From: Helge Deller deller@gmx.de

commit 71bdea6f798b425bc0003780b13e3fdecb16a010 upstream.

Adjust some MADV_XXX constants to be in sync what their values are on all other platforms. There is currently no reason to have an own numbering on parisc, but it requires workarounds in many userspace sources (e.g. glibc, qemu, ...) - which are often forgotten and thus introduce bugs and different behaviour on parisc.

A wrapper avoids an ABI breakage for existing userspace applications by translating any old values to the new ones, so this change allows us to move over all programs to the new ABI over time.

Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/parisc/include/uapi/asm/mman.h | 29 ++++++++++++++--------------- arch/parisc/kernel/sys_parisc.c | 28 ++++++++++++++++++++++++++++ arch/parisc/kernel/syscalls/syscall.tbl | 2 +- tools/arch/parisc/include/uapi/asm/mman.h | 12 ++++++------ tools/perf/bench/bench.h | 12 ------------ 5 files changed, 49 insertions(+), 34 deletions(-)

--- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -49,6 +49,19 @@ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */

+#define MADV_MERGEABLE 12 /* KSM may merge identical pages */ +#define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */ + +#define MADV_HUGEPAGE 14 /* Worth backing with hugepages */ +#define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */ + +#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump, + overrides the coredump filter bits */ +#define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */ + +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */

@@ -57,27 +70,13 @@

#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */

-#define MADV_MERGEABLE 65 /* KSM may merge identical pages */ -#define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ - -#define MADV_HUGEPAGE 67 /* Worth backing with hugepages */ -#define MADV_NOHUGEPAGE 68 /* Not worth backing with hugepages */ - -#define MADV_DONTDUMP 69 /* Explicity exclude from the core dump, - overrides the coredump filter bits */ -#define MADV_DODUMP 70 /* Clear the MADV_NODUMP flag */ - -#define MADV_WIPEONFORK 71 /* Zero memory on fork, child only */ -#define MADV_KEEPONFORK 72 /* Undo MADV_WIPEONFORK */ - -#define MADV_COLLAPSE 73 /* Synchronous hugepage collapse */ +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */

#define MADV_HWPOISON 100 /* poison a page for testing */ #define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */

/* compatibility flags */ #define MAP_FILE 0 -#define MAP_VARIABLE 0

#define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -465,3 +465,31 @@ asmlinkage long parisc_inotify_init1(int flags = FIX_O_NONBLOCK(flags); return sys_inotify_init1(flags); } + +/* + * madvise() wrapper + * + * Up to kernel v6.1 parisc has different values than all other + * platforms for the MADV_xxx flags listed below. + * To keep binary compatibility with existing userspace programs + * translate the former values to the new values. + * + * XXX: Remove this wrapper in year 2025 (or later) + */ + +asmlinkage notrace long parisc_madvise(unsigned long start, size_t len_in, int behavior) +{ + switch (behavior) { + case 65: behavior = MADV_MERGEABLE; break; + case 66: behavior = MADV_UNMERGEABLE; break; + case 67: behavior = MADV_HUGEPAGE; break; + case 68: behavior = MADV_NOHUGEPAGE; break; + case 69: behavior = MADV_DONTDUMP; break; + case 70: behavior = MADV_DODUMP; break; + case 71: behavior = MADV_WIPEONFORK; break; + case 72: behavior = MADV_KEEPONFORK; break; + case 73: behavior = MADV_COLLAPSE; break; + } + + return sys_madvise(start, len_in, behavior); +} --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -131,7 +131,7 @@ 116 common sysinfo sys_sysinfo compat_sys_sysinfo 117 common shutdown sys_shutdown 118 common fsync sys_fsync -119 common madvise sys_madvise +119 common madvise parisc_madvise 120 common clone sys_clone_wrapper 121 common setdomainname sys_setdomainname 122 common sendfile sys_sendfile compat_sys_sendfile --- a/tools/arch/parisc/include/uapi/asm/mman.h +++ b/tools/arch/parisc/include/uapi/asm/mman.h @@ -1,20 +1,20 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H -#define MADV_DODUMP 70 +#define MADV_DODUMP 17 #define MADV_DOFORK 11 -#define MADV_DONTDUMP 69 +#define MADV_DONTDUMP 16 #define MADV_DONTFORK 10 #define MADV_DONTNEED 4 #define MADV_FREE 8 -#define MADV_HUGEPAGE 67 -#define MADV_MERGEABLE 65 -#define MADV_NOHUGEPAGE 68 +#define MADV_HUGEPAGE 14 +#define MADV_MERGEABLE 12 +#define MADV_NOHUGEPAGE 15 #define MADV_NORMAL 0 #define MADV_RANDOM 1 #define MADV_REMOVE 9 #define MADV_SEQUENTIAL 2 -#define MADV_UNMERGEABLE 66 +#define MADV_UNMERGEABLE 13 #define MADV_WILLNEED 3 #define MAP_ANONYMOUS 0x10 #define MAP_DENYWRITE 0x0800 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -10,25 +10,13 @@ extern struct timeval bench__start, benc * The madvise transparent hugepage constants were added in glibc * 2.13. For compatibility with older versions of glibc, define these * tokens if they are not already defined. - * - * PA-RISC uses different madvise values from other architectures and - * needs to be special-cased. */ -#ifdef __hppa__ -# ifndef MADV_HUGEPAGE -# define MADV_HUGEPAGE 67 -# endif -# ifndef MADV_NOHUGEPAGE -# define MADV_NOHUGEPAGE 68 -# endif -#else # ifndef MADV_HUGEPAGE # define MADV_HUGEPAGE 14 # endif # ifndef MADV_NOHUGEPAGE # define MADV_NOHUGEPAGE 15 # endif -#endif

