January 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] mptcp: don't always assume copied data in" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 551844f26da2a9f76c0a698baaffa631d1178645 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010605-obscurity-buckshot-fc5f@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 551844f26da2a9f76c0a698baaffa631d1178645 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Mon, 30 Dec 2024 19:12:31 +0100 Subject: [PATCH] mptcp: don't always assume copied data in mptcp_cleanup_rbuf() Under some corner cases the MPTCP protocol can end-up invoking mptcp_cleanup_rbuf() when no data has been copied, but such helper assumes the opposite condition. Explicitly drop such assumption and performs the costly call only when strictly needed - before releasing the msk socket lock. Fixes: fd8976790a6c ("mptcp: be careful on MPTCP-level ack.") Cc: stable(a)vger.kernel.org Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Link: https://patch.msgid.link/20241230-net-mptcp-rbuf-fixes-v1-2-8608af434ceb@ke… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 27afdb7e2071..5307fff9d995 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -528,13 +528,13 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } -static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) - tcp_cleanup_rbuf(ssk, 1); + tcp_cleanup_rbuf(ssk, copied); unlock_sock_fast(ssk, slow); } @@ -551,7 +551,7 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } -static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) +static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; @@ -559,14 +559,14 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) int space = __mptcp_space(sk); bool cleanup, rx_empty; - cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !__mptcp_rmem(sk); + cleanup = (space > 0) && (space >= (old_space << 1)) && copied; + rx_empty = !__mptcp_rmem(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) - mptcp_subflow_cleanup_rbuf(ssk); + mptcp_subflow_cleanup_rbuf(ssk, copied); } } @@ -2220,9 +2220,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, copied += bytes_read; - /* be sure to advertise window change */ - mptcp_cleanup_rbuf(msk); - if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; @@ -2271,6 +2268,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } pr_debug("block timeout %ld\n", timeo); + mptcp_cleanup_rbuf(msk, copied); err = sk_wait_data(sk, &timeo, NULL); if (err < 0) { err = copied ? : err; @@ -2278,6 +2276,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } + mptcp_cleanup_rbuf(msk, copied); + out_err: if (cmsg_flags && copied >= 0) { if (cmsg_flags & MPTCP_CMSG_TS)

