VM_HIGH_ARCH_5 is used for riscv

Reviewed-by: Zong Li zong.li@sifive.com Reviewed-by: Alexandre Ghiti alexghiti@rivosinc.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 b7f13f087954..3487f28fa0bf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -352,6 +352,13 @@ 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 bcab59e0cc2e..c9e68bdbf099 100644 --- a/Documentation/devicetree/bindings/riscv/extensions.yaml +++ b/Documentation/devicetree/bindings/riscv/extensions.yaml @@ -444,6 +444,20 @@ 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

zicfiss and zicfilp extension gets enabled via b3 and b2 in *envcfg CSR. menvcfg controls enabling for S/HS mode. henvcfg control enabling for VS while senvcfg controls enabling for U/VU mode.

zicfilp extension extends *status CSR to hold `expected landing pad` bit. A trap or interrupt can occur between an indirect jmp/call and target instr. `expected landing pad` bit from CPU is recorded into xstatus CSR so that when supervisor performs xret, `expected landing pad` state of CPU can be restored.

zicfiss adds one new CSR - CSR_SSP: CSR_SSP contains current shadow stack pointer.

Signed-off-by: Deepak Gupta debug@rivosinc.com Reviewed-by: Charlie Jenkins charlie@rivosinc.com --- arch/riscv/include/asm/csr.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 6fed42e37705..2f49b9663640 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -18,6 +18,15 @@ #define SR_MPP _AC(0x00001800, UL) /* Previously Machine */ #define SR_SUM _AC(0x00040000, UL) /* Supervisor User Memory Access */

+/* zicfilp landing pad status bit */ +#define SR_SPELP _AC(0x00800000, UL) +#define SR_MPELP _AC(0x020000000000, UL) +#ifdef CONFIG_RISCV_M_MODE +#define SR_ELP SR_MPELP +#else +#define SR_ELP SR_SPELP +#endif + #define SR_FS _AC(0x00006000, UL) /* Floating-point Status */ #define SR_FS_OFF _AC(0x00000000, UL) #define SR_FS_INITIAL _AC(0x00002000, UL) @@ -212,6 +221,8 @@ #define ENVCFG_PMM_PMLEN_16 (_AC(0x3, ULL) << 32) #define ENVCFG_CBZE (_AC(1, UL) << 7) #define ENVCFG_CBCFE (_AC(1, UL) << 6) +#define ENVCFG_LPE (_AC(1, UL) << 2) +#define ENVCFG_SSE (_AC(1, UL) << 3) #define ENVCFG_CBIE_SHIFT 4 #define ENVCFG_CBIE (_AC(0x3, UL) << ENVCFG_CBIE_SHIFT) #define ENVCFG_CBIE_ILL _AC(0x0, UL) @@ -230,6 +241,11 @@ #define SMSTATEEN0_HSENVCFG (_ULL(1) << SMSTATEEN0_HSENVCFG_SHIFT) #define SMSTATEEN0_SSTATEEN0_SHIFT 63 #define SMSTATEEN0_SSTATEEN0 (_ULL(1) << SMSTATEEN0_SSTATEEN0_SHIFT) +/* + * zicfiss user mode csr + * CSR_SSP holds current shadow stack pointer. + */ +#define CSR_SSP 0x011

/* mseccfg bits */ #define MSECCFG_PMM ENVCFG_PMM

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 dba257cc4e2d..f21c888f59eb 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -433,6 +433,11 @@ 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) @@ -778,6 +783,11 @@ 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 60d4821627d2..4e3431ccf634 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -423,7 +423,7 @@ 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) */ @@ -624,7 +624,15 @@ 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

Userspace specifies CLONE_VM to share address space and spawn new thread. `clone` allow userspace to specify a new stack for new thread. However there is no way to specify new shadow stack base address without changing API. This patch allocates a new shadow stack whenever CLONE_VM is given.

In case of CLONE_VFORK, parent is suspended until child finishes and thus can child use parent shadow stack. In case of !CLONE_VM, COW kicks in because entire address space is copied from parent to child.

