--- /dev/null
+From dd21bfa425c098b95ca86845f8e7d1ec1ddf6e4a Mon Sep 17 00:00:00 2001
+From: Yun Zhou <yun.zhou@windriver.com>
+Date: Fri, 4 Mar 2022 20:29:07 -0800
+Subject: proc: fix documentation and description of pagemap
+
+From: Yun Zhou <yun.zhou@windriver.com>
+
+commit dd21bfa425c098b95ca86845f8e7d1ec1ddf6e4a upstream.
+
+Since bit 57 was exported for uffd-wp write-protected (commit
+fb8e37f35a2f: "mm/pagemap: export uffd-wp protection information"),
+fixing it can reduce some unnecessary confusion.
+
+Link: https://lkml.kernel.org/r/20220301044538.3042713-1-yun.zhou@windriver.com
+Fixes: fb8e37f35a2fe1 ("mm/pagemap: export uffd-wp protection information")
+Signed-off-by: Yun Zhou <yun.zhou@windriver.com>
+Reviewed-by: Peter Xu <peterx@redhat.com>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Tiberiu A Georgescu <tiberiu.georgescu@nutanix.com>
+Cc: Florian Schmidt <florian.schmidt@nutanix.com>
+Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com>
+Cc: SeongJae Park <sj@kernel.org>
+Cc: Yang Shi <shy828301@gmail.com>
+Cc: David Hildenbrand <david@redhat.com>
+Cc: Axel Rasmussen <axelrasmussen@google.com>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Andrea Arcangeli <aarcange@redhat.com>
+Cc: Colin Cross <ccross@google.com>
+Cc: Alistair Popple <apopple@nvidia.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ Documentation/admin-guide/mm/pagemap.rst | 2 +-
+ fs/proc/task_mmu.c | 3 ++-
+ 2 files changed, 3 insertions(+), 2 deletions(-)
+
+--- a/Documentation/admin-guide/mm/pagemap.rst
++++ b/Documentation/admin-guide/mm/pagemap.rst
+@@ -23,7 +23,7 @@ There are four components to pagemap:
+ * Bit 56 page exclusively mapped (since 4.2)
+ * Bit 57 pte is uffd-wp write-protected (since 5.13) (see
+ :ref:`Documentation/admin-guide/mm/userfaultfd.rst <userfaultfd>`)
+- * Bits 57-60 zero
++ * Bits 58-60 zero
+ * Bit 61 page is file-page or shared-anon (since 3.5)
+ * Bit 62 page swapped
+ * Bit 63 page present
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -1586,7 +1586,8 @@ static const struct mm_walk_ops pagemap_
+ * Bits 5-54 swap offset if swapped
+ * Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst)
+ * Bit 56 page exclusively mapped
+- * Bits 57-60 zero
++ * Bit 57 pte is uffd-wp write-protected
++ * Bits 58-60 zero
+ * Bit 61 page is file-page or shared-anon
+ * Bit 62 page swapped
+ * Bit 63 page present
--- /dev/null
+From a6d95c5a628a09be129f25d5663a7e9db8261f51 Mon Sep 17 00:00:00 2001
+From: Jiri Bohac <jbohac@suse.cz>
+Date: Wed, 26 Jan 2022 16:00:18 +0100
+Subject: Revert "xfrm: xfrm_state_mtu should return at least 1280 for ipv6"
+
+From: Jiri Bohac <jbohac@suse.cz>
+
+commit a6d95c5a628a09be129f25d5663a7e9db8261f51 upstream.
+
+This reverts commit b515d2637276a3810d6595e10ab02c13bfd0b63a.
+
+Commit b515d2637276a3810d6595e10ab02c13bfd0b63a ("xfrm: xfrm_state_mtu
+should return at least 1280 for ipv6") in v5.14 breaks the TCP MSS
+calculation in ipsec transport mode, resulting complete stalls of TCP
+connections. This happens when the (P)MTU is 1280 or slighly larger.
