don't perform any +comparision with ``x7``. If ``imm_20bit`` != 0, then ``imm_20bit`` must match +``x7`` else CPU will raise ``software check exception`` (``cause=18``) with +``*tval = 2``. + +Compiler can generate a hash over function signatures and setup them (truncated +to 20bit) in x7 at callsites and function prologues can have ``lpad`` with same +function hash. This further reduces number of program counters a call site can +reach. + +2. ELF and psABI +----------------- + +Toolchain sets up :c:macro:`GNU_PROPERTY_RISCV_FEATURE_1_FCFI` for property +:c:macro:`GNU_PROPERTY_RISCV_FEATURE_1_AND` in notes section of the object file. + +3. Linux enabling +------------------ + +User space programs can have multiple shared objects loaded in its address space +and it's a difficult task to make sure all the dependencies have been compiled +with support of indirect branch. Thus it's left to dynamic loader to enable +indirect branch tracking for the program. + +4. prctl() enabling +-------------------- + +:c:macro:`PR_SET_INDIR_BR_LP_STATUS` / :c:macro:`PR_GET_INDIR_BR_LP_STATUS` / +:c:macro:`PR_LOCK_INDIR_BR_LP_STATUS` are three prctls added to manage indirect +branch tracking. prctls are arch agnostic and returns -EINVAL on other arches. + +* prctl(PR_SET_INDIR_BR_LP_STATUS, unsigned long arg) + +If arg1 is :c:macro:`PR_INDIR_BR_LP_ENABLE` and if CPU supports ``zicfilp`` +then kernel will enabled indirect branch tracking for the task. Dynamic loader +can issue this :c:macro:`prctl` once it has determined that all the objects +loaded in address space support indirect branch tracking. Additionally if there +is a `dlopen` to an object which wasn't compiled with ``zicfilp``, dynamic +loader can issue this prctl with arg1 set to 0 (i.e. +:c:macro:`PR_INDIR_BR_LP_ENABLE` being clear) + +* prctl(PR_GET_INDIR_BR_LP_STATUS, unsigned long arg) + +Returns current status of indirect branch tracking. If enabled it'll return +:c:macro:`PR_INDIR_BR_LP_ENABLE` + +* prctl(PR_LOCK_INDIR_BR_LP_STATUS, unsigned long arg) + +Locks current status of indirect branch tracking on the task. User space may +want to run with strict security posture and wouldn't want loading of objects +without ``zicfilp`` support in it and thus would want to disallow disabling of +indirect branch tracking. In that case user space can use this prctl to lock +current settings. + +5. violations related to indirect branch tracking +-------------------------------------------------- + +Pertaining to indirect branch tracking, CPU raises software check exception in +following conditions: + +- missing ``lpad`` after indirect call / jmp +- ``lpad`` not on 4 byte boundary +- ``imm_20bit`` embedded in ``lpad`` instruction doesn't match with ``x7`` + +In all 3 cases, ``*tval = 2`` is captured and software check exception is +raised (``cause=18``) + +Linux kernel will treat this as :c:macro:`SIGSEV`` with code = +:c:macro:`SEGV_CPERR` and follow normal course of signal delivery.

Adding documentation on shadow stack for user mode on riscv and kernel interfaces exposed so that user tasks can enable it.