2 days, 16 hours

1
0
0 0

FAILED: patch "[PATCH] mptcp: fix TCP options overflow." failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x cbb26f7d8451fe56ccac802c6db48d16240feebd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010636-stereo-friend-8023@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From cbb26f7d8451fe56ccac802c6db48d16240feebd Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Sat, 21 Dec 2024 09:51:46 +0100 Subject: [PATCH] mptcp: fix TCP options overflow. Syzbot reported the following splat: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 1 UID: 0 PID: 5836 Comm: sshd Not tainted 6.13.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/25/2024 RIP: 0010:_compound_head include/linux/page-flags.h:242 [inline] RIP: 0010:put_page+0x23/0x260 include/linux/mm.h:1552 Code: 90 90 90 90 90 90 90 55 41 57 41 56 53 49 89 fe 48 bd 00 00 00 00 00 fc ff df e8 f8 5e 12 f8 49 8d 5e 08 48 89 d8 48 c1 e8 03 <80> 3c 28 00 74 08 48 89 df e8 8f c7 78 f8 48 8b 1b 48 89 de 48 83 RSP: 0000:ffffc90003916c90 EFLAGS: 00010202 RAX: 0000000000000001 RBX: 0000000000000008 RCX: ffff888030458000 RDX: 0000000000000100 RSI: 0000000000000000 RDI: 0000000000000000 RBP: dffffc0000000000 R08: ffffffff898ca81d R09: 1ffff110054414ac R10: dffffc0000000000 R11: ffffed10054414ad R12: 0000000000000007 R13: ffff88802a20a542 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f34f496e800(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f9d6ec9ec28 CR3: 000000004d260000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> skb_page_unref include/linux/skbuff_ref.h:43 [inline] __skb_frag_unref include/linux/skbuff_ref.h:56 [inline] skb_release_data+0x483/0x8a0 net/core/skbuff.c:1119 skb_release_all net/core/skbuff.c:1190 [inline] __kfree_skb+0x55/0x70 net/core/skbuff.c:1204 tcp_clean_rtx_queue net/ipv4/tcp_input.c:3436 [inline] tcp_ack+0x2442/0x6bc0 net/ipv4/tcp_input.c:4032 tcp_rcv_state_process+0x8eb/0x44e0 net/ipv4/tcp_input.c:6805 tcp_v4_do_rcv+0x77d/0xc70 net/ipv4/tcp_ipv4.c:1939 tcp_v4_rcv+0x2dc0/0x37f0 net/ipv4/tcp_ipv4.c:2351 ip_protocol_deliver_rcu+0x22e/0x440 net/ipv4/ip_input.c:205 ip_local_deliver_finish+0x341/0x5f0 net/ipv4/ip_input.c:233 NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314 NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314 __netif_receive_skb_one_core net/core/dev.c:5672 [inline] __netif_receive_skb+0x2bf/0x650 net/core/dev.c:5785 process_backlog+0x662/0x15b0 net/core/dev.c:6117 __napi_poll+0xcb/0x490 net/core/dev.c:6883 napi_poll net/core/dev.c:6952 [inline] net_rx_action+0x89b/0x1240 net/core/dev.c:7074 handle_softirqs+0x2d4/0x9b0 kernel/softirq.c:561 __do_softirq kernel/softirq.c:595 [inline] invoke_softirq kernel/softirq.c:435 [inline] __irq_exit_rcu+0xf7/0x220 kernel/softirq.c:662 irq_exit_rcu+0x9/0x30 kernel/softirq.c:678 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1049 [inline] sysvec_apic_timer_interrupt+0x57/0xc0 arch/x86/kernel/apic/apic.c:1049 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702 RIP: 0033:0x7f34f4519ad5 Code: 85 d2 74 0d 0f 10 02 48 8d 54 24 20 0f 11 44 24 20 64 8b 04 25 18 00 00 00 85 c0 75 27 41 b8 08 00 00 00 b8 0f 01 00 00 0f 05 <48> 3d 00 f0 ff ff 76 75 48 8b 15 24 73 0d 00 f7 d8 64 89 02 48 83 RSP: 002b:00007ffec5b32ce0 EFLAGS: 00000246 RAX: 0000000000000001 RBX: 00000000000668a0 RCX: 00007f34f4519ad5 RDX: 00007ffec5b32d00 RSI: 0000000000000004 RDI: 0000564f4bc6cae0 RBP: 0000564f4bc6b5a0 R08: 0000000000000008 R09: 0000000000000000 R10: 00007ffec5b32de8 R11: 0000000000000246 R12: 0000564f48ea8aa4 R13: 0000000000000001 R14: 0000564f48ea93e8 R15: 00007ffec5b32d68 </TASK> Eric noted a probable shinfo->nr_frags corruption, which indeed occurs. The root cause is a buggy MPTCP option len computation in some circumstances: the ADD_ADDR option should be mutually exclusive with DSS since the blamed commit. Still, mptcp_established_options_add_addr() tries to set the relevant info in mptcp_out_options, if the remaining space is large enough even when DSS is present. Since the ADD_ADDR infos and the DSS share the same union fields, adding first corrupts the latter. In the worst-case scenario, such corruption increases the DSS binary layout, exceeding the computed length and possibly overwriting the skb shared info. Address the issue by enforcing mutual exclusion in mptcp_established_options_add_addr(), too. Cc: stable(a)vger.kernel.org Reported-by: syzbot+38a095a81f30d82884c1(a)syzkaller.appspotmail.com Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/538 Fixes: 1bff1e43a30e ("mptcp: optimize out option generation") Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://patch.msgid.link/025d9df8cde3c9a557befc47e9bc08fbbe3476e5.173477104… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1603b3702e22..a62bc874bf1e 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -667,8 +667,15 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * &echo, &drop_other_suboptions)) return false; + /* + * Later on, mptcp_write_options() will enforce mutually exclusion with + * DSS, bail out if such option is set and we can't drop it. + */ if (drop_other_suboptions) remaining += opt_size; + else if (opts->suboptions & OPTION_MPTCP_DSS) + return false; + len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); if (remaining < len) return false;

