From: Deepak Gupta <debug@rivosinc.com>
To: paul.walmsley@sifive.com, rick.p.edgecombe@intel.com,
broonie@kernel.org, Szabolcs.Nagy@arm.com, kito.cheng@sifive.com,
keescook@chromium.org, ajones@ventanamicro.com,
conor.dooley@microchip.com, cleger@rivosinc.com,
atishp@atishpatra.org, alex@ghiti.fr, bjorn@rivosinc.com,
alexghiti@rivosinc.com, samuel.holland@sifive.com,
conor@kernel.org
Cc: linux-doc@vger.kernel.org, linux-riscv@lists.infradead.org,
linux-kernel@vger.kernel.org, devicetree@vger.kernel.org,
linux-mm@kvack.org, linux-arch@vger.kernel.org,
linux-kselftest@vger.kernel.org, corbet@lwn.net,
palmer@dabbelt.com, aou@eecs.berkeley.edu, robh+dt@kernel.org,
krzysztof.kozlowski+dt@linaro.org, oleg@redhat.com,
akpm@linux-foundation.org, arnd@arndb.de, ebiederm@xmission.com,
Liam.Howlett@oracle.com, vbabka@suse.cz, lstoakes@gmail.com,
shuah@kernel.org, brauner@kernel.org, debug@rivosinc.com,
andy.chiu@sifive.com, jerry.shih@sifive.com,
hankuan.chen@sifive.com, greentime.hu@sifive.com,
evan@rivosinc.com, xiao.w.wang@intel.com, charlie@rivosinc.com,
apatel@ventanamicro.com, mchitale@ventanamicro.com,
dbarboza@ventanamicro.com, sameo@rivosinc.com,
shikemeng@huaweicloud.com, willy@infradead.org,
vincent.chen@sifive.com, guoren@kernel.org,
samitolvanen@google.com, songshuaishuai@tinylab.org,
gerg@kernel.org, heiko@sntech.de, bhe@redhat.com,
jeeheng.sia@starfivetech.com, cyy@cyyself.name,
maskray@google.com, ancientmodern4@gmail.com,
mathis.salmen@matsal.de, cuiyunhui@bytedance.com,
bgray@linux.ibm.com, mpe@ellerman.id.au, baruch@tkos.co.il,
alx@kernel.org, david@redhat.com, catalin.marinas@arm.com,
revest@chromium.org, josh@joshtriplett.org, shr@devkernel.io,
deller@gmx.de, omosnace@redhat.com, ojeda@kernel.org,
jhubbard@nvidia.com
Subject: [PATCH v3 15/29] riscv/shstk: If needed allocate a new shadow stack on clone
Date: Wed, 3 Apr 2024 16:35:03 -0700 [thread overview]
Message-ID: <20240403234054.2020347-16-debug@rivosinc.com> (raw)
In-Reply-To: <20240403234054.2020347-1-debug@rivosinc.com>
Userspace specifies VM_CLONE 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 VM_CLONE is given.
In case of VM_FORK, parent is suspended until child finishes and thus can
child use parent shadow stack. In case of !VM_CLONE, 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.
Signed-off-by: Deepak Gupta <debug@rivosinc.com>
---
arch/riscv/include/asm/usercfi.h | 39 ++++++++++
arch/riscv/kernel/process.c | 12 ++-
arch/riscv/kernel/usercfi.c | 121 +++++++++++++++++++++++++++++++
3 files changed, 171 insertions(+), 1 deletion(-)
diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h
index 4fa201b4fc4e..b47574a7a8c9 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_status {
unsigned long ubcfi_en : 1; /* Enable for backward cfi. */
@@ -17,6 +20,42 @@ struct cfi_status {
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);
+void set_active_shstk(struct task_struct *task, unsigned long shstk_addr);
+bool is_shstk_enabled(struct task_struct *task);
+
+#else
+
+static inline unsigned long shstk_alloc_thread_stack(struct task_struct *tsk,
+ const struct kernel_clone_args *args)
+{
+ return 0;
+}
+
+static inline void shstk_release(struct task_struct *tsk)
+{
+
+}
+
+static inline void set_shstk_base(struct task_struct *task, unsigned long shstk_addr,
+ unsigned long size)
+{
+
+}
+
+static inline void set_active_shstk(struct task_struct *task, unsigned long shstk_addr)
+{
+
+}
+
+static inline bool is_shstk_enabled(struct task_struct *task)
+{
+ return false;
+}
+
#endif /* CONFIG_RISCV_USER_CFI */
#endif /* __ASSEMBLY__ */
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index ce577cdc2af3..ef48a25b0eff 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -26,6 +26,7 @@
#include <asm/cpuidle.h>
#include <asm/vector.h>
#include <asm/cpufeature.h>
+#include <asm/usercfi.h>
register unsigned long gp_in_global __asm__("gp");
@@ -202,7 +203,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
void exit_thread(struct task_struct *tsk)
{