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- Documentation/arch/riscv/index.rst | 1 + Documentation/arch/riscv/zicfiss.rst | 176 +++++++++++++++++++++++++++++++++++ 2 files changed, 177 insertions(+)

diff --git a/Documentation/arch/riscv/index.rst b/Documentation/arch/riscv/index.rst index be7237b69682..e240eb0ceb70 100644 --- a/Documentation/arch/riscv/index.rst +++ b/Documentation/arch/riscv/index.rst @@ -15,6 +15,7 @@ RISC-V architecture vector cmodx zicfilp + zicfiss

features

diff --git a/Documentation/arch/riscv/zicfiss.rst b/Documentation/arch/riscv/zicfiss.rst new file mode 100644 index 000000000000..5ba389f15b3f --- /dev/null +++ b/Documentation/arch/riscv/zicfiss.rst @@ -0,0 +1,176 @@ +.. SPDX-License-Identifier: GPL-2.0 + +:Author: Deepak Gupta debug@rivosinc.com +:Date: 12 January 2024 + +========================================================= +Shadow stack to protect function returns on RISC-V Linux +========================================================= + +This document briefly describes the interface provided to userspace by Linux +to enable shadow stack for user mode applications on RISV-V + +1. Feature Overview +-------------------- + +Memory corruption issues usually result in to crashes, however when in hands of +an adversary and if used creatively can result into variety security issues. + +One of those security issues can be code re-use attacks on program where +adversary can use corrupt return addresses present on stack and chain them +together to perform return oriented programming (ROP) and thus compromising +control flow integrity (CFI) of the program. + +Return addresses live on stack and thus in read-write memory and thus are +susceptible to corruption and allows an adversary to reach any program counter +(PC) in address space. On RISC-V ``zicfiss`` extension provides an alternate +stack termed as shadow stack on which return addresses can be safely placed in +prolog of the function and retrieved in epilog. ``zicfiss`` extension makes +following changes: + +- PTE encodings for shadow stack virtual memory + An earlier reserved encoding in first stage translation i.e. + PTE.R=0, PTE.W=1, PTE.X=0 becomes PTE encoding for shadow stack pages. + +- ``sspush x1/x5`` instruction pushes (stores) ``x1/x5`` to shadow stack. + +- ``sspopchk x1/x5`` instruction pops (loads) from shadow stack and compares + with ``x1/x5`` and if un-equal, CPU raises ``software check exception`` with + ``*tval = 3`` + +Compiler toolchain makes sure that function prologue have ``sspush x1/x5`` to +save return address on shadow stack in addition to regular stack. Similarly +function epilogs have ``ld x5, offset(x2)`` followed by ``sspopchk x5`` to +ensure that popped value from regular stack matches with popped value from +shadow stack. + +2. Shadow stack protections and linux memory manager +----------------------------------------------------- + +As mentioned earlier, shadow stack get new page table encodings and thus have +some special properties assigned to them and instructions that operate on them +as below: + +- Regular stores to shadow stack memory raises access store faults. This way + shadow stack memory is protected from stray inadvertant writes. + +- Regular loads to shadow stack memory are allowed. This allows stack trace + utilities or backtrace functions to read true callstack (not tampered). + +- Only shadow stack instructions can generate shadow stack load or shadow stack + store. + +- Shadow stack load / shadow stack store on read-only memory raises AMO/store + page fault. Thus both ``sspush x1/x5`` and ``sspopchk x1/x5`` will raise AMO/ + store page fault. This simplies COW handling in kernel During fork, kernel + can convert shadow stack pages into read-only memory (as it does for regular + read-write memory) and as soon as subsequent ``sspush`` or ``sspopchk`` in + userspace is encountered, then kernel can perform COW. + +- Shadow stack load / shadow stack store on read-write, read-write-execute + memory raises an access fault. This is a fatal condition because shadow stack + should never be operating on read-write, read-write-execute memory. + +3. ELF and psABI +----------------- + +Toolchain sets up :c:macro:`GNU_PROPERTY_RISCV_FEATURE_1_BCFI` for property +:c:macro:`GNU_PROPERTY_RISCV_FEATURE_1_AND` in notes section of the object file. + +4. Linux enabling +------------------ + +User space programs can have multiple shared objects loaded in its address space +and it's a difficult task to