+
+The desired formula for the MSS is:
+MSS = (MTU - ESP_overhead) - IP header - TCP header
+
+However, the above commit clamps the (MTU - ESP_overhead) to a
+minimum of 1280, turning the formula into
+MSS = max(MTU - ESP overhead, 1280) - IP header - TCP header
+
+With the (P)MTU near 1280, the calculated MSS is too large and the
+resulting TCP packets never make it to the destination because they
+are over the actual PMTU.
+
+The above commit also causes suboptimal double fragmentation in
+xfrm tunnel mode, as described in
+https://lore.kernel.org/netdev/20210429202529.codhwpc7w6kbudug@dwarf.suse.cz/
+
+The original problem the above commit was trying to fix is now fixed
+by commit 6596a0229541270fb8d38d989f91b78838e5e9da ("xfrm: fix MTU
+regression").
+
+Signed-off-by: Jiri Bohac <jbohac@suse.cz>
+Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/xfrm.h | 1 -
+ net/ipv4/esp4.c | 2 +-
+ net/ipv6/esp6.c | 2 +-
+ net/xfrm/xfrm_state.c | 14 ++------------
+ 4 files changed, 4 insertions(+), 15 deletions(-)
+
+--- a/include/net/xfrm.h
++++ b/include/net/xfrm.h
+@@ -1567,7 +1567,6 @@ void xfrm_sad_getinfo(struct net *net, s
+ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
+ u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
+ int xfrm_init_replay(struct xfrm_state *x);
+-u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu);
+ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu);
+ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
+ int xfrm_init_state(struct xfrm_state *x);
+--- a/net/ipv4/esp4.c
++++ b/net/ipv4/esp4.c
+@@ -671,7 +671,7 @@ static int esp_output(struct xfrm_state
+ struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
+ u32 padto;
+
+- padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached));
++ padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
+ if (skb->len < padto)
+ esp.tfclen = padto - skb->len;
+ }
+--- a/net/ipv6/esp6.c
++++ b/net/ipv6/esp6.c
+@@ -708,7 +708,7 @@ static int esp6_output(struct xfrm_state
+ struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
+ u32 padto;
+
+- padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached));
++ padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
+ if (skb->len < padto)
+ esp.tfclen = padto - skb->len;
+ }
+--- a/net/xfrm/xfrm_state.c
++++ b/net/xfrm/xfrm_state.c
+@@ -2571,7 +2571,7 @@ void xfrm_state_delete_tunnel(struct xfr
+ }
+ EXPORT_SYMBOL(xfrm_state_delete_tunnel);
+
+-u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu)
++u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
+ {
+ const struct xfrm_type *type = READ_ONCE(x->type);
+ struct crypto_aead *aead;
+@@ -2602,17 +2602,7 @@ u32 __xfrm_state_mtu(struct xfrm_state *
+ return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
+ net_adj) & ~(blksize - 1)) + net_adj - 2;
+ }
+-EXPORT_SYMBOL_GPL(__xfrm_state_mtu);
+-
+-u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
+-{
+- mtu = __xfrm_state_mtu(x, mtu);
+-
+- if (x->props.family == AF_INET6 && mtu < IPV6_MIN_MTU)
+- return IPV6_MIN_MTU;
+-
+- return mtu;
+-}
++EXPORT_SYMBOL_GPL(xfrm_state_mtu);
+
+ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
+ {
--- /dev/null
+From 1389f17937a03fe4ec71b094e1aa6530a901963e Mon Sep 17 00:00:00 2001
+From: Heiko Carstens <hca@linux.ibm.com>
+Date: Tue, 22 Feb 2022 14:53:47 +0100
+Subject: s390/ftrace: fix arch_ftrace_get_regs implementation
+
+From: Heiko Carstens <hca@linux.ibm.com>
+
+commit 1389f17937a03fe4ec71b094e1aa6530a901963e upstream.