2 days, 16 hours

1
0
0 0

[PATCH v2] arm64: Filter out SVE hwcaps when FEAT_SVE isn't implemented

by Marc Zyngier

The hwcaps code that exposes SVE features to userspace only considers ID_AA64ZFR0_EL1, while this is only valid when ID_AA64PFR0_EL1.SVE advertises that SVE is actually supported. The expectations are that when ID_AA64PFR0_EL1.SVE is 0, the ID_AA64ZFR0_EL1 register is also 0. So far, so good. Things become a bit more interesting if the HW implements SME. In this case, a few ID_AA64ZFR0_EL1 fields indicate *SME* features. And these fields overlap with their SVE interpretations. But the architecture says that the SME and SVE feature sets must match, so we're still hunky-dory. This goes wrong if the HW implements SME, but not SVE. In this case, we end-up advertising some SVE features to userspace, even if the HW has none. That's because we never consider whether SVE is actually implemented. Oh well. Fix it by restricting all SVE capabilities to ID_AA64PFR0_EL1.SVE being non-zero. Fixes: 06a916feca2b ("arm64: Expose SVE2 features for userspace") Reported-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Marc Zyngier <maz(a)kernel.org> Cc: Will Deacon <will(a)kernel.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mark Brown <broonie(a)kernel.org> Cc: stable(a)vger.kernel.org --- arch/arm64/kernel/cpufeature.c | 40 +++++++++++++++++++++++----------- 1 file changed, 27 insertions(+), 13 deletions(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6ce71f444ed84..6874aca5da9df 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -3022,6 +3022,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = match, \ } +#define HWCAP_CAP_MATCH_ID(match, reg, field, min_value, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + HWCAP_CPUID_MATCH(reg, field, min_value) \ + .matches = match, \ + } + #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { @@ -3050,6 +3057,13 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { }; #endif +#ifdef CONFIG_ARM64_SVE +static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope) +{ + return system_supports_sve() && has_user_cpuid_feature(cap, scope); +} +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), @@ -3092,19 +3106,19 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), - HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), - HWCAP_CAP(ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), - HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), - HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), #endif #ifdef CONFIG_ARM64_GCS HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS), -- 2.39.2