-
+ if (IS_ENABLED(CONFIG_RISCV_USER_CFI))
+ shstk_release(tsk);
}
int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
@@ -210,6 +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);
memset(&p->thread.s, 0, sizeof(p->thread.s));
@@ -225,11 +228,18 @@ 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 (ssp) /* if needed, set new ssp */
+ set_active_shstk(p, ssp);
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 c4ed0d4e33d6..11ef7ab925c9 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 ? true : false;
+}
+
+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
@@ -147,3 +182,89 @@ 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);
+}
--
2.43.2
next prev parent reply other threads:[~2024-04-03 23:42 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-03 23:34 [PATCH v3 00/29] riscv control-flow integrity for usermode Deepak Gupta
2024-04-03 23:34 ` [PATCH v3 01/29] riscv: envcfg save and restore on task switching Deepak Gupta
2024-05-09 0:10 ` Charlie Jenkins
2024-05-09 19:00 ` Deepak Gupta
2024-04-03 23:34 ` [PATCH v3 02/29] riscv: define default value for envcfg for task Deepak Gupta
2024-05-10 22:33 ` Charlie Jenkins
2024-05-13 18:33 ` Deepak Gupta
2024-04-03 23:34 ` [PATCH v3 03/29] riscv/Kconfig: enable HAVE_EXIT_THREAD for riscv Deepak Gupta
2024-05-10 22:36 ` Charlie Jenkins
2024-04-03 23:34 ` [PATCH v3 04/29] riscv: zicfilp / zicfiss in dt-bindings (extensions.yaml) Deepak Gupta
2024-04-10 11:58 ` Rob Herring
2024-04-10 21:37 ` Deepak Gupta
2024-04-15 19:41 ` Rob Herring
2024-04-16 15:44 ` Deepak Gupta
2024-05-09 18:14 ` Conor Dooley
2024-05-09 18:46 ` Deepak Gupta
2024-05-09 20:32 ` Conor Dooley
2024-05-09 23:26 ` Deepak Gupta
2024-04-03 23:34 ` [PATCH v3 05/29] riscv: zicfiss / zicfilp enumeration Deepak Gupta
2024-05-09 0:00 ` Andy Chiu
2024-05-09 0:07 ` Charlie Jenkins
2024-04-03 23:34 ` [PATCH v3 06/29] riscv: zicfiss / zicfilp extension csr and bit definitions Deepak Gupta
2024-05-10 22:37 ` Charlie Jenkins
2024-04-03 23:34 ` [PATCH v3 07/29] riscv: usercfi state for task and save/restore of CSR_SSP on trap entry/exit Deepak Gupta
2024-05-10 22:51 ` Charlie Jenkins
2024-04-03 23:34 ` [PATCH v3 08/29] mm: Define VM_SHADOW_STACK for RISC-V Deepak Gupta
2024-04-04 18:58 ` David Hildenbrand
2024-04-04 19:04 ` Mark Brown
2024-04-04 19:15 ` David Hildenbrand
2024-04-04 19:21 ` Deepak Gupta
2024-04-03 23:34 ` [PATCH v3 09/29] mm: abstract shadow stack vma behind `vma_is_shadow_stack` Deepak Gupta
2024-04-04 19:02 ` David Hildenbrand
2024-04-04 21:39 ` Deepak Gupta
2024-04-03 23:34 ` [PATCH v3 10/29] riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE Deepak Gupta
2024-05-10 21:02 ` Charlie Jenkins
2024-05-13 17:47 ` Deepak Gupta
2024-05-13 18:36 ` Charlie Jenkins
2024-05-13 18:41 ` Deepak Gupta
2024-05-13 21:26 ` Charlie Jenkins
2024-05-12 16:24 ` Alexandre Ghiti
2024-05-13 18:29 ` Deepak Gupta
2024-04-03 23:34 ` [PATCH v3 11/29] riscv mm: manufacture shadow stack pte Deepak Gupta
2024-05-12 16:26 ` Alexandre Ghiti
2024-04-03 23:35 ` [PATCH v3 12/29] riscv mmu: teach pte_mkwrite to manufacture shadow stack PTEs Deepak Gupta
2024-05-12 16:28 ` Alexandre Ghiti
2024-05-13 17:33 ` Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 13/29] riscv mmu: write protect and shadow stack Deepak Gupta
2024-05-12 16:31 ` Alexandre Ghiti
2024-05-13 17:32 ` Deepak Gupta
2024-05-23 14:59 ` Alexandre Ghiti
2024-05-24 7:16 ` Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 14/29] riscv/mm: Implement map_shadow_stack() syscall Deepak Gupta
2024-05-12 16:50 ` Alexandre Ghiti
2024-05-13 17:25 ` Deepak Gupta
2024-04-03 23:35 ` Deepak Gupta [this message]
2024-05-12 17:05 ` [PATCH v3 15/29] riscv/shstk: If needed allocate a new shadow stack on clone Alexandre Ghiti
2024-05-13 17:10 ` Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 16/29] prctl: arch-agnostic prctl for shadow stack Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 17/29] prctl: arch-agnostic prctl for indirect branch tracking Deepak Gupta