+
+arch_ftrace_get_regs is supposed to return a struct pt_regs pointer
+only if the pt_regs structure contains all register contents, which
+means it must have been populated when created via ftrace_regs_caller.
+
+If it was populated via ftrace_caller the contents are not complete
+(the psw mask part is missing), and therefore a NULL pointer needs be
+returned.
+
+The current code incorrectly always returns a struct pt_regs pointer.
+
+Fix this by adding another pt_regs flag which indicates if the
+contents are complete, and fix arch_ftrace_get_regs accordingly.
+
+Fixes: 894979689d3a ("s390/ftrace: provide separate ftrace_caller/ftrace_regs_caller implementations")
+Reported-by: Christophe Leroy <christophe.leroy@csgroup.eu>
+Reported-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
+Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
+Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
+Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
+Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/s390/include/asm/ftrace.h | 10 ++++++----
+ arch/s390/include/asm/ptrace.h | 2 ++
+ arch/s390/kernel/ftrace.c | 2 +-
+ arch/s390/kernel/mcount.S | 9 +++++++++
+ 4 files changed, 18 insertions(+), 5 deletions(-)
+
+--- a/arch/s390/include/asm/ftrace.h
++++ b/arch/s390/include/asm/ftrace.h
+@@ -47,15 +47,17 @@ struct ftrace_regs {
+
+ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs)
+ {
+- return &fregs->regs;
++ struct pt_regs *regs = &fregs->regs;
++
++ if (test_pt_regs_flag(regs, PIF_FTRACE_FULL_REGS))
++ return regs;
++ return NULL;
+ }
+
+ static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs,
+ unsigned long ip)
+ {
+- struct pt_regs *regs = arch_ftrace_get_regs(fregs);
+-
+- regs->psw.addr = ip;
++ fregs->regs.psw.addr = ip;
+ }
+
+ /*
+--- a/arch/s390/include/asm/ptrace.h
++++ b/arch/s390/include/asm/ptrace.h
+@@ -15,11 +15,13 @@
+ #define PIF_EXECVE_PGSTE_RESTART 1 /* restart execve for PGSTE binaries */
+ #define PIF_SYSCALL_RET_SET 2 /* return value was set via ptrace */
+ #define PIF_GUEST_FAULT 3 /* indicates program check in sie64a */
++#define PIF_FTRACE_FULL_REGS 4 /* all register contents valid (ftrace) */
+
+ #define _PIF_SYSCALL BIT(PIF_SYSCALL)
+ #define _PIF_EXECVE_PGSTE_RESTART BIT(PIF_EXECVE_PGSTE_RESTART)
+ #define _PIF_SYSCALL_RET_SET BIT(PIF_SYSCALL_RET_SET)
+ #define _PIF_GUEST_FAULT BIT(PIF_GUEST_FAULT)
++#define _PIF_FTRACE_FULL_REGS BIT(PIF_FTRACE_FULL_REGS)
+
+ #ifndef __ASSEMBLY__
+
+--- a/arch/s390/kernel/ftrace.c
++++ b/arch/s390/kernel/ftrace.c
+@@ -291,7 +291,7 @@ void kprobe_ftrace_handler(unsigned long
+
+ regs = ftrace_get_regs(fregs);
+ p = get_kprobe((kprobe_opcode_t *)ip);
+- if (unlikely(!p) || kprobe_disabled(p))
++ if (!regs || unlikely(!p) || kprobe_disabled(p))
+ goto out;
+
+ if (kprobe_running()) {
+--- a/arch/s390/kernel/mcount.S
++++ b/arch/s390/kernel/mcount.S
+@@ -27,6 +27,7 @@ ENDPROC(ftrace_stub)
+ #define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
+ #define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW)
+ #define STACK_PTREGS_ORIG_GPR2 (STACK_PTREGS + __PT_ORIG_GPR2)
++#define STACK_PTREGS_FLAGS (STACK_PTREGS + __PT_FLAGS)
+ #ifdef __PACK_STACK