make sure all the dependencies have been compiled +with support of shadow stack. Thus it's left to dynamic loader to enable +shadow stack for the program. + +5. prctl() enabling +-------------------- + +:c:macro:`PR_SET_SHADOW_STACK_STATUS` / :c:macro:`PR_GET_SHADOW_STACK_STATUS` / +:c:macro:`PR_LOCK_SHADOW_STACK_STATUS` are three prctls added to manage shadow +stack enabling for tasks. prctls are arch agnostic and returns -EINVAL on other +arches. + +* prctl(PR_SET_SHADOW_STACK_STATUS, unsigned long arg) + +If arg1 :c:macro:`PR_SHADOW_STACK_ENABLE` and if CPU supports ``zicfiss`` then +kernel will enable shadow stack for the task. Dynamic loader can issue this +:c:macro:`prctl` once it has determined that all the objects loaded in address +space have support for shadow stack. Additionally if there is a +:c:macro:`dlopen` to an object which wasn't compiled with ``zicfiss``, dynamic +loader can issue this prctl with arg1 set to 0 (i.e. +:c:macro:`PR_SHADOW_STACK_ENABLE` being clear) + +* prctl(PR_GET_SHADOW_STACK_STATUS, unsigned long *arg) + +Returns current status of indirect branch tracking. If enabled it'll return +:c:macro:`PR_SHADOW_STACK_ENABLE`. + +* prctl(PR_LOCK_SHADOW_STACK_STATUS, unsigned long arg) + +Locks current status of shadow stack enabling on the task. User space may want +to run with strict security posture and wouldn't want loading of objects +without ``zicfiss`` support in it and thus would want to disallow disabling of +shadow stack on current task. In that case user space can use this prctl to +lock current settings. + +5. violations related to returns with shadow stack enabled +----------------------------------------------------------- + +Pertaining to shadow stack, CPU raises software check exception in following +condition: + +- On execution of ``sspopchk x1/x5``, ``x1/x5`` didn't match top of shadow + stack. If mismatch happens then cpu does ``*tval = 3`` and raise software + check exception. + +Linux kernel will treat this as :c:macro:`SIGSEV`` with code = +:c:macro:`SEGV_CPERR` and follow normal course of signal delivery. + +6. Shadow stack tokens +----------------------- +Regular stores on shadow stacks are not allowed and thus can't be tampered +with via arbitrary stray writes due to bugs. Method of pivoting / switching to +shadow stack is simply writing to csr ``CSR_SSP`` changes active shadow stack. +This can be problematic because usually value to be written to ``CSR_SSP`` will +be loaded somewhere in writeable memory and thus allows an adversary to +corruption bug in software to pivot to an any address in shadow stack range. +Shadow stack tokens can help mitigate this problem by making sure that: + +- When software is switching away from a shadow stack, shadow stack pointer + should be saved on shadow stack itself and call it ``shadow stack token`` + +- When software is switching to a shadow stack, it should read the + ``shadow stack token`` from shadow stack pointer and verify that + ``shadow stack token`` itself is pointer to shadow stack itself. + +- Once the token verification is done, software can perform the write to + ``CSR_SSP`` to switch shadow stack. + +Here software can be user mode task runtime itself which is managing various +contexts as part of single thread. Software can be kernel as well when kernel +has to deliver a signal to user task and must save shadow stack pointer. Kernel +can perform similar procedure by saving a token on user shadow stack itself. +This way whenever :c:macro:`sigreturn` happens, kernel can read the token and +verify the token and then switch to shadow stack. Using this mechanism, kernel +helps user task so that any corruption issue in user task is not exploited by +adversary by arbitrarily using :c:macro:`sigreturn`. Adversary will have to +make sure that there is a ``shadow stack token`` in addition to invoking +:c:macro:`sigreturn` + +7. Signal shadow stack +----------------------- +Following structure has been added to sigcontext for RISC-V:: + + struct __sc_riscv_cfi_state { + unsigned long ss_ptr; + }; + +As part of signal delivery, shadow stack token is saved on current shadow stack +itself and updated pointer is saved away in :c:macro:`ss_ptr` field in +:c:macro:`__sc_riscv_cfi_state` under :c:macro:`sigcontext`. Existing shadow +stack allocation is used for signal delivery. During :c:macro:`sigreturn`, +kernel will obtain :c:macro:`ss_ptr` from :c:macro:`sigcontext` and verify the +saved token on shadow stack itself and switch shadow stack.