2 days, 16 hours

3
5
0 0

FAILED: patch "[PATCH] mm: reinstate ability to map write-sealed memfd mappings" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 8ec396d05d1b737c87311fb7311f753b02c2a6b1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010652-resemble-faceplate-702c@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8ec396d05d1b737c87311fb7311f753b02c2a6b1 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Date: Thu, 28 Nov 2024 15:06:17 +0000 Subject: [PATCH] mm: reinstate ability to map write-sealed memfd mappings read-only Patch series "mm: reinstate ability to map write-sealed memfd mappings read-only". In commit 158978945f31 ("mm: perform the mapping_map_writable() check after call_mmap()") (and preceding changes in the same series) it became possible to mmap() F_SEAL_WRITE sealed memfd mappings read-only. Commit 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") unintentionally undid this logic by moving the mapping_map_writable() check before the shmem_mmap() hook is invoked, thereby regressing this change. This series reworks how we both permit write-sealed mappings being mapped read-only and disallow mprotect() from undoing the write-seal, fixing this regression. We also add a regression test to ensure that we do not accidentally regress this in future. Thanks to Julian Orth for reporting this regression. This patch (of 2): In commit 158978945f31 ("mm: perform the mapping_map_writable() check after call_mmap()") (and preceding changes in the same series) it became possible to mmap() F_SEAL_WRITE sealed memfd mappings read-only. This was previously unnecessarily disallowed, despite the man page documentation indicating that it would be, thereby limiting the usefulness of F_SEAL_WRITE logic. We fixed this by adapting logic that existed for the F_SEAL_FUTURE_WRITE seal (one which disallows future writes to the memfd) to also be used for F_SEAL_WRITE. For background - the F_SEAL_FUTURE_WRITE seal clears VM_MAYWRITE for a read-only mapping to disallow mprotect() from overriding the seal - an operation performed by seal_check_write(), invoked from shmem_mmap(), the f_op->mmap() hook used by shmem mappings. By extending this to F_SEAL_WRITE and critically - checking mapping_map_writable() to determine if we may map the memfd AFTER we invoke shmem_mmap() - the desired logic becomes possible. This is because mapping_map_writable() explicitly checks for VM_MAYWRITE, which we will have cleared. Commit 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") unintentionally undid this logic by moving the mapping_map_writable() check before the shmem_mmap() hook is invoked, thereby regressing this change. We reinstate this functionality by moving the check out of shmem_mmap() and instead performing it in do_mmap() at the point at which VMA flags are being determined, which seems in any case to be a more appropriate place in which to make this determination. In order to achieve this we rework memfd seal logic to allow us access to this information using existing logic and eliminate the clearing of VM_MAYWRITE from seal_check_write() which we are performing in do_mmap() instead. Link: https://lkml.kernel.org/r/99fc35d2c62bd2e05571cf60d9f8b843c56069e0.17328047… Fixes: 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reported-by: Julian Orth <ju.orth(a)gmail.com> Closes: https://lore.kernel.org/all/CAHijbEUMhvJTN9Xw1GmbM266FXXv=U7s4L_Jem5x3AaPZx… Cc: Jann Horn <jannh(a)google.com> Cc: Liam R. Howlett <Liam.Howlett(a)Oracle.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 3f2cf339ceaf..d437e3070850 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -7,6 +7,7 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); +unsigned int *memfd_file_seals_ptr(struct file *file); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { return ERR_PTR(-EINVAL); } + +static inline unsigned int *memfd_file_seals_ptr(struct file *file) +{ + return NULL; +} #endif +/* Retrieve memfd seals associated with the file, if any. */ +static inline unsigned int memfd_file_seals(struct file *file) +{ + unsigned int *sealsp = memfd_file_seals_ptr(file); + + return sealsp ? *sealsp : 0; +} + #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 338a76ce9083..fb397918c43d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4101,6 +4101,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +static inline bool is_write_sealed(int seals) +{ + return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); +} + +/** + * is_readonly_sealed - Checks whether write-sealed but mapped read-only, + * in which case writes should be disallowing moving + * forwards. + * @seals: the seals to check + * @vm_flags: the VMA flags to check + * + * Returns whether readonly sealed, in which case writess should be disallowed + * going forward. + */ +static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) +{ + /* + * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (is_write_sealed(seals) && + ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) + return true; + + return false; +} + /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. @@ -4112,24 +4143,15 @@ static inline void mem_dump_obj(void *object) {} */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; + if (!is_write_sealed(seals)) + return 0; - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * write seals are active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; return 0; } diff --git a/mm/memfd.c b/mm/memfd.c index c17c3ea701a1..35a370d75c9a 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -170,7 +170,7 @@ static int memfd_wait_for_pins(struct address_space *mapping) return error; } -static unsigned int *memfd_file_seals_ptr(struct file *file) +unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; diff --git a/mm/mmap.c b/mm/mmap.c index d32b7e701058..16f8e8be01f8 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -47,6 +47,7 @@ #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> +#include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -368,6 +369,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (file) { struct inode *inode = file_inode(file); + unsigned int seals = memfd_file_seals(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) @@ -408,6 +410,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); + else if (is_readonly_sealed(seals, vm_flags)) + vm_flags &= ~VM_MAYWRITE; fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ))