+ /* allocate just enough for r14, r15 and backchain */
+ #define TRACED_FUNC_FRAME_SIZE 24
+@@ -57,6 +58,14 @@ ENDPROC(ftrace_stub)
+ .if \allregs == 1
+ stg %r14,(STACK_PTREGS_PSW)(%r15)
+ stosm (STACK_PTREGS_PSW)(%r15),0
++#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
++ mvghi STACK_PTREGS_FLAGS(%r15),_PIF_FTRACE_FULL_REGS
++#else
++ lghi %r14,_PIF_FTRACE_FULL_REGS
++ stg %r14,STACK_PTREGS_FLAGS(%r15)
++#endif
++ .else
++ xc STACK_PTREGS_FLAGS(8,%r15),STACK_PTREGS_FLAGS(%r15)
+ .endif
+
+ lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address
--- /dev/null
+From 9fa881f7e3c74ce6626d166bca9397e5d925937f Mon Sep 17 00:00:00 2001
+From: Heiko Carstens <hca@linux.ibm.com>
+Date: Wed, 23 Feb 2022 13:02:59 +0100
+Subject: s390/ftrace: fix ftrace_caller/ftrace_regs_caller generation
+
+From: Heiko Carstens <hca@linux.ibm.com>
+
+commit 9fa881f7e3c74ce6626d166bca9397e5d925937f upstream.
+
+ftrace_caller was used for both ftrace_caller and ftrace_regs_caller,
+which means that the target address of the hotpatch trampoline was
+never updated.
+
+With commit 894979689d3a ("s390/ftrace: provide separate
+ftrace_caller/ftrace_regs_caller implementations") a separate
+ftrace_regs_caller entry point was implemeted, however it was
+forgotten to implement the necessary changes for ftrace_modify_call
+and ftrace_make_call, where the branch target has to be modified
+accordingly.
+
+Therefore add the missing code now.
+
+Fixes: 894979689d3a ("s390/ftrace: provide separate ftrace_caller/ftrace_regs_caller implementations")
+Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
+Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
+Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
+Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/s390/kernel/ftrace.c | 35 +++++++++++++++++++++++++++++++++++
+ 1 file changed, 35 insertions(+)
+
+--- a/arch/s390/kernel/ftrace.c
++++ b/arch/s390/kernel/ftrace.c
+@@ -159,9 +159,38 @@ int ftrace_init_nop(struct module *mod,
+ return 0;
+ }
+
++static struct ftrace_hotpatch_trampoline *ftrace_get_trampoline(struct dyn_ftrace *rec)
++{
++ struct ftrace_hotpatch_trampoline *trampoline;
++ struct ftrace_insn insn;
++ s64 disp;
++ u16 opc;
++
++ if (copy_from_kernel_nofault(&insn, (void *)rec->ip, sizeof(insn)))
++ return ERR_PTR(-EFAULT);
++ disp = (s64)insn.disp * 2;
++ trampoline = (void *)(rec->ip + disp);
++ if (get_kernel_nofault(opc, &trampoline->brasl_opc))
++ return ERR_PTR(-EFAULT);
++ if (opc != 0xc015)
++ return ERR_PTR(-EINVAL);
++ return trampoline;
++}
++
+ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+ {
++ struct ftrace_hotpatch_trampoline *trampoline;
++ u64 old;
++
++ trampoline = ftrace_get_trampoline(rec);
++ if (IS_ERR(trampoline))
++ return PTR_ERR(trampoline);
++ if (get_kernel_nofault(old, &trampoline->interceptor))
++ return -EFAULT;
++ if (old != old_addr)
++ return -EINVAL;
++ s390_kernel_write(&trampoline->interceptor, &addr, sizeof(addr));
+ return 0;
+ }
+
+@@ -188,6 +217,12 @@ static void brcl_enable(void *brcl)
+
+ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+ {
++ struct ftrace_hotpatch_trampoline *trampoline;
++
++ trampoline = ftrace_get_trampoline(rec);
++ if (IS_ERR(trampoline))