Adds kselftest for RISC-V control flow integrity implementation for user mode. There is not a lot going on in kernel for enabling landing pad for user mode. cfi selftest are intended to be compiled with zicfilp and zicfiss enabled compiler. Thus kselftest simply checks if landing pad and shadow stack for the binary and process are enabled or not. selftest then register a signal handler for SIGSEGV. Any control flow violation are reported as SIGSEGV with si_code = SEGV_CPERR. Test will fail on receiving any SEGV_CPERR. Shadow stack part has more changes in kernel and thus there are separate tests for that

- Exercise `map_shadow_stack` syscall - `fork` test to make sure COW works for shadow stack pages - gup tests Kernel uses FOLL_FORCE when access happens to memory via /proc/<pid>/mem. Not breaking that for shadow stack. - signal test. Make sure signal delivery results in token creation on shadow stack and consumes (and verifies) token on sigreturn - shadow stack protection test. attempts to write using regular store instruction on shadow stack memory must result in access faults

Test outut ==========

""" TAP version 13 1..5 This is to ensure shadow stack is indeed enabled and working This is to ensure shadow stack is indeed enabled and working ok 1 shstk fork test ok 2 map shadow stack syscall ok 3 shadow stack gup tests ok 4 shadow stack signal tests ok 5 memory protections of shadow stack memory """

Signed-off-by: Deepak Gupta debug@rivosinc.com --- tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/cfi/.gitignore | 3 + tools/testing/selftests/riscv/cfi/Makefile | 10 + tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 82 +++++ tools/testing/selftests/riscv/cfi/riscv_cfi_test.c | 78 +++++ tools/testing/selftests/riscv/cfi/shadowstack.c | 385 +++++++++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 27 ++ 7 files changed, 586 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 099b8c1f46f8..5671b4405a12 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not)

ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?= abi hwprobe mm sigreturn vector +RISCV_SUBTARGETS ?= abi hwprobe mm sigreturn vector cfi else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/cfi/.gitignore b/tools/testing/selftests/riscv/cfi/.gitignore new file mode 100644 index 000000000000..82545863bac6 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/.gitignore @@ -0,0 +1,3 @@ +cfitests +riscv_cfi_test +shadowstack diff --git a/tools/testing/selftests/riscv/cfi/Makefile b/tools/testing/selftests/riscv/cfi/Makefile new file mode 100644 index 000000000000..b65f7ff38a32 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/Makefile @@ -0,0 +1,10 @@ +CFLAGS += -I$(top_srcdir)/tools/include + +CFLAGS += -march=rv64gc_zicfilp_zicfiss + +TEST_GEN_PROGS := cfitests + +include ../../lib.mk + +$(OUTPUT)/cfitests: riscv_cfi_test.c shadowstack.c + $(CC) -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/cfi/cfi_rv_test.h b/tools/testing/selftests/riscv/cfi/cfi_rv_test.h new file mode 100644 index 000000000000..1c8043f2b778 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/cfi_rv_test.