`clone3` is extensible and can provide mechanisms using which shadow stack as an input parameter can be provided. This is not settled yet and being extensively discussed on mailing list. Once that's settled, this commit will adapt to that.

Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/mmu_context.h | 7 ++ arch/riscv/include/asm/usercfi.h | 25 ++++++++ arch/riscv/kernel/process.c | 9 +++ arch/riscv/kernel/usercfi.c | 120 +++++++++++++++++++++++++++++++++++ 4 files changed, 161 insertions(+)

diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h index 8c4bc49a3a0f..dbf27a78df6c 100644 --- a/arch/riscv/include/asm/mmu_context.h +++ b/arch/riscv/include/asm/mmu_context.h @@ -48,6 +48,13 @@ static inline unsigned long mm_untag_mask(struct mm_struct *mm) } #endif

+#define deactivate_mm deactivate_mm +static inline void deactivate_mm(struct task_struct *tsk, + struct mm_struct *mm) +{ + shstk_release(tsk); +} + #include <asm-generic/mmu_context.h>

#endif /* _ASM_RISCV_MMU_CONTEXT_H */ diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index 94b214c295c0..0581587490c2 100644 --- a/arch/riscv/include/asm/usercfi.h +++ b/arch/riscv/include/asm/usercfi.h @@ -8,6 +8,9 @@ #ifndef __ASSEMBLY__ #include <linux/types.h>

+struct task_struct; +struct kernel_clone_args; + #ifdef CONFIG_RISCV_USER_CFI struct cfi_state { unsigned long ubcfi_en : 1; /* Enable for backward cfi. */ @@ -16,6 +19,28 @@ struct cfi_state { unsigned long shdw_stk_size; /* size of shadow stack */ };

+unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args); +void shstk_release(struct task_struct *tsk); +void set_shstk_base(struct task_struct *task, unsigned long shstk_addr, unsigned long size); +unsigned long get_shstk_base(struct task_struct *task, unsigned long *size); +void set_active_shstk(struct task_struct *task, unsigned long shstk_addr); +bool is_shstk_enabled(struct task_struct *task); + +#else + +#define shstk_alloc_thread_stack(tsk, args) 0 + +#define shstk_release(tsk) + +#define get_shstk_base(task, size) 0UL + +#define set_shstk_base(task, shstk_addr, size) + +#define set_active_shstk(task, shstk_addr) + +#define is_shstk_enabled(task) false + #endif /* CONFIG_RISCV_USER_CFI */

#endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 7c244de77180..99acb6342a37 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -29,6 +29,7 @@ #include <asm/vector.h> #include <asm/cpufeature.h> #include <asm/exec.h> +#include <asm/usercfi.h>

#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include <linux/stackprotector.h> @@ -211,6 +212,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) unsigned long clone_flags = args->flags; unsigned long usp = args->stack; unsigned long tls = args->tls; + unsigned long ssp = 0; struct pt_regs *childregs = task_pt_regs(p);

/* Ensure all threads in this mm have the same pointer masking mode. */ @@ -229,11 +231,18 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.s[0] = (unsigned long)args->fn; p->thread.s[1] = (unsigned long)args->fn_arg; } else { + /* allocate new shadow stack if needed. In case of CLONE_VM we have to */ + ssp = shstk_alloc_thread_stack(p, args); + if (IS_ERR_VALUE(ssp)) + return PTR_ERR((void *)ssp); + *childregs = *(current_pt_regs()); /* Turn off status.VS */ riscv_v_vstate_off(childregs); if (usp) /* User fork */ childregs->sp = usp; + /* if needed, set new ssp */ + ssp ? set_active_shstk(p, ssp) : 0; if (clone_flags & CLONE_SETTLS) childregs->tp = tls; childregs->a0 = 0; /* Return value of fork() */ diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index 0b3bbb41490a..ec3d78efd6f3 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -19,6 +19,41 @@

#define SHSTK_ENTRY_SIZE sizeof(void *)