int bench_numa(int argc, const char **argv); int bench_sched_messaging(int argc, const char **argv);

From: Kyle Huey me@kylehuey.com

commit 1c813ce0305571e1b2e4cc4acca451da9e6ad18f upstream.

Both KVM (through KVM_SET_XSTATE) and ptrace (through PTRACE_SETREGSET with NT_X86_XSTATE) ultimately call copy_uabi_from_kernel_to_xstate(), but the canonical locations for the current PKRU value for KVM guests and processes in a ptrace stop are different (in the kvm_vcpu_arch and the thread_state structs respectively).

In preparation for eventually handling PKRU in copy_uabi_to_xstate, pass in a pointer to the PKRU location.

Signed-off-by: Kyle Huey me@kylehuey.com Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Link: https://lore.kernel.org/all/20221115230932.7126-3-khuey%40kylehuey.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/fpu/core.c | 2 +- arch/x86/kernel/fpu/regset.c | 2 +- arch/x86/kernel/fpu/xstate.c | 2 +- arch/x86/kernel/fpu/xstate.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-)

--- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -406,7 +406,7 @@ int fpu_copy_uabi_to_guest_fpstate(struc if (ustate->xsave.header.xfeatures & ~xcr0) return -EINVAL;

- ret = copy_uabi_from_kernel_to_xstate(kstate, ustate); + ret = copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru); if (ret) return ret;

--- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -167,7 +167,7 @@ int xstateregs_set(struct task_struct *t }

fpu_force_restore(fpu); - ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf); + ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf, &target->thread.pkru);

out: vfree(tmpbuf); --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1268,7 +1268,7 @@ static int copy_uabi_to_xstate(struct fp * Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S] * format and copy to the target thread. Used by ptrace and KVM. */ -int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf) +int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru) { return copy_uabi_to_xstate(fpstate, kbuf, NULL); } --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -46,7 +46,7 @@ extern void __copy_xstate_to_uabi_buf(st u32 pkru_val, enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); -extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf); +extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf);

From: Kyle Huey me@kylehuey.com

commit 4a804c4f8356393d6b5eff7600f07615d7869c13 upstream.

Move KVM's PKRU handling code in fpu_copy_uabi_to_guest_fpstate() to copy_uabi_to_xstate() so that it is shared with other APIs that write the XSTATE such as PTRACE_SETREGSET with NT_X86_XSTATE.

This restores the pre-5.14 behavior of ptrace. The regression can be seen by running gdb and executing `p $pkru`, `set $pkru = 42`, and `p $pkru`. On affected kernels (5.14+) the write to the PKRU register (which gdb performs through ptrace) is ignored.

[ dhansen: removed stable@ tag for now. The ABI was broken for long enough that this is not urgent material. Let's let it stew in tip for a few weeks before it's submitted to stable because there are so many ABIs potentially affected. ]

Fixes: e84ba47e313d ("x86/fpu: Hook up PKRU into ptrace()") Signed-off-by: Kyle Huey me@kylehuey.com Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Link: https://lore.kernel.org/all/20221115230932.7126-5-khuey%40kylehuey.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/fpu/core.c | 13 +------------ arch/x86/kernel/fpu/xstate.c | 21 ++++++++++++++++++++- 2 files changed, 21 insertions(+), 13 deletions(-)

--- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -391,8 +391,6 @@ int fpu_copy_uabi_to_guest_fpstate(struc { struct fpstate *kstate = gfpu->fpstate; const union fpregs_state *ustate = buf; - struct pkru_state *xpkru; - int ret;

if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) { if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE) @@ -406,16 +404,7 @@ int fpu_copy_uabi_to_guest_fpstate(struc if (ustate->xsave.header.xfeatures & ~xcr0) return -EINVAL;

- ret = copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru); - if (ret) - return ret; - - /* Retrieve PKRU if not in init state */ - if (kstate->regs.xsave.header.xfeatures & XFEATURE_MASK_PKRU) { - xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU); - *vpkru = xpkru->pkru; - } - return 0; + return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru); } EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate); #endif /* CONFIG_KVM */ --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1205,10 +1205,22 @@ static int copy_from_buffer(void *dst, u * @fpstate: The fpstate buffer to copy to * @kbuf: The UABI format buffer, if it comes from the kernel * @ubuf: The UABI format buffer, if it comes from userspace - * @pkru: unused + * @pkru: The location to write the PKRU value to * * Converts from the UABI format into the kernel internal hardware * dependent format. + * + * This function ultimately has three different callers with distinct PKRU + * behavior. + * 1. When called from sigreturn the PKRU register will be restored from + * @fpstate via an XRSTOR. Correctly copying the UABI format buffer to + * @fpstate is sufficient to cover this case, but the caller will also + * pass a pointer to the thread_struct's pkru field in @pkru and updating + * it is harmless. + * 2. When called from ptrace the PKRU register will be restored from the + * thread_struct's pkru field. A pointer to that is passed in @pkru. + * 3. When called from KVM the PKRU register will be restored from the vcpu's + * pkru field. A pointer to that is passed in @pkru. */ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, const void __user *ubuf, u32 *pkru) @@ -1260,6 +1272,13 @@ static int copy_uabi_to_xstate(struct fp } }

+ if (hdr.xfeatures & XFEATURE_MASK_PKRU) { + struct pkru_state *xpkru; + + xpkru = __raw_xsave_addr(xsave, XFEATURE_PKRU); + *pkru = xpkru->pkru; + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures':

From: Kyle Huey me@kylehuey.com

commit 6ea25770b043c7997ab21d1ce95ba5de4d3d85d9 upstream.

This tests PTRACE_SETREGSET with NT_X86_XSTATE modifying PKRU directly and removing the PKRU bit from XSTATE_BV.

Signed-off-by: Kyle Huey me@kylehuey.com Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Link: https://lore.kernel.org/all/20221115230932.7126-7-khuey%40kylehuey.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/vm/pkey-x86.h | 12 ++ tools/testing/selftests/vm/protection_keys.c | 131 ++++++++++++++++++++++++++- 2 files changed, 141 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/vm/pkey-x86.h @@ -104,6 +104,18 @@ static inline int cpu_has_pkeys(void) return 1; }

+static inline int cpu_max_xsave_size(void) +{ + unsigned long XSTATE_CPUID = 0xd; + unsigned int eax; + unsigned int ebx; + unsigned int ecx; + unsigned int edx; + + __cpuid_count(XSTATE_CPUID, 0, eax, ebx, ecx, edx); + return ecx; +} + static inline u32 pkey_bit_position(int pkey) { return pkey * PKEY_BITS_PER_PKEY; --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -18,12 +18,13 @@ * do a plain mprotect() to a mprotect_pkey() area and make sure the pkey sticks * * Compile like this: - * gcc -o protection_keys -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm - * gcc -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm + * gcc -mxsave -o protection_keys -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm + * gcc -mxsave -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm */ #define _GNU_SOURCE #define __SANE_USERSPACE_TYPES__ #include <errno.h> +#include <linux/elf.h> #include <linux/futex.h> #include <time.h> #include <sys/time.h> @@ -1550,6 +1551,129 @@ void test_implicit_mprotect_exec_only_me do_not_expect_pkey_fault("plain read on recently PROT_EXEC area"); }