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef SELFTEST_RISCV_CFI_H +#define SELFTEST_RISCV_CFI_H +#include <stddef.h> +#include <sys/types.h> +#include "shadowstack.h" + +#define CHILD_EXIT_CODE_SSWRITE 10 +#define CHILD_EXIT_CODE_SIG_TEST 11 + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 __asm__ ("a4") = (long)(arg5); \ + \ + __asm__ volatile( \ + "ecall\n" \ + : "+r" \ + (_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + \ + __asm__ volatile( \ + "ecall\n" \ + : "+r" (_arg1) \ + : "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#ifndef __NR_prctl +#define __NR_prctl 167 +#endif + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 453 +#endif + +#define CSR_SSP 0x011 + +#ifdef __ASSEMBLY__ +#define __ASM_STR(x) x +#else +#define __ASM_STR(x) #x +#endif + +#define csr_read(csr) \ +({ \ + register unsigned long __v; \ + __asm__ __volatile__ ("csrr %0, " __ASM_STR(csr) \ + : "=r" (__v) : \ + : "memory"); \ + __v; \ +}) + +#define csr_write(csr, val) \ +({ \ + unsigned long __v = (unsigned long)(val); \ + __asm__ __volatile__ ("csrw " __ASM_STR(csr) ", %0" \ + : : "rK" (__v) \ + : "memory"); \ +}) + +#endif diff --git a/tools/testing/selftests/riscv/cfi/riscv_cfi_test.c b/tools/testing/selftests/riscv/cfi/riscv_cfi_test.c new file mode 100644 index 000000000000..cf33aa25cc73 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/riscv_cfi_test.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest.h" +#include <sys/signal.h> +#include <asm/ucontext.h> +#include <linux/prctl.h> +#include "cfi_rv_test.h" + +/* do not optimize cfi related test functions */ +#pragma GCC push_options +#pragma GCC optimize("O0") + +void sigsegv_handler(int signum, siginfo_t *si, void *uc) +{ + struct ucontext *ctx = (struct ucontext *)uc; + + if (si->si_code == SEGV_CPERR) { + ksft_print_msg("Control flow violation happened somewhere\n"); + ksft_print_msg("PC where violation happened %lx\n", ctx->uc_mcontext.gregs[0]); + exit(-1); + } + + /* all other cases are expected to be of shadow stack write case */ + exit(CHILD_EXIT_CODE_SSWRITE); +} + +bool register_signal_handler(void) +{ + struct sigaction sa = {}; + + sa.sa_sigaction = sigsegv_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGSEGV, &sa, NULL)) { + ksft_print_msg("Registering signal handler for landing pad violation failed\n"); + return false; + } + + return true; +} + +int main(int argc, char *argv[]) +{ + int ret = 0; + unsigned long lpad_status = 0, ss_status = 0; + + ksft_print_header(); + + ksft_print_msg("Starting risc-v tests\n"); + + /* + * Landing pad test. Not a lot of kernel changes to support landing + * pad for user mode except lighting up a bit in senvcfg via a prctl + * Enable landing pad through out the execution of test binary + */ + ret = my_syscall5(__NR_prctl, PR_GET_INDIR_BR_LP_STATUS, &lpad_status, 0, 0, 0); + if (ret) + ksft_exit_fail_msg("Get landing pad status failed with %d\n", ret); + + if (!(lpad_status & PR_INDIR_BR_LP_ENABLE)) + ksft_exit_fail_msg("Landing pad is not enabled, should be enabled via glibc\n"); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &ss_status, 0, 0, 0); + if (ret) + ksft_exit_fail_msg("Get shadow stack failed with %d\n", ret); + + if (!(ss_status & PR_SHADOW_STACK_ENABLE)) + ksft_exit_fail_msg("Shadow stack is not enabled, should be enabled via glibc\n"); + + if (!register_signal_handler()) + ksft_exit_fail_msg("Registering signal handler for SIGSEGV failed\n"); + + ksft_print_msg("Landing pad and shadow stack are enabled for binary\n"); + execute_shadow_stack_tests(); + + return 0; +} + +#pragma GCC pop_options diff --git a/tools/testing/selftests/riscv/cfi/shadowstack.c b/tools/testing/selftests/riscv/cfi/shadowstack.c new file mode 100644 index 000000000000..53387dbd9cf5 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/shadowstack.