+bool is_shstk_enabled(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.ubcfi_en; +} + +void set_shstk_base(struct task_struct *task, unsigned long shstk_addr, unsigned long size) +{ + task->thread_info.user_cfi_state.shdw_stk_base = shstk_addr; + task->thread_info.user_cfi_state.shdw_stk_size = size; +} + +unsigned long get_shstk_base(struct task_struct *task, unsigned long *size) +{ + if (size) + *size = task->thread_info.user_cfi_state.shdw_stk_size; + return task->thread_info.user_cfi_state.shdw_stk_base; +} + +void set_active_shstk(struct task_struct *task, unsigned long shstk_addr) +{ + task->thread_info.user_cfi_state.user_shdw_stk = shstk_addr; +} + +/* + * 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 + */ +static unsigned long calc_shstk_size(unsigned long size) +{ + if (size) + return PAGE_ALIGN(size); + + return PAGE_ALIGN(min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G)); +} + /* * Writes on shadow stack can either be `sspush` or `ssamoswap`. `sspush` can happen * implicitly on current shadow stack pointed to by CSR_SSP. `ssamoswap` takes pointer to @@ -141,3 +176,88 @@ SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsi

return allocate_shadow_stack(addr, aligned_size, size, set_tok); } + +/* + * This gets called during clone/clone3/fork. And is needed to allocate a shadow stack for + * cases where CLONE_VM is specified and thus a different stack is specified by user. We + * thus need a separate shadow stack too. How does separate shadow stack is specified by + * user is still being debated. Once that's settled, remove this part of the comment. + * This function simply returns 0 if shadow stack are not supported or if separate shadow + * stack allocation is not needed (like in case of !CLONE_VM) + */ +unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) +{ + unsigned long addr, size; + + /* If shadow stack is not supported, return 0 */ + if (!cpu_supports_shadow_stack()) + return 0; + + /* + * If shadow stack is not enabled on the new thread, skip any + * switch to a new shadow stack. + */ + if (!is_shstk_enabled(tsk)) + return 0; + + /* + * For CLONE_VFORK the child will share the parents shadow stack. + * Set base = 0 and size = 0, this is special means to track this state + * so the freeing logic run for child knows to leave it alone. + */ + if (args->flags & CLONE_VFORK) { + set_shstk_base(tsk, 0, 0); + return 0; + } + + /* + * For !CLONE_VM the child will use a copy of the parents shadow + * stack. + */ + if (!(args->flags & CLONE_VM)) + return 0; + + /* + * reaching here means, CLONE_VM was specified and thus a separate shadow + * stack is needed for new cloned thread. Note: below allocation is happening + * using current mm. + */ + size = calc_shstk_size(args->stack_size); + addr = allocate_shadow_stack(0, size, 0, false); + if (IS_ERR_VALUE(addr)) + return addr; + + set_shstk_base(tsk, addr, size); + + return addr + size; +} + +void shstk_release(struct task_struct *tsk) +{ + unsigned long base = 0, size = 0; + /* If shadow stack is not supported or not enabled, nothing to release */ + if (!cpu_supports_shadow_stack() || !is_shstk_enabled(tsk)) + return; + + /* + * When fork() with CLONE_VM fails, the child (tsk) already has a + * shadow stack allocated, and exit_thread() calls this function to + * free it. In this case the parent (current) and the child share + * the same mm struct. Move forward only when they're same. + */ + if (!tsk->mm || tsk->mm != current->mm) + return; + + /* + * We know shadow stack is enabled but if base is NULL, then + * this task is not managing its own shadow stack (CLONE_VFORK). So + * skip freeing it. + */ + base = get_shstk_base(tsk, &size); + if (!base) + return; + + vm_munmap(base, size); + set_shstk_base(tsk, 0, 0); +}

Three architectures (x86, aarch64, riscv) have support for indirect branch tracking feature in a very similar fashion. On a very high level, indirect branch tracking is a CPU feature where CPU tracks branches which uses memory operand to perform control transfer in program. As part of this tracking on indirect branches, CPU goes in a state where it expects a landing pad instr on target and if not found then CPU raises some fault (architecture dependent)

x86 landing pad instr - `ENDBRANCH` arch64 landing pad instr - `BTI` riscv landing instr - `lpad`

Given that three major arches have support for indirect branch tracking, This patch makes `prctl` for indirect branch tracking arch agnostic.