2024-05-10 23:29 ` Charlie Jenkins
2024-05-13 18:31 ` Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 18/29] riscv: Implements arch agnostic shadow stack prctls Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 19/29] riscv: Implements arch agnostic indirect branch tracking prctls Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 20/29] riscv/kernel: update __show_regs to print shadow stack register Deepak Gupta
2024-05-12 17:10 ` Alexandre Ghiti
2024-04-03 23:35 ` [PATCH v3 21/29] riscv/traps: Introduce software check exception Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 22/29] riscv sigcontext: adding cfi state field in sigcontext Deepak Gupta
2024-05-24 9:46 ` Andy Chiu
2024-05-24 19:11 ` Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 23/29] riscv signal: Save and restore of shadow stack for signal Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 24/29] riscv/ptrace: riscv cfi status and state via ptrace and in core files Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 25/29] riscv/hwprobe: zicfilp / zicfiss enumeration in hwprobe Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 26/29] riscv: create a config for shadow stack and landing pad instr support Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 27/29] riscv: Documentation for landing pad / indirect branch tracking Deepak Gupta
2024-05-10 20:30 ` Charlie Jenkins
2024-05-13 17:07 ` Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 28/29] riscv: Documentation for shadow stack on riscv Deepak Gupta
2024-04-03 23:35 ` [PATCH v3 29/29] kselftest/riscv: kselftest for user mode cfi Deepak Gupta
2024-05-09 18:21 ` Charlie Jenkins
2024-05-09 19:16 ` Deepak Gupta
2024-05-10 1:20 ` Charlie Jenkins
2024-05-09 0:33 ` [PATCH v3 00/29] riscv control-flow integrity for usermode Charlie Jenkins
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240403234054.2020347-16-debug@rivosinc.com \
--to=debug@rivosinc.com \
--cc=Liam.Howlett@oracle.com \
--cc=Szabolcs.Nagy@arm.com \
--cc=ajones@ventanamicro.com \
--cc=akpm@linux-foundation.org \
--cc=alex@ghiti.fr \
--cc=alexghiti@rivosinc.com \
--cc=alx@kernel.org \
--cc=ancientmodern4@gmail.com \
--cc=andy.chiu@sifive.com \
--cc=aou@eecs.berkeley.edu \
--cc=apatel@ventanamicro.com \
--cc=arnd@arndb.de \
--cc=atishp@atishpatra.org \
--cc=baruch@tkos.co.il \
--cc=bgray@linux.ibm.com \
--cc=bhe@redhat.com \
--cc=bjorn@rivosinc.com \
--cc=brauner@kernel.org \
--cc=broonie@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=charlie@rivosinc.com \
--cc=cleger@rivosinc.com \
--cc=conor.dooley@microchip.com \
--cc=conor@kernel.org \
--cc=corbet@lwn.net \
--cc=cuiyunhui@bytedance.com \
--cc=cyy@cyyself.name \
--cc=david@redhat.com \
--cc=dbarboza@ventanamicro.com \
--cc=deller@gmx.de \
--cc=devicetree@vger.kernel.org \
--cc=ebiederm@xmission.com \
--cc=evan@rivosinc.com \
--cc=gerg@kernel.org \
--cc=greentime.hu@sifive.com \
--cc=guoren@kernel.org \
--cc=hankuan.chen@sifive.com \
--cc=heiko@sntech.de \
--cc=jeeheng.sia@starfivetech.com \
--cc=jerry.shih@sifive.com \
--cc=jhubbard@nvidia.com \
--cc=josh@joshtriplett.org \
--cc=keescook@chromium.org \
--cc=kito.cheng@sifive.com \
--cc=krzysztof.kozlowski+dt@linaro.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-riscv@lists.infradead.org \
--cc=lstoakes@gmail.com \
--cc=maskray@google.com \
--cc=mathis.salmen@matsal.de \
--cc=mchitale@ventanamicro.com \
--cc=mpe@ellerman.id.au \
--cc=ojeda@kernel.org \
--cc=oleg@redhat.com \
--cc=omosnace@redhat.com \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.com \
--cc=revest@chromium.org \
--cc=rick.p.edgecombe@intel.com \
--cc=robh+dt@kernel.org \
--cc=sameo@rivosinc.com \
--cc=samitolvanen@google.com \
--cc=samuel.holland@sifive.com \
--cc=shikemeng@huaweicloud.com \
--cc=shr@devkernel.io \
--cc=shuah@kernel.org \
--cc=songshuaishuai@tinylab.org \
--cc=vbabka@suse.cz \
--cc=vincent.chen@sifive.com \
--cc=willy@infradead.org \
--cc=xiao.w.wang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).