2 days, 16 hours

3
3
0 0

FAILED: patch "[PATCH] mm: hugetlb: independent PMD page table shared count" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 59d9094df3d79443937add8700b2ef1a866b1081 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010625-stopped-snowflake-603f@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 59d9094df3d79443937add8700b2ef1a866b1081 Mon Sep 17 00:00:00 2001 From: Liu Shixin <liushixin2(a)huawei.com> Date: Mon, 16 Dec 2024 15:11:47 +0800 Subject: [PATCH] mm: hugetlb: independent PMD page table shared count The folio refcount may be increased unexpectly through try_get_folio() by caller such as split_huge_pages. In huge_pmd_unshare(), we use refcount to check whether a pmd page table is shared. The check is incorrect if the refcount is increased by the above caller, and this can cause the page table leaked: BUG: Bad page state in process sh pfn:109324 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x66 pfn:0x109324 flags: 0x17ffff800000000(node=0|zone=2|lastcpupid=0xfffff) page_type: f2(table) raw: 017ffff800000000 0000000000000000 0000000000000000 0000000000000000 raw: 0000000000000066 0000000000000000 00000000f2000000 0000000000000000 page dumped because: nonzero mapcount ... CPU: 31 UID: 0 PID: 7515 Comm: sh Kdump: loaded Tainted: G B 6.13.0-rc2master+ #7 Tainted: [B]=BAD_PAGE Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 dump_stack+0x18/0x28 bad_page+0x8c/0x130 free_page_is_bad_report+0xa4/0xb0 free_unref_page+0x3cc/0x620 __folio_put+0xf4/0x158 split_huge_pages_all+0x1e0/0x3e8 split_huge_pages_write+0x25c/0x2d8 full_proxy_write+0x64/0xd8 vfs_write+0xcc/0x280 ksys_write+0x70/0x110 __arm64_sys_write+0x24/0x38 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0xc8/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x34/0x128 el0t_64_sync_handler+0xc8/0xd0 el0t_64_sync+0x190/0x198 The issue may be triggered by damon, offline_page, page_idle, etc, which will increase the refcount of page table. 1. The page table itself will be discarded after reporting the "nonzero mapcount". 2. The HugeTLB page mapped by the page table miss freeing since we treat the page table as shared and a shared page table will not be unmapped. Fix it by introducing independent PMD page table shared count. As described by comment, pt_index/pt_mm/pt_frag_refcount are used for s390 gmap, x86 pgds and powerpc, pt_share_count is used for x86/arm64/riscv pmds, so we can reuse the field as pt_share_count. Link: https://lkml.kernel.org/r/20241216071147.3984217-1-liushixin2@huawei.com Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Ken Chen <kenneth.w.chen(a)intel.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Nanyong Sun <sunnanyong(a)huawei.com> Cc: Jane Chu <jane.chu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/mm.h b/include/linux/mm.h index fb397918c43d..b1c3db9cf355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..332cee285662 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..c498874a7170 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7211,7 +7211,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7226,7 +7226,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7238,10 +7238,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7250,18 +7246,20 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; }

2 days, 17 hours

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: independent PMD page table shared count" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 59d9094df3d79443937add8700b2ef1a866b1081 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010623-platform-unmasked-77c7@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 59d9094df3d79443937add8700b2ef1a866b1081 Mon Sep 17 00:00:00 2001 From: Liu Shixin <liushixin2(a)huawei.com> Date: Mon, 16 Dec 2024 15:11:47 +0800 Subject: [PATCH] mm: hugetlb: independent PMD page table shared count The folio refcount may be increased unexpectly through try_get_folio() by caller such as split_huge_pages. In huge_pmd_unshare(), we use refcount to check whether a pmd page table is shared. The check is incorrect if the refcount is increased by the above caller, and this can cause the page table leaked: BUG: Bad page state in process sh pfn:109324 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x66 pfn:0x109324 flags: 0x17ffff800000000(node=0|zone=2|lastcpupid=0xfffff) page_type: f2(table) raw: 017ffff800000000 0000000000000000 0000000000000000 0000000000000000 raw: 0000000000000066 0000000000000000 00000000f2000000 0000000000000000 page dumped because: nonzero mapcount ... CPU: 31 UID: 0 PID: 7515 Comm: sh Kdump: loaded Tainted: G B 6.13.0-rc2master+ #7 Tainted: [B]=BAD_PAGE Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 dump_stack+0x18/0x28 bad_page+0x8c/0x130 free_page_is_bad_report+0xa4/0xb0 free_unref_page+0x3cc/0x620 __folio_put+0xf4/0x158 split_huge_pages_all+0x1e0/0x3e8 split_huge_pages_write+0x25c/0x2d8 full_proxy_write+0x64/0xd8 vfs_write+0xcc/0x280 ksys_write+0x70/0x110 __arm64_sys_write+0x24/0x38 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0xc8/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x34/0x128 el0t_64_sync_handler+0xc8/0xd0 el0t_64_sync+0x190/0x198 The issue may be triggered by damon, offline_page, page_idle, etc, which will increase the refcount of page table. 1. The page table itself will be discarded after reporting the "nonzero mapcount". 2. The HugeTLB page mapped by the page table miss freeing since we treat the page table as shared and a shared page table will not be unmapped. Fix it by introducing independent PMD page table shared count. As described by comment, pt_index/pt_mm/pt_frag_refcount are used for s390 gmap, x86 pgds and powerpc, pt_share_count is used for x86/arm64/riscv pmds, so we can reuse the field as pt_share_count. Link: https://lkml.kernel.org/r/20241216071147.3984217-1-liushixin2@huawei.com Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Ken Chen <kenneth.w.chen(a)intel.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Nanyong Sun <sunnanyong(a)huawei.com> Cc: Jane Chu <jane.chu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/mm.h b/include/linux/mm.h index fb397918c43d..b1c3db9cf355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..332cee285662 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..c498874a7170 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7211,7 +7211,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7226,7 +7226,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7238,10 +7238,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7250,18 +7246,20 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; }