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest.h" +#include <sys/wait.h> +#include <signal.h> +#include <fcntl.h> +#include <asm-generic/unistd.h> +#include <sys/mman.h> +#include "shadowstack.h" +#include "cfi_rv_test.h" + +static struct shadow_stack_tests shstk_tests[] = { + { "shstk fork test\n", shadow_stack_fork_test }, + { "map shadow stack syscall\n", shadow_stack_map_test }, + { "shadow stack gup tests\n", shadow_stack_gup_tests }, + { "shadow stack signal tests\n", shadow_stack_signal_test}, + { "memory protections of shadow stack memory\n", shadow_stack_protection_test } +}; + +#define RISCV_SHADOW_STACK_TESTS ARRAY_SIZE(shstk_tests) + +/* do not optimize shadow stack related test functions */ +#pragma GCC push_options +#pragma GCC optimize("O0") + +void zar(void) +{ + unsigned long ssp = 0; + + ssp = csr_read(CSR_SSP); + ksft_print_msg("Spewing out shadow stack ptr: %lx\n" + " This is to ensure shadow stack is indeed enabled and working\n", + ssp); +} + +void bar(void) +{ + zar(); +} + +void foo(void) +{ + bar(); +} + +void zar_child(void) +{ + unsigned long ssp = 0; + + ssp = csr_read(CSR_SSP); + ksft_print_msg("Spewing out shadow stack ptr: %lx\n" + " This is to ensure shadow stack is indeed enabled and working\n", + ssp); +} + +void bar_child(void) +{ + zar_child(); +} + +void foo_child(void) +{ + bar_child(); +} + +typedef void (call_func_ptr)(void); +/* + * call couple of functions to test push pop. + */ +int shadow_stack_call_tests(call_func_ptr fn_ptr, bool parent) +{ + ksft_print_msg("dummy calls for sspush and sspopchk in context of %s\n", + parent ? "parent" : "child"); + + (fn_ptr)(); + + return 0; +} + +/* forks a thread, and ensure shadow stacks fork out */ +bool shadow_stack_fork_test(unsigned long test_num, void *ctx) +{ + int pid = 0, child_status = 0, parent_pid = 0, ret = 0; + unsigned long ss_status = 0; + + ksft_print_msg("Exercising shadow stack fork test\n"); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &ss_status, 0, 0, 0); + if (ret) { + ksft_exit_skip("Shadow stack get status prctl failed with errorcode %d\n", ret); + return false; + } + + if (!(ss_status & PR_SHADOW_STACK_ENABLE)) + ksft_exit_skip("Shadow stack is not enabled, should be enabled via glibc\n"); + + parent_pid = getpid(); + pid = fork(); + + if (pid) { + ksft_print_msg("Parent pid %d and child pid %d\n", parent_pid, pid); + shadow_stack_call_tests(&foo, true); + } else { + shadow_stack_call_tests(&foo_child, false); + } + + if (pid) { + ksft_print_msg("Waiting on child to finish\n"); + wait(&child_status); + } else { + /* exit child gracefully */ + exit(0); + } + + if (pid && WIFSIGNALED(child_status)) { + ksft_print_msg("Child faulted, fork test failed\n"); + return false; + } + + return true; +} + +/* exercise `map_shadow_stack`, pivot to it and call some functions to ensure it works */ +#define SHADOW_STACK_ALLOC_SIZE 4096 +bool shadow_stack_map_test(unsigned long test_num, void *ctx) +{ + unsigned long shdw_addr; + int ret = 0; + + ksft_print_msg("Exercising shadow stack map test\n"); + + shdw_addr = my_syscall3(__NR_map_shadow_stack, NULL, SHADOW_STACK_ALLOC_SIZE, 0); + + if (((long)shdw_addr) <= 0) { + ksft_print_msg("map_shadow_stack failed with error code %d\n", + (int)shdw_addr); + return false; + } + + ret = munmap((void *)shdw_addr, SHADOW_STACK_ALLOC_SIZE); + + if (ret) { + ksft_print_msg("munmap