To allow userspace to enable this feature for itself, following prtcls are defined: - PR_GET_INDIR_BR_LP_STATUS: Gets current configured status for indirect branch tracking. - PR_SET_INDIR_BR_LP_STATUS: Sets a configuration for indirect branch tracking. Following status options are allowed - PR_INDIR_BR_LP_ENABLE: Enables indirect branch tracking on user thread. - PR_INDIR_BR_LP_DISABLE; Disables indirect branch tracking on user thread. - PR_LOCK_INDIR_BR_LP_STATUS: Locks configured status for indirect branch tracking for user thread.

Reviewed-by: Mark Brown broonie@kernel.org Reviewed-by: Zong Li zong.li@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- include/linux/cpu.h | 4 ++++ include/uapi/linux/prctl.h | 27 +++++++++++++++++++++++++++ kernel/sys.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 61 insertions(+)

diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e3049543008b..ea8b351b5bc5 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -204,4 +204,8 @@ static inline bool cpu_mitigations_auto_nosmt(void) } #endif

+int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status); +int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status); +int arch_lock_indir_br_lp_status(struct task_struct *t, unsigned long status); + #endif /* _LINUX_CPU_H_ */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 15c18ef4eb11..2e09b19317a3 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -364,4 +364,31 @@ struct prctl_mm_map { # define PR_TIMER_CREATE_RESTORE_IDS_ON 1 # define PR_TIMER_CREATE_RESTORE_IDS_GET 2

+/* + * Get the current indirect branch tracking configuration for the current + * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS. + */ +#define PR_GET_INDIR_BR_LP_STATUS 78 + +/* + * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will + * enable cpu feature for user thread, to track all indirect branches and ensure + * they land on arch defined landing pad instruction. + * x86 - If enabled, an indirect branch must land on `ENDBRANCH` instruction. + * arch64 - If enabled, an indirect branch must land on `BTI` instruction. + * riscv - If enabled, an indirect branch must land on `lpad` instruction. + * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect + * branches will no more be tracked by cpu to land on arch defined landing pad + * instruction. + */ +#define PR_SET_INDIR_BR_LP_STATUS 79 +# define PR_INDIR_BR_LP_ENABLE (1UL << 0) + +/* + * Prevent further changes to the specified indirect branch tracking + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_INDIR_BR_LP_STATUS 80 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index c434968e9f5d..91a1dc093c2a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2340,6 +2340,21 @@ int __weak arch_lock_shadow_stack_status(struct task_struct *t, unsigned long st return -EINVAL; }

+int __weak arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status) +{ + return -EINVAL; +} + +int __weak arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status) +{ + return -EINVAL; +} + +int __weak arch_lock_indir_br_lp_status(struct task_struct *t, unsigned long status) +{ + return -EINVAL; +} + #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE)

#ifdef CONFIG_ANON_VMA_NAME @@ -2820,6 +2835,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EINVAL; error = posixtimer_create_prctl(arg2); break; + case PR_GET_INDIR_BR_LP_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_get_indir_br_lp_status(me, (unsigned long __user *)arg2); + break; + case PR_SET_INDIR_BR_LP_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_set_indir_br_lp_status(me, arg2); + break; + case PR_LOCK_INDIR_BR_LP_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_lock_indir_br_lp_status(me, arg2); + break; default: trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5); error = -EINVAL;

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 978115567bca..8d25837a9384 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -474,6 +474,9 @@ 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 | 86 ++++++++++++++++++++++++++++++++ arch/riscv/kernel/usercfi.c | 56 +++++++++++++++++++++ 5 files changed, 157 insertions(+)

diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index cea7908cdb3a..68da5b7b79fd 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; @@ -34,6 +35,9 @@ 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); @@ -71,6 +75,12 @@ 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 a5e3d54fe54b..1bcda11e0680 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_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; } @@ -223,6 +291,16 @@ static size_t get_rt_frame_size(bool cal_all) 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 + */ + if (total_context_size) + total_context_size += sizeof(struct __riscv_ctx_hdr); + frame_size += total_context_size;

frame_size = round_up(frame_size, 16); @@ -359,6 +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 @@ -487,6 +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 2ebe789caa6b..8bc3e1e3f712 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()) @@ -169,6 +174,57 @@ 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, disabling and locking 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 | 30 ++++++++++++ arch/riscv/kernel/ptrace.c | 95 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 2 + 3 files changed, 127 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index 659ea3af5680..42c3fc8bd513 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -131,6 +131,36 @@ struct __sc_riscv_cfi_state { unsigned long ss_ptr; /* shadow stack pointer */ };