+#if defined(__i386__) || defined(__x86_64__) +void test_ptrace_modifies_pkru(int *ptr, u16 pkey) +{ + u32 new_pkru; + pid_t child; + int status, ret; + int pkey_offset = pkey_reg_xstate_offset(); + size_t xsave_size = cpu_max_xsave_size(); + void *xsave; + u32 *pkey_register; + u64 *xstate_bv; + struct iovec iov; + + new_pkru = ~read_pkey_reg(); + /* Don't make PROT_EXEC mappings inaccessible */ + new_pkru &= ~3; + + child = fork(); + pkey_assert(child >= 0); + dprintf3("[%d] fork() ret: %d\n", getpid(), child); + if (!child) { + ptrace(PTRACE_TRACEME, 0, 0, 0); + /* Stop and allow the tracer to modify PKRU directly */ + raise(SIGSTOP); + + /* + * need __read_pkey_reg() version so we do not do shadow_pkey_reg + * checking + */ + if (__read_pkey_reg() != new_pkru) + exit(1); + + /* Stop and allow the tracer to clear XSTATE_BV for PKRU */ + raise(SIGSTOP); + + if (__read_pkey_reg() != 0) + exit(1); + + /* Stop and allow the tracer to examine PKRU */ + raise(SIGSTOP); + + exit(0); + } + + pkey_assert(child == waitpid(child, &status, 0)); + dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status); + pkey_assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP); + + xsave = (void *)malloc(xsave_size); + pkey_assert(xsave > 0); + + /* Modify the PKRU register directly */ + iov.iov_base = xsave; + iov.iov_len = xsave_size; + ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov); + pkey_assert(ret == 0); + + pkey_register = (u32 *)(xsave + pkey_offset); + pkey_assert(*pkey_register == read_pkey_reg()); + + *pkey_register = new_pkru; + + ret = ptrace(PTRACE_SETREGSET, child, (void *)NT_X86_XSTATE, &iov); + pkey_assert(ret == 0); + + /* Test that the modification is visible in ptrace before any execution */ + memset(xsave, 0xCC, xsave_size); + ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov); + pkey_assert(ret == 0); + pkey_assert(*pkey_register == new_pkru); + + /* Execute the tracee */ + ret = ptrace(PTRACE_CONT, child, 0, 0); + pkey_assert(ret == 0); + + /* Test that the tracee saw the PKRU value change */ + pkey_assert(child == waitpid(child, &status, 0)); + dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status); + pkey_assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP); + + /* Test that the modification is visible in ptrace after execution */ + memset(xsave, 0xCC, xsave_size); + ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov); + pkey_assert(ret == 0); + pkey_assert(*pkey_register == new_pkru); + + /* Clear the PKRU bit from XSTATE_BV */ + xstate_bv = (u64 *)(xsave + 512); + *xstate_bv &= ~(1 << 9); + + ret = ptrace(PTRACE_SETREGSET, child, (void *)NT_X86_XSTATE, &iov); + pkey_assert(ret == 0); + + /* Test that the modification is visible in ptrace before any execution */ + memset(xsave, 0xCC, xsave_size); + ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov); + pkey_assert(ret == 0); + pkey_assert(*pkey_register == 0); + + ret = ptrace(PTRACE_CONT, child, 0, 0); + pkey_assert(ret == 0); + + /* Test that the tracee saw the PKRU value go to 0 */ + pkey_assert(child == waitpid(child, &status, 0)); + dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status); + pkey_assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP); + + /* Test that the modification is visible in ptrace after execution */ + memset(xsave, 0xCC, xsave_size); + ret = ptrace(PTRACE_GETREGSET, child, (void *)NT_X86_XSTATE, &iov); + pkey_assert(ret == 0); + pkey_assert(*pkey_register == 0); + + ret = ptrace(PTRACE_CONT, child, 0, 0); + pkey_assert(ret == 0); + pkey_assert(child == waitpid(child, &status, 0)); + dprintf3("[%d] waitpid(%d) status: %x\n", getpid(), child, status); + pkey_assert(WIFEXITED(status)); + pkey_assert(WEXITSTATUS(status) == 0); + free(xsave); +} +#endif + void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) { int size = PAGE_SIZE; @@ -1585,6 +1709,9 @@ void (*pkey_tests[])(int *ptr, u16 pkey) test_pkey_syscalls_bad_args, test_pkey_alloc_exhaust, test_pkey_alloc_free_attach_pkey0, +#if defined(__i386__) || defined(__x86_64__) + test_ptrace_modifies_pkru, +#endif };

void run_tests_once(void)

From: Linus Torvalds torvalds@linux-foundation.org

commit 5a41237ad1d4b62008f93163af1d9b1da90729d8 upstream.

We had already disabled this warning for gcc-12 due to bugs in the value range analysis, but it turns out we end up having some similar problems with gcc-11.3 too, so let's disable it there too.

Older gcc versions end up being increasingly less relevant, and hopefully clang and newer version of gcc (ie gcc-13) end up working reliably enough that we still get the build coverage even when we disable this for some versions.