failed with error code %d\n", ret); + return false; + } + + return true; +} + +/* + * shadow stack protection tests. map a shadow stack and + * validate all memory protections work on it + */ +bool shadow_stack_protection_test(unsigned long test_num, void *ctx) +{ + unsigned long shdw_addr; + unsigned long *write_addr = NULL; + int ret = 0, pid = 0, child_status = 0; + + ksft_print_msg("Exercising shadow stack protection test (WPT)\n"); + + shdw_addr = my_syscall3(__NR_map_shadow_stack, NULL, SHADOW_STACK_ALLOC_SIZE, 0); + + if (((long)shdw_addr) <= 0) { + ksft_print_msg("map_shadow_stack failed with error code %d\n", + (int)shdw_addr); + return false; + } + + write_addr = (unsigned long *)shdw_addr; + pid = fork(); + + /* no child was created, return false */ + if (pid == -1) + return false; + + /* + * try to perform a store from child on shadow stack memory + * it should result in SIGSEGV + */ + if (!pid) { + /* below write must lead to SIGSEGV */ + *write_addr = 0xdeadbeef; + } else { + wait(&child_status); + } + + /* test fail, if 0xdeadbeef present on shadow stack address */ + if (*write_addr == 0xdeadbeef) { + ksft_print_msg("Shadow stack WPT failed\n"); + return false; + } + + /* if child reached here, then fail */ + if (!pid) { + ksft_print_msg("Shadow stack WPT failed: child reached unreachable state\n"); + return false; + } + + /* if child exited via signal handler but not for write on ss */ + if (WIFEXITED(child_status) && + WEXITSTATUS(child_status) != CHILD_EXIT_CODE_SSWRITE) { + ksft_print_msg("Shadow stack WPT failed: child wasn't signaled for write\n"); + return false; + } + + ret = munmap(write_addr, SHADOW_STACK_ALLOC_SIZE); + if (ret) { + ksft_print_msg("Shadow stack WPT failed: munmap failed, error code %d\n", + ret); + return false; + } + + return true; +} + +#define SS_MAGIC_WRITE_VAL 0xbeefdead + +int gup_tests(int mem_fd, unsigned long *shdw_addr) +{ + unsigned long val = 0; + + lseek(mem_fd, (unsigned long)shdw_addr, SEEK_SET); + if (read(mem_fd, &val, sizeof(val)) < 0) { + ksft_print_msg("Reading shadow stack mem via gup failed\n"); + return 1; + } + + val = SS_MAGIC_WRITE_VAL; + lseek(mem_fd, (unsigned long)shdw_addr, SEEK_SET); + if (write(mem_fd, &val, sizeof(val)) < 0) { + ksft_print_msg("Writing shadow stack mem via gup failed\n"); + return 1; + } + + if (*shdw_addr != SS_MAGIC_WRITE_VAL) { + ksft_print_msg("GUP write to shadow stack memory failed\n"); + return 1; + } + + return 0; +} + +bool shadow_stack_gup_tests(unsigned long test_num, void *ctx) +{ + unsigned long shdw_addr = 0; + unsigned long *write_addr = NULL; + int fd = 0; + bool ret = false; + + ksft_print_msg("Exercising shadow stack gup tests\n"); + shdw_addr = my_syscall3(__NR_map_shadow_stack, NULL, SHADOW_STACK_ALLOC_SIZE, 0); + + if (((long)shdw_addr) <= 0) { + ksft_print_msg("map_shadow_stack failed with error code %d\n", (int)shdw_addr); + return false; + } + + write_addr = (unsigned long *)shdw_addr; + + fd = open("/proc/self/mem", O_RDWR); + if (fd == -1) + return false; + + if (gup_tests(fd, write_addr)) { + ksft_print_msg("gup tests failed\n"); + goto out; + } + + ret = true; +out: + if (shdw_addr && munmap(write_addr, SHADOW_STACK_ALLOC_SIZE)) { + ksft_print_msg("munmap failed with error code %d\n", ret); + ret = false; + } + + return ret; +} + +volatile bool break_loop; + +void sigusr1_handler(int signo) +{ + break_loop = true; +} + +bool sigusr1_signal_test(void) +{ + struct sigaction