2 days, 17 hours

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: independent PMD page table shared count" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 59d9094df3d79443937add8700b2ef1a866b1081 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010622-overflow-raffle-07fa@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 59d9094df3d79443937add8700b2ef1a866b1081 Mon Sep 17 00:00:00 2001 From: Liu Shixin <liushixin2(a)huawei.com> Date: Mon, 16 Dec 2024 15:11:47 +0800 Subject: [PATCH] mm: hugetlb: independent PMD page table shared count The folio refcount may be increased unexpectly through try_get_folio() by caller such as split_huge_pages. In huge_pmd_unshare(), we use refcount to check whether a pmd page table is shared. The check is incorrect if the refcount is increased by the above caller, and this can cause the page table leaked: BUG: Bad page state in process sh pfn:109324 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x66 pfn:0x109324 flags: 0x17ffff800000000(node=0|zone=2|lastcpupid=0xfffff) page_type: f2(table) raw: 017ffff800000000 0000000000000000 0000000000000000 0000000000000000 raw: 0000000000000066 0000000000000000 00000000f2000000 0000000000000000 page dumped because: nonzero mapcount ... CPU: 31 UID: 0 PID: 7515 Comm: sh Kdump: loaded Tainted: G B 6.13.0-rc2master+ #7 Tainted: [B]=BAD_PAGE Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 dump_stack+0x18/0x28 bad_page+0x8c/0x130 free_page_is_bad_report+0xa4/0xb0 free_unref_page+0x3cc/0x620 __folio_put+0xf4/0x158 split_huge_pages_all+0x1e0/0x3e8 split_huge_pages_write+0x25c/0x2d8 full_proxy_write+0x64/0xd8 vfs_write+0xcc/0x280 ksys_write+0x70/0x110 __arm64_sys_write+0x24/0x38 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0xc8/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x34/0x128 el0t_64_sync_handler+0xc8/0xd0 el0t_64_sync+0x190/0x198 The issue may be triggered by damon, offline_page, page_idle, etc, which will increase the refcount of page table. 1. The page table itself will be discarded after reporting the "nonzero mapcount". 2. The HugeTLB page mapped by the page table miss freeing since we treat the page table as shared and a shared page table will not be unmapped. Fix it by introducing independent PMD page table shared count. As described by comment, pt_index/pt_mm/pt_frag_refcount are used for s390 gmap, x86 pgds and powerpc, pt_share_count is used for x86/arm64/riscv pmds, so we can reuse the field as pt_share_count. Link: https://lkml.kernel.org/r/20241216071147.3984217-1-liushixin2@huawei.com Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Ken Chen <kenneth.w.chen(a)intel.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Nanyong Sun <sunnanyong(a)huawei.com> Cc: Jane Chu <jane.chu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/mm.h b/include/linux/mm.h index fb397918c43d..b1c3db9cf355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..332cee285662 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..c498874a7170 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7211,7 +7211,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7226,7 +7226,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7238,10 +7238,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7250,18 +7246,20 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; }