++ return PTR_ERR(trampoline);
++ s390_kernel_write(&trampoline->interceptor, &addr, sizeof(addr));
+ brcl_enable((void *)rec->ip);
+ return 0;
+ }
btrfs-add-missing-run-of-delayed-items-after-unlink-during-log-replay.patch
btrfs-fallback-to-blocking-mode-when-doing-async-dio-over-multiple-extents.patch
btrfs-do-not-start-relocation-until-in-progress-drops-are-done.patch
+revert-xfrm-xfrm_state_mtu-should-return-at-least-1280-for-ipv6.patch
+proc-fix-documentation-and-description-of-pagemap.patch
+x86-kvmclock-fix-hyper-v-isolated-vm-s-boot-issue-when-vcpus-64.patch
+s390-ftrace-fix-arch_ftrace_get_regs-implementation.patch
+s390-ftrace-fix-ftrace_caller-ftrace_regs_caller-generation.patch
--- /dev/null
+From 92e68cc558774de01024c18e8b35cdce4731c910 Mon Sep 17 00:00:00 2001
+From: Dexuan Cui <decui@microsoft.com>
+Date: Fri, 25 Feb 2022 00:46:00 -0800
+Subject: x86/kvmclock: Fix Hyper-V Isolated VM's boot issue when vCPUs > 64
+
+From: Dexuan Cui <decui@microsoft.com>
+
+commit 92e68cc558774de01024c18e8b35cdce4731c910 upstream.
+
+When Linux runs as an Isolated VM on Hyper-V, it supports AMD SEV-SNP
+but it's partially enlightened, i.e. cc_platform_has(
+CC_ATTR_GUEST_MEM_ENCRYPT) is true but sev_active() is false.
+
+Commit 4d96f9109109 per se is good, but with it now
+kvm_setup_vsyscall_timeinfo() -> kvmclock_init_mem() calls
+set_memory_decrypted(), and later gets stuck when trying to zere out
+the pages pointed by 'hvclock_mem', if Linux runs as an Isolated VM on
+Hyper-V. The cause is that here now the Linux VM should no longer access
+the original guest physical addrss (GPA); instead the VM should do
+memremap() and access the original GPA + ms_hyperv.shared_gpa_boundary:
+see the example code in drivers/hv/connection.c: vmbus_connect() or
+drivers/hv/ring_buffer.c: hv_ringbuffer_init(). If the VM tries to
+access the original GPA, it keepts getting injected a fault by Hyper-V
+and gets stuck there.
+
+Here the issue happens only when the VM has >=65 vCPUs, because the
+global static array hv_clock_boot[] can hold 64 "struct
+pvclock_vsyscall_time_info" (the sizeof of the struct is 64 bytes), so
+kvmclock_init_mem() only allocates memory in the case of vCPUs > 64.
+
+Since the 'hvclock_mem' pages are only useful when the kvm clock is
+supported by the underlying hypervisor, fix the issue by returning
+early when Linux VM runs on Hyper-V, which doesn't support kvm clock.
+
+Fixes: 4d96f9109109 ("x86/sev: Replace occurrences of sev_active() with cc_platform_has()")
+Tested-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
+Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
+Signed-off-by: Dexuan Cui <decui@microsoft.com>
+Message-Id: <20220225084600.17817-1-decui@microsoft.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/x86/kernel/kvmclock.c | 3 +++
+ 1 file changed, 3 insertions(+)
+
+--- a/arch/x86/kernel/kvmclock.c
++++ b/arch/x86/kernel/kvmclock.c
+@@ -239,6 +239,9 @@ static void __init kvmclock_init_mem(voi
+
+ static int __init kvm_setup_vsyscall_timeinfo(void)
+ {
++ if (!kvm_para_available())
++ return 0;
++
+ kvmclock_init_mem();
+
+ #ifdef CONFIG_X86_64
projects / thirdparty / kernel / stable-queue.git / commitdiff