+#define PTRACE_CFI_LP_EN_BIT 0 +#define PTRACE_CFI_LP_LOCK_BIT 1 +#define PTRACE_CFI_ELP_BIT 2 +#define PTRACE_CFI_SS_EN_BIT 3 +#define PTRACE_CFI_SS_LOCK_BIT 4 +#define PTRACE_CFI_SS_PTR_BIT 5 + +#define PTRACE_CFI_LP_EN_STATE (1 << PTRACE_CFI_LP_EN_BIT) +#define PTRACE_CFI_LP_LOCK_STATE (1 << PTRACE_CFI_LP_LOCK_BIT) +#define PTRACE_CFI_ELP_STATE (1 << PTRACE_CFI_ELP_BIT) +#define PTRACE_CFI_SS_EN_STATE (1 << PTRACE_CFI_SS_EN_BIT) +#define PTRACE_CFI_SS_LOCK_STATE (1 << PTRACE_CFI_SS_LOCK_BIT) +#define PTRACE_CFI_SS_PTR_STATE (1 << PTRACE_CFI_SS_PTR_BIT) + +#define PRACE_CFI_STATE_INVALID_MASK ~(PTRACE_CFI_LP_EN_STATE | \ + PTRACE_CFI_LP_LOCK_STATE | \ + PTRACE_CFI_ELP_STATE | \ + PTRACE_CFI_SS_EN_STATE | \ + PTRACE_CFI_SS_LOCK_STATE | \ + PTRACE_CFI_SS_PTR_STATE) + +struct __cfi_status { + __u64 cfi_state; +}; + +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..933a3d26d33c 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 +188,87 @@ 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; + + memset(&user_cfi, 0, sizeof(user_cfi)); + regs = task_pt_regs(target); + + if (is_indir_lp_enabled(target)) { + user_cfi.cfi_status.cfi_state |= PTRACE_CFI_LP_EN_STATE; + user_cfi.cfi_status.cfi_state |= is_indir_lp_locked(target) ? + PTRACE_CFI_LP_LOCK_STATE : 0; + user_cfi.cfi_status.cfi_state |= (regs->status & SR_ELP) ? + PTRACE_CFI_ELP_STATE : 0; + } + + if (is_shstk_enabled(target)) { + user_cfi.cfi_status.cfi_state |= (PTRACE_CFI_SS_EN_STATE | + PTRACE_CFI_SS_PTR_STATE); + user_cfi.cfi_status.cfi_state |= is_shstk_locked(target) ? + PTRACE_CFI_SS_LOCK_STATE : 0; + 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.cfi_state & + (PTRACE_CFI_LP_EN_STATE | PTRACE_CFI_LP_LOCK_STATE | + PTRACE_CFI_SS_EN_STATE | PTRACE_CFI_SS_LOCK_STATE)) || + (user_cfi.cfi_status.cfi_state & PRACE_CFI_STATE_INVALID_MASK)) + 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.cfi_state & + PTRACE_CFI_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) && + (user_cfi.cfi_status.cfi_state & PTRACE_CFI_SS_PTR_STATE)) + 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 +309,16 @@ 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 819ded2d39de..ee30dcd80901 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -545,6 +545,8 @@ typedef struct elf64_shdr { #define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ #define NN_RISCV_TAGGED_ADDR_CTRL "LINUX" #define NT_RISCV_TAGGED_ADDR_CTRL 0x902 /* RISC-V tagged address control (prctl()) */ +#define NN_RISCV_USER_CFI "LINUX" +#define NT_RISCV_USER_CFI 0x903 /* RISC-V shadow stack state */ #define NN_LOONGARCH_CPUCFG "LINUX" #define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ #define NN_LOONGARCH_CSR "LINUX"