2 days, 17 hours

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: independent PMD page table shared count" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 59d9094df3d79443937add8700b2ef1a866b1081 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010621-candy-fall-1396@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 59d9094df3d79443937add8700b2ef1a866b1081 Mon Sep 17 00:00:00 2001 From: Liu Shixin <liushixin2(a)huawei.com> Date: Mon, 16 Dec 2024 15:11:47 +0800 Subject: [PATCH] mm: hugetlb: independent PMD page table shared count The folio refcount may be increased unexpectly through try_get_folio() by caller such as split_huge_pages. In huge_pmd_unshare(), we use refcount to check whether a pmd page table is shared. The check is incorrect if the refcount is increased by the above caller, and this can cause the page table leaked: BUG: Bad page state in process sh pfn:109324 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x66 pfn:0x109324 flags: 0x17ffff800000000(node=0|zone=2|lastcpupid=0xfffff) page_type: f2(table) raw: 017ffff800000000 0000000000000000 0000000000000000 0000000000000000 raw: 0000000000000066 0000000000000000 00000000f2000000 0000000000000000 page dumped because: nonzero mapcount ... CPU: 31 UID: 0 PID: 7515 Comm: sh Kdump: loaded Tainted: G B 6.13.0-rc2master+ #7 Tainted: [B]=BAD_PAGE Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 dump_stack+0x18/0x28 bad_page+0x8c/0x130 free_page_is_bad_report+0xa4/0xb0 free_unref_page+0x3cc/0x620 __folio_put+0xf4/0x158 split_huge_pages_all+0x1e0/0x3e8 split_huge_pages_write+0x25c/0x2d8 full_proxy_write+0x64/0xd8 vfs_write+0xcc/0x280 ksys_write+0x70/0x110 __arm64_sys_write+0x24/0x38 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0xc8/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x34/0x128 el0t_64_sync_handler+0xc8/0xd0 el0t_64_sync+0x190/0x198 The issue may be triggered by damon, offline_page, page_idle, etc, which will increase the refcount of page table. 1. The page table itself will be discarded after reporting the "nonzero mapcount". 2. The HugeTLB page mapped by the page table miss freeing since we treat the page table as shared and a shared page table will not be unmapped. Fix it by introducing independent PMD page table shared count. As described by comment, pt_index/pt_mm/pt_frag_refcount are used for s390 gmap, x86 pgds and powerpc, pt_share_count is used for x86/arm64/riscv pmds, so we can reuse the field as pt_share_count. Link: https://lkml.kernel.org/r/20241216071147.3984217-1-liushixin2@huawei.com Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Ken Chen <kenneth.w.chen(a)intel.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Nanyong Sun <sunnanyong(a)huawei.com> Cc: Jane Chu <jane.chu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/mm.h b/include/linux/mm.h index fb397918c43d..b1c3db9cf355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..332cee285662 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..c498874a7170 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7211,7 +7211,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7226,7 +7226,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7238,10 +7238,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7250,18 +7246,20 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; }

2 days, 17 hours

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: independent PMD page table shared count" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 59d9094df3d79443937add8700b2ef1a866b1081 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010620-lethargic-backspin-e75d@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 59d9094df3d79443937add8700b2ef1a866b1081 Mon Sep 17 00:00:00 2001 From: Liu Shixin <liushixin2(a)huawei.com> Date: Mon, 16 Dec 2024 15:11:47 +0800 Subject: [PATCH] mm: hugetlb: independent PMD page table shared count The folio refcount may be increased unexpectly through try_get_folio() by caller such as split_huge_pages. In huge_pmd_unshare(), we use refcount to check whether a pmd page table is shared. The check is incorrect if the refcount is increased by the above caller, and this can cause the page table leaked: BUG: Bad page state in process sh pfn:109324 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x66 pfn:0x109324 flags: 0x17ffff800000000(node=0|zone=2|lastcpupid=0xfffff) page_type: f2(table) raw: 017ffff800000000 0000000000000000 0000000000000000 0000000000000000 raw: 0000000000000066 0000000000000000 00000000f2000000 0000000000000000 page dumped because: nonzero mapcount ... CPU: 31 UID: 0 PID: 7515 Comm: sh Kdump: loaded Tainted: G B 6.13.0-rc2master+ #7 Tainted: [B]=BAD_PAGE Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 dump_stack+0x18/0x28 bad_page+0x8c/0x130 free_page_is_bad_report+0xa4/0xb0 free_unref_page+0x3cc/0x620 __folio_put+0xf4/0x158 split_huge_pages_all+0x1e0/0x3e8 split_huge_pages_write+0x25c/0x2d8 full_proxy_write+0x64/0xd8 vfs_write+0xcc/0x280 ksys_write+0x70/0x110 __arm64_sys_write+0x24/0x38 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0xc8/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x34/0x128 el0t_64_sync_handler+0xc8/0xd0 el0t_64_sync+0x190/0x198 The issue may be triggered by damon, offline_page, page_idle, etc, which will increase the refcount of page table. 1. The page table itself will be discarded after reporting the "nonzero mapcount". 2. The HugeTLB page mapped by the page table miss freeing since we treat the page table as shared and a shared page table will not be unmapped. Fix it by introducing independent PMD page table shared count. As described by comment, pt_index/pt_mm/pt_frag_refcount are used for s390 gmap, x86 pgds and powerpc, pt_share_count is used for x86/arm64/riscv pmds, so we can reuse the field as pt_share_count. Link: https://lkml.kernel.org/r/20241216071147.3984217-1-liushixin2@huawei.com Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Ken Chen <kenneth.w.chen(a)intel.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Nanyong Sun <sunnanyong(a)huawei.com> Cc: Jane Chu <jane.chu(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/mm.h b/include/linux/mm.h index fb397918c43d..b1c3db9cf355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..332cee285662 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..c498874a7170 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7211,7 +7211,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7226,7 +7226,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7238,10 +7238,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7250,18 +7246,20 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; }