sa = {}; + + sa.sa_handler = sigusr1_handler; + sa.sa_flags = 0; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGUSR1, &sa, NULL)) { + ksft_print_msg("Registering signal handler for SIGUSR1 failed\n"); + return false; + } + + return true; +} + +/* + * shadow stack signal test. shadow stack must be enabled. + * register a signal, fork another thread which is waiting + * on signal. Send a signal from parent to child, verify + * that signal was received by child. If not test fails + */ +bool shadow_stack_signal_test(unsigned long test_num, void *ctx) +{ + int pid = 0, child_status = 0, ret = 0; + unsigned long ss_status = 0; + + ksft_print_msg("Exercising shadow stack signal test\n"); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &ss_status, 0, 0, 0); + if (ret) { + ksft_print_msg("Shadow stack get status prctl failed with errorcode %d\n", ret); + return false; + } + + if (!(ss_status & PR_SHADOW_STACK_ENABLE)) + ksft_print_msg("Shadow stack is not enabled, should be enabled via glibc\n"); + + /* this should be caught by signal handler and do an exit */ + if (!sigusr1_signal_test()) { + ksft_print_msg("Registering sigusr1 handler failed\n"); + exit(-1); + } + + pid = fork(); + + if (pid == -1) { + ksft_print_msg("Signal test: fork failed\n"); + goto out; + } + + if (pid == 0) { + while (!break_loop) + sleep(1); + + exit(11); + /* child shouldn't go beyond here */ + } + + /* send SIGUSR1 to child */ + kill(pid, SIGUSR1); + wait(&child_status); + +out: + + return (WIFEXITED(child_status) && + WEXITSTATUS(child_status) == 11); +} + +int execute_shadow_stack_tests(void) +{ + int ret = 0; + unsigned long test_count = 0; + unsigned long shstk_status = 0; + bool test_pass = false; + + ksft_print_msg("Executing RISC-V shadow stack self tests\n"); + ksft_set_plan(RISCV_SHADOW_STACK_TESTS); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &shstk_status, 0, 0, 0); + + if (ret != 0) + ksft_exit_fail_msg("Get shadow stack status failed with %d\n", ret); + + /* + * If we are here that means get shadow stack status succeeded and + * thus shadow stack support is baked in the kernel. + */ + while (test_count < RISCV_SHADOW_STACK_TESTS) { + test_pass = (*shstk_tests[test_count].t_func)(test_count, NULL); + ksft_test_result(test_pass, shstk_tests[test_count].name); + test_count++; + } + + ksft_finished(); + + return 0; +} + +#pragma GCC pop_options diff --git a/tools/testing/selftests/riscv/cfi/shadowstack.h b/tools/testing/selftests/riscv/cfi/shadowstack.h new file mode 100644 index 000000000000..0be510167de3 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/shadowstack.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef SELFTEST_SHADOWSTACK_TEST_H +#define SELFTEST_SHADOWSTACK_TEST_H +#include <stddef.h> +#include <linux/prctl.h> + +/* + * a cfi test returns true for success or false for fail + * takes a number for test number to index into array and void pointer. + */ +typedef bool (*shstk_test_func)(unsigned long test_num, void *); + +struct shadow_stack_tests { + char *name; + shstk_test_func t_func; +}; + +bool shadow_stack_fork_test(unsigned long test_num, void *ctx); +bool shadow_stack_map_test(unsigned long test_num, void *ctx); +bool shadow_stack_protection_test(unsigned long test_num, void *ctx); +bool shadow_stack_gup_tests(unsigned long test_num, void *ctx); +bool shadow_stack_signal_test(unsigned long test_num, void *ctx); + +int execute_shadow_stack_tests(void); + +#endif