This commit adds a kernel command line option using which user cfi can be disabled. User backward cfi and forward cfi can be enabled independently. Kernel command line parameter "riscv_nousercfi" can take below values: - "all" : Disable forward and backward cfi both. - "bcfi" : Disable backward cfi. - "fcfi" : Disable forward cfi

Signed-off-by: Deepak Gupta debug@rivosinc.com --- Documentation/admin-guide/kernel-parameters.txt | 8 ++++ arch/riscv/include/asm/usercfi.h | 7 +++ arch/riscv/kernel/usercfi.c | 59 ++++++++++++++++++++----- 3 files changed, 63 insertions(+), 11 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 76e538c77e31..f75d50420a56 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6237,6 +6237,14 @@ replacement properties are not found. See the Kconfig entry for RISCV_ISA_FALLBACK.

+ riscv_nousercfi= + all Disable user cfi ABI to userspace even if cpu extension + are available. + bcfi Disable user backward cfi ABI to userspace even if + shadow stack extension is available. + fcfi Disable user forward cfi ABI to userspace even if landing + pad extension is available. + ro [KNL] Mount root device read-only on boot

rodata= [KNL,EARLY] diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index 68da5b7b79fd..6867ba6bd5a5 100644 --- a/arch/riscv/include/asm/usercfi.h +++ b/arch/riscv/include/asm/usercfi.h @@ -5,6 +5,10 @@ #ifndef _ASM_RISCV_USERCFI_H #define _ASM_RISCV_USERCFI_H

+#define CMDLINE_DISABLE_RISCV_USERCFI_FCFI 1 +#define CMDLINE_DISABLE_RISCV_USERCFI_BCFI 2 +#define CMDLINE_DISABLE_RISCV_USERCFI 3 + #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/prctl.h> @@ -83,6 +87,9 @@ void set_indir_lp_lock(struct task_struct *task);

#endif /* CONFIG_RISCV_USER_CFI */

+bool is_user_shstk_enabled(void); +bool is_user_lpad_enabled(void); + #endif /* __ASSEMBLY__ */

#endif /* _ASM_RISCV_USERCFI_H */ diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index 8bc3e1e3f712..5ef357f43ad7 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>

+unsigned int riscv_nousercfi; + #define SHSTK_ENTRY_SIZE sizeof(void *)

bool is_shstk_enabled(struct task_struct *task) @@ -59,7 +61,7 @@ unsigned long get_active_shstk(struct task_struct *task)

void set_shstk_status(struct task_struct *task, bool enable) { - if (!cpu_supports_shadow_stack()) + if (!is_user_shstk_enabled()) return;

task->thread_info.user_cfi_state.ubcfi_en = enable ? 1 : 0; @@ -89,7 +91,7 @@ bool is_indir_lp_locked(struct task_struct *task)

void set_indir_lp_status(struct task_struct *task, bool enable) { - if (!cpu_supports_indirect_br_lp_instr()) + if (!is_user_lpad_enabled()) return;

task->thread_info.user_cfi_state.ufcfi_en = enable ? 1 : 0; @@ -259,7 +261,7 @@ SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsi bool set_tok = flags & SHADOW_STACK_SET_TOKEN; unsigned long aligned_size = 0;

- if (!cpu_supports_shadow_stack()) + if (!is_user_shstk_enabled()) return -EOPNOTSUPP;

/* Anything other than set token should result in invalid param */ @@ -306,7 +308,7 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long addr, size;

/* If shadow stack is not supported, return 0 */ - if (!cpu_supports_shadow_stack()) + if (!is_user_shstk_enabled()) return 0;

/* @@ -352,7 +354,7 @@ void shstk_release(struct task_struct *tsk) { unsigned long base = 0, size = 0; /* If shadow stack is not supported or not enabled, nothing to release */ - if (!cpu_supports_shadow_stack() || !is_shstk_enabled(tsk)) + if (!is_user_shstk_enabled() || !is_shstk_enabled(tsk)) return;

