6.1.6-rc1 review

@@ -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

@@ -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);
+}

@@ -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

@@ -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);

@@ -396,7 +396,7 @@ static bool __fpu_restore_sig(void __use
 
 	fpregs = &fpu->fpstate->regs;
 	if (use_xsave() && !fx_only) {
-		if (copy_sigframe_from_user_to_xstate(fpu->fpstate, buf_fx))
+		if (copy_sigframe_from_user_to_xstate(tsk, buf_fx))
 			return false;
 	} else {
 		if (__copy_from_user(&fpregs->fxsave, buf_fx,

@@ -1278,10 +1278,10 @@ int copy_uabi_from_kernel_to_xstate(stru
  * XSAVE[S] format and copy to the target thread. This is called from the
  * sigreturn() and rt_sigreturn() system calls.
  */
-int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate,
+int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
 				      const void __user *ubuf)
 {
-	return copy_uabi_to_xstate(fpstate, NULL, ubuf);
+	return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf);
 }
 
 static bool validate_independent_components(u64 mask)

@@ -47,7 +47,7 @@ extern void __copy_xstate_to_uabi_buf(st
 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_sigframe_from_user_to_xstate(struct fpstate *fpstate, const void __user *ubuf);
+extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf);
 
 
 extern void fpu__init_cpu_xstate(void);

@@ -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;
 

@@ -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);

@@ -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);
 }

@@ -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);
 
 

@@ -1200,8 +1200,18 @@ static int copy_from_buffer(void *dst, u
 }
 
 
+/**
+ * copy_uabi_to_xstate - Copy a UABI format buffer to the kernel xstate
+ * @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
+ *
+ * Converts from the UABI format into the kernel internal hardware
+ * dependent format.
+ */
 static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
-			       const void __user *ubuf)
+			       const void __user *ubuf, u32 *pkru)
 {
 	struct xregs_state *xsave = &fpstate->regs.xsave;
 	unsigned int offset, size;

@@ -1270,7 +1280,7 @@ static int copy_uabi_to_xstate(struct fp
  */
 int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru)
 {
-	return copy_uabi_to_xstate(fpstate, kbuf, NULL);
+	return copy_uabi_to_xstate(fpstate, kbuf, NULL, pkru);
 }
 
 /*

@@ -1281,7 +1291,7 @@ int copy_uabi_from_kernel_to_xstate(stru
 int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
 				      const void __user *ubuf)
 {
-	return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf);
+	return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
 }
 
 static bool validate_independent_components(u64 mask)

@@ -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 */

@@ -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':

@@ -404,6 +404,14 @@ int fpu_copy_uabi_to_guest_fpstate(struc
 	if (ustate->xsave.header.xfeatures & ~xcr0)
 		return -EINVAL;
 
+	/*
+	 * Nullify @vpkru to preserve its current value if PKRU's bit isn't set
+	 * in the header.  KVM's odd ABI is to leave PKRU untouched in this
+	 * case (all other components are eventually re-initialized).
+	 */
+	if (!(ustate->xsave.header.xfeatures & XFEATURE_MASK_PKRU))
+		vpkru = NULL;
+
 	return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru);
 }
 EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);

@@ -1219,8 +1219,14 @@ static int copy_from_buffer(void *dst, u
  *	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.
+ *	The kernel will restore it manually, so the XRSTOR behavior that resets
+ *	the PKRU register to the hardware init value (0) if the corresponding
+ *	xfeatures bit is not set is emulated here.
  * 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.
+ *	pkru field. A pointer to that is passed in @pkru. KVM hasn't used
+ *	XRSTOR and hasn't had the PKRU resetting behavior described above. To
+ *	preserve that KVM behavior, it passes NULL for @pkru if the xfeatures
+ *	bit is not set.
  */
 static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
 			       const void __user *ubuf, u32 *pkru)

@@ -1277,6 +1283,13 @@ static int copy_uabi_to_xstate(struct fp
 
 		xpkru = __raw_xsave_addr(xsave, XFEATURE_PKRU);
 		*pkru = xpkru->pkru;
+	} else {
+		/*
+		 * KVM may pass NULL here to indicate that it does not need
+		 * PKRU updated.
+		 */
+		if (pkru)
+			*pkru = 0;
 	}
 
 	/*

@@ -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;