Link: https://lore.kernel.org/all/20221227002941.GA2691687@roeck-us.net/ Link: https://lore.kernel.org/all/D8BDBF66-E44C-45D4-9758-BAAA4F0C1998@kernel.org/ Cc: Kees Cook kees@kernel.org Cc: Vlastimil Babka vbabka@suse.cz Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- init/Kconfig | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/init/Kconfig +++ b/init/Kconfig @@ -892,13 +892,17 @@ config CC_IMPLICIT_FALLTHROUGH default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5) default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough)

-# Currently, disable gcc-12 array-bounds globally. +# Currently, disable gcc-11,12 array-bounds globally. # We may want to target only particular configurations some day. +config GCC11_NO_ARRAY_BOUNDS + def_bool y + config GCC12_NO_ARRAY_BOUNDS def_bool y

config CC_NO_ARRAY_BOUNDS bool + default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_ARRAY_BOUNDS default y if CC_IS_GCC && GCC_VERSION >= 120000 && GCC_VERSION < 130000 && GCC12_NO_ARRAY_BOUNDS

#

From: Frederick Lawler fred@cloudflare.com

commit 96398560f26aa07e8f2969d73c8197e6a6d10407 upstream.

While experimenting with applying noqueue to a classful queue discipline, we discovered a NULL pointer dereference in the __dev_queue_xmit() path that generates a kernel OOPS:

# dev=enp0s5 # tc qdisc replace dev $dev root handle 1: htb default 1 # tc class add dev $dev parent 1: classid 1:1 htb rate 10mbit # tc qdisc add dev $dev parent 1:1 handle 10: noqueue # ping -I $dev -w 1 -c 1 1.1.1.1

[ 2.172856] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 2.173217] #PF: supervisor instruction fetch in kernel mode ... [ 2.178451] Call Trace: [ 2.178577] <TASK> [ 2.178686] htb_enqueue+0x1c8/0x370 [ 2.178880] dev_qdisc_enqueue+0x15/0x90 [ 2.179093] __dev_queue_xmit+0x798/0xd00 [ 2.179305] ? _raw_write_lock_bh+0xe/0x30 [ 2.179522] ? __local_bh_enable_ip+0x32/0x70 [ 2.179759] ? ___neigh_create+0x610/0x840 [ 2.179968] ? eth_header+0x21/0xc0 [ 2.180144] ip_finish_output2+0x15e/0x4f0 [ 2.180348] ? dst_output+0x30/0x30 [ 2.180525] ip_push_pending_frames+0x9d/0xb0 [ 2.180739] raw_sendmsg+0x601/0xcb0 [ 2.180916] ? _raw_spin_trylock+0xe/0x50 [ 2.181112] ? _raw_spin_unlock_irqrestore+0x16/0x30 [ 2.181354] ? get_page_from_freelist+0xcd6/0xdf0 [ 2.181594] ? sock_sendmsg+0x56/0x60 [ 2.181781] sock_sendmsg+0x56/0x60 [ 2.181958] __sys_sendto+0xf7/0x160 [ 2.182139] ? handle_mm_fault+0x6e/0x1d0 [ 2.182366] ? do_user_addr_fault+0x1e1/0x660 [ 2.182627] __x64_sys_sendto+0x1b/0x30 [ 2.182881] do_syscall_64+0x38/0x90 [ 2.183085] entry_SYSCALL_64_after_hwframe+0x63/0xcd ... [ 2.187402] </TASK>

Previously in commit d66d6c3152e8 ("net: sched: register noqueue qdisc"), NULL was set for the noqueue discipline on noqueue init so that __dev_queue_xmit() falls through for the noqueue case. This also sets a bypass of the enqueue NULL check in the register_qdisc() function for the struct noqueue_disc_ops.

Classful queue disciplines make it past the NULL check in __dev_queue_xmit() because the discipline is set to htb (in this case), and then in the call to __dev_xmit_skb(), it calls into htb_enqueue() which grabs a leaf node for a class and then calls qdisc_enqueue() by passing in a queue discipline which assumes ->enqueue() is not set to NULL.

Fix this by not allowing classes to be assigned to the noqueue discipline. Linux TC Notes states that classes cannot be set to the noqueue discipline. [1] Let's enforce that here.

Links: 1. https://linux-tc-notes.sourceforge.net/tc/doc/sch_noqueue.txt

Fixes: d66d6c3152e8 ("net: sched: register noqueue qdisc") Cc: stable@vger.kernel.org Signed-off-by: Frederick Lawler fred@cloudflare.com Reviewed-by: Jakub Sitnicki jakub@cloudflare.com Link: https://lore.kernel.org/r/20230109163906.706000-1-fred@cloudflare.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_api.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1132,6 +1132,11 @@ skip: return -ENOENT; }

+ if (new && new->ops == &noqueue_qdisc_ops) { + NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); + return -EINVAL; + } + err = cops->graft(parent, cl, new, &old, extack); if (err) return err;