/* @@ -381,7 +383,7 @@ int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *st { unsigned long bcfi_status = 0;

- if (!cpu_supports_shadow_stack()) + if (!is_user_shstk_enabled()) return -EINVAL;

/* this means shadow stack is enabled on the task */ @@ -395,7 +397,7 @@ int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) unsigned long size = 0, addr = 0; bool enable_shstk = false;

- if (!cpu_supports_shadow_stack()) + if (!is_user_shstk_enabled()) return -EINVAL;

/* Reject unknown flags */ @@ -448,7 +450,7 @@ int arch_lock_shadow_stack_status(struct task_struct *task, unsigned long arg) { /* If shtstk not supported or not enabled on task, nothing to lock here */ - if (!cpu_supports_shadow_stack() || + if (!is_user_shstk_enabled() || !is_shstk_enabled(task) || arg != 0) return -EINVAL;

@@ -461,7 +463,7 @@ int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *sta { unsigned long fcfi_status = 0;

- if (!cpu_supports_indirect_br_lp_instr()) + if (!is_user_lpad_enabled()) return -EINVAL;

/* indirect branch tracking is enabled on the task or not */ @@ -474,7 +476,7 @@ 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()) + if (!is_user_lpad_enabled()) return -EINVAL;

/* indirect branch tracking is locked and further can't be modified by user */ @@ -498,7 +500,7 @@ int arch_lock_indir_br_lp_status(struct task_struct *task, * If indirect branch tracking is not supported or not enabled on task, * nothing to lock here */ - if (!cpu_supports_indirect_br_lp_instr() || + if (!is_user_lpad_enabled() || !is_indir_lp_enabled(task) || arg != 0) return -EINVAL;

@@ -506,3 +508,38 @@ int arch_lock_indir_br_lp_status(struct task_struct *task,

return 0; } + +bool is_user_shstk_enabled(void) +{ + return (cpu_supports_shadow_stack() && + !(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI)); +} + +bool is_user_lpad_enabled(void) +{ + return (cpu_supports_indirect_br_lp_instr() && + !(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI)); +} + +static int __init setup_global_riscv_enable(char *str) +{ + if (strcmp(str, "all") == 0) + riscv_nousercfi = CMDLINE_DISABLE_RISCV_USERCFI; + + if (strcmp(str, "fcfi") == 0) + riscv_nousercfi |= CMDLINE_DISABLE_RISCV_USERCFI_FCFI; + + if (strcmp(str, "bcfi") == 0) + riscv_nousercfi |= CMDLINE_DISABLE_RISCV_USERCFI_BCFI; + + if (riscv_nousercfi) + pr_info("riscv user cfi disabled via cmdline" + "shadow stack status : %s, landing pad status : %s\n", + (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI) ? "disabled" : + "enabled", (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI) ? + "disabled" : "enabled"); + + return 1; +} + +__setup("riscv_nousercfi=", 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 | 6 +++++ 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, 70 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 539d2aef5cab..c2dd09bb9db3 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 ad73607abc28..441c5431d27e 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_zicfiss -fcf-protection=full +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) 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

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..dcf43de73a06 --- /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 RISC-V + +1. Feature Overview +-------------------- + +Memory corruption issues usually result into crashes, however when in hands of +an adversary and if used creatively can result into a 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 with x7. If ``imm_20bit`` == 0, CPU doesn'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 enable 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.

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 / shadow stack for the process are enabled or not and executes ptrace selftests on cfi. 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 - ptrace test: adds landing pad violation, clears ELP and continues