153 lines not on this page · raw message

@@ -928,7 +928,7 @@ nfsd4_read(struct svc_rqst *rqstp, struc
 	 * the client wants us to do more in this compound:
 	 */
 	if (!nfsd4_last_compound_op(rqstp))
-		__clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+		clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	/* check stateid */
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,

@@ -2615,12 +2615,11 @@ nfsd4_proc_compound(struct svc_rqst *rqs
 	cstate->minorversion = args->minorversion;
 	fh_init(current_fh, NFS4_FHSIZE);
 	fh_init(save_fh, NFS4_FHSIZE);
-
 	/*
 	 * Don't use the deferral mechanism for NFSv4; compounds make it
 	 * too hard to avoid non-idempotency problems.
 	 */
-	__clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+	clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 
 	/*
 	 * According to RFC3010, this takes precedence over all other errors.

@@ -2742,7 +2741,7 @@ encode_op:
 out:
 	cstate->status = status;
 	/* Reset deferral mechanism for RPC deferrals */
-	__set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 	return rpc_success;
 }
 

@@ -2464,7 +2464,7 @@ nfsd4_decode_compound(struct nfsd4_compo
 	argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
 
 	if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
-		__clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
+		clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
 
 	return true;
 }

@@ -900,7 +900,7 @@ unwrap_integ_data(struct svc_rqst *rqstp
 	 * rejecting the server-computed MIC in this somewhat rare case,
 	 * do not use splice with the GSS integrity service.
 	 */
-	__clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	/* Did we already verify the signature on the original pass through? */
 	if (rqstp->rq_deferred)

@@ -972,7 +972,7 @@ unwrap_priv_data(struct svc_rqst *rqstp,
 	int pad, remaining_len, offset;
 	u32 rseqno;
 
-	__clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 
 	priv_len = svc_getnl(&buf->head[0]);
 	if (rqstp->rq_deferred) {

@@ -1244,10 +1244,10 @@ svc_process_common(struct svc_rqst *rqst
 		goto err_short_len;
 
 	/* Will be turned off by GSS integrity and privacy services */
-	__set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+	set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 	/* Will be turned off only when NFSv4 Sessions are used */
-	__set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
-	__clear_bit(RQ_DROPME, &rqstp->rq_flags);
+	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+	clear_bit(RQ_DROPME, &rqstp->rq_flags);
 
 	svc_putu32(resv, rqstp->rq_xid);
 

@@ -1238,7 +1238,7 @@ static struct cache_deferred_req *svc_de
 	trace_svc_defer(rqstp);
 	svc_xprt_get(rqstp->rq_xprt);
 	dr->xprt = rqstp->rq_xprt;
-	__set_bit(RQ_DROPME, &rqstp->rq_flags);
+	set_bit(RQ_DROPME, &rqstp->rq_flags);
 
 	dr->handle.revisit = svc_revisit;
 	return &dr->handle;

@@ -298,9 +298,9 @@ static void svc_sock_setbufsize(struct s
 static void svc_sock_secure_port(struct svc_rqst *rqstp)
 {
 	if (svc_port_is_privileged(svc_addr(rqstp)))
-		__set_bit(RQ_SECURE, &rqstp->rq_flags);
+		set_bit(RQ_SECURE, &rqstp->rq_flags);
 	else
-		__clear_bit(RQ_SECURE, &rqstp->rq_flags);
+		clear_bit(RQ_SECURE, &rqstp->rq_flags);
 }
 
 /*

@@ -1008,9 +1008,9 @@ static int svc_tcp_recvfrom(struct svc_r
 	rqstp->rq_xprt_ctxt   = NULL;
 	rqstp->rq_prot	      = IPPROTO_TCP;
 	if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags))
-		__set_bit(RQ_LOCAL, &rqstp->rq_flags);
+		set_bit(RQ_LOCAL, &rqstp->rq_flags);
 	else
-		__clear_bit(RQ_LOCAL, &rqstp->rq_flags);
+		clear_bit(RQ_LOCAL, &rqstp->rq_flags);
 
 	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
 	calldir = p[1];

@@ -602,7 +602,7 @@ static int svc_rdma_has_wspace(struct sv
 
 static void svc_rdma_secure_port(struct svc_rqst *rqstp)
 {
-	__set_bit(RQ_SECURE, &rqstp->rq_flags);
+	set_bit(RQ_SECURE, &rqstp->rq_flags);
 }
 
 static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt)

@@ -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;