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

squash

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 | 173 +++++++++ tools/testing/selftests/riscv/cfi/shadowstack.c | 385 +++++++++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 27 ++ 7 files changed, 681 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 $(ARCH),riscv)) -RISCV_SUBTARGETS ?= abi hwprobe mm sigreturn vector +RISCV_SUBTARGETS ?= abi hwprobe mm sigreturn vector cfi else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/cfi/.gitignore b/tools/testing/selftests/riscv/cfi/.gitignore new file mode 100644 index 000000000000..82545863bac6 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/.gitignore @@ -0,0 +1,3 @@ +cfitests +riscv_cfi_test +shadowstack diff --git a/tools/testing/selftests/riscv/cfi/Makefile b/tools/testing/selftests/riscv/cfi/Makefile new file mode 100644 index 000000000000..1fa27cc10fb5 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/Makefile @@ -0,0 +1,10 @@ +CFLAGS += -I$(top_srcdir)/tools/include + +CFLAGS += -march=rv64gc_zicfilp_zicfiss -fcf-protection=full + +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..486a2e779053 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/riscv_cfi_test.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest.h" +#include <sys/signal.h> +#include <asm/ucontext.h> +#include <linux/prctl.h> +#include <errno.h> +#include <linux/ptrace.h> +#include <sys/wait.h> +#include <linux/elf.h> +#include <sys/uio.h> +#include <asm-generic/unistd.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; +} + +long ptrace(int request, pid_t pid, void *addr, void *data); + +bool cfi_ptrace_test(void) +{ + pid_t pid; + int status, ret = 0; + unsigned long ptrace_test_num = 0, total_ptrace_tests = 2; + + struct user_cfi_state cfi_reg; + struct iovec iov; + + pid = fork(); + + if (pid == -1) { + ksft_exit_fail_msg("%s: fork failed\n", __func__); + exit(1); + } + + if (pid == 0) { + /* allow to be traced */ + ptrace(PTRACE_TRACEME, 0, NULL, NULL); + raise(SIGSTOP); + asm volatile ( + "la a5, 1f\n" + "jalr a5 \n" + "nop \n" + "nop \n" + "1: nop\n" + : : : "a5"); + exit(11); + /* child shouldn't go beyond here */ + } + + /* parent's code goes here */ + iov.iov_base = &cfi_reg; + iov.iov_len = sizeof(cfi_reg); + + while (ptrace_test_num < total_ptrace_tests) { + memset(&cfi_reg, 0, sizeof(cfi_reg)); + waitpid(pid, &status, 0); + if (WIFSTOPPED(status)) { + errno = 0; + ret = ptrace(PTRACE_GETREGSET, pid, (void *)NT_RISCV_USER_CFI, &iov); + if (ret == -1 && errno) + ksft_exit_fail_msg("%s: PTRACE_GETREGSET failed\n", __func__); + } else + ksft_exit_fail_msg("%s: child didn't stop, failed\n", __func__); + + switch (ptrace_test_num) { +#define CFI_ENABLE_MASK (PTRACE_CFI_LP_EN_STATE | \ + PTRACE_CFI_SS_EN_STATE | \ + PTRACE_CFI_SS_PTR_STATE) + case 0: + if ((cfi_reg.cfi_status.cfi_state & CFI_ENABLE_MASK) != CFI_ENABLE_MASK) + ksft_exit_fail_msg("%s: ptrace_getregset failed, %llu\n", __func__, + cfi_reg.cfi_status.cfi_state); + if (!cfi_reg.shstk_ptr) + ksft_exit_fail_msg("%s: NULL shadow stack pointer, test failed\n", + __func__); + break; + case 1: + if (!(cfi_reg.cfi_status.cfi_state & PTRACE_CFI_ELP_STATE)) + ksft_exit_fail_msg("%s: elp must have been set\n", __func__); + /* clear elp state. not interested in anything else */ + cfi_reg.cfi_status.cfi_state = 0; + + ret = ptrace(PTRACE_SETREGSET, pid, (void *)NT_RISCV_USER_CFI, &iov); + if (ret == -1 && errno) + ksft_exit_fail_msg("%s: PTRACE_GETREGSET failed\n", __func__); + break; + default: + ksft_exit_fail_msg("%s: unreachable switch case\n", __func__); + break; + } + ptrace(PTRACE_CONT, pid, NULL, NULL); + ptrace_test_num++; + } + + waitpid(pid, &status, 0); + if (WEXITSTATUS(status) != 11) + ksft_print_msg("%s, bad return code from child\n", __func__); + + ksft_print_msg("%s, ptrace test succeeded\n", __func__); + 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"); + cfi_ptrace_test(); + + 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