2 days, 17 hours

1
0
0 0

FAILED: patch "[PATCH] mm: reinstate ability to map write-sealed memfd mappings" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 8ec396d05d1b737c87311fb7311f753b02c2a6b1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025010657-rental-seltzer-1a53@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8ec396d05d1b737c87311fb7311f753b02c2a6b1 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Date: Thu, 28 Nov 2024 15:06:17 +0000 Subject: [PATCH] mm: reinstate ability to map write-sealed memfd mappings read-only Patch series "mm: reinstate ability to map write-sealed memfd mappings read-only". In commit 158978945f31 ("mm: perform the mapping_map_writable() check after call_mmap()") (and preceding changes in the same series) it became possible to mmap() F_SEAL_WRITE sealed memfd mappings read-only. Commit 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") unintentionally undid this logic by moving the mapping_map_writable() check before the shmem_mmap() hook is invoked, thereby regressing this change. This series reworks how we both permit write-sealed mappings being mapped read-only and disallow mprotect() from undoing the write-seal, fixing this regression. We also add a regression test to ensure that we do not accidentally regress this in future. Thanks to Julian Orth for reporting this regression. This patch (of 2): In commit 158978945f31 ("mm: perform the mapping_map_writable() check after call_mmap()") (and preceding changes in the same series) it became possible to mmap() F_SEAL_WRITE sealed memfd mappings read-only. This was previously unnecessarily disallowed, despite the man page documentation indicating that it would be, thereby limiting the usefulness of F_SEAL_WRITE logic. We fixed this by adapting logic that existed for the F_SEAL_FUTURE_WRITE seal (one which disallows future writes to the memfd) to also be used for F_SEAL_WRITE. For background - the F_SEAL_FUTURE_WRITE seal clears VM_MAYWRITE for a read-only mapping to disallow mprotect() from overriding the seal - an operation performed by seal_check_write(), invoked from shmem_mmap(), the f_op->mmap() hook used by shmem mappings. By extending this to F_SEAL_WRITE and critically - checking mapping_map_writable() to determine if we may map the memfd AFTER we invoke shmem_mmap() - the desired logic becomes possible. This is because mapping_map_writable() explicitly checks for VM_MAYWRITE, which we will have cleared. Commit 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") unintentionally undid this logic by moving the mapping_map_writable() check before the shmem_mmap() hook is invoked, thereby regressing this change. We reinstate this functionality by moving the check out of shmem_mmap() and instead performing it in do_mmap() at the point at which VMA flags are being determined, which seems in any case to be a more appropriate place in which to make this determination. In order to achieve this we rework memfd seal logic to allow us access to this information using existing logic and eliminate the clearing of VM_MAYWRITE from seal_check_write() which we are performing in do_mmap() instead. Link: https://lkml.kernel.org/r/99fc35d2c62bd2e05571cf60d9f8b843c56069e0.17328047… Fixes: 5de195060b2e ("mm: resolve faulty mmap_region() error path behaviour") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reported-by: Julian Orth <ju.orth(a)gmail.com> Closes: https://lore.kernel.org/all/CAHijbEUMhvJTN9Xw1GmbM266FXXv=U7s4L_Jem5x3AaPZx… Cc: Jann Horn <jannh(a)google.com> Cc: Liam R. Howlett <Liam.Howlett(a)Oracle.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 3f2cf339ceaf..d437e3070850 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -7,6 +7,7 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); +unsigned int *memfd_file_seals_ptr(struct file *file); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { return ERR_PTR(-EINVAL); } + +static inline unsigned int *memfd_file_seals_ptr(struct file *file) +{ + return NULL; +} #endif +/* Retrieve memfd seals associated with the file, if any. */ +static inline unsigned int memfd_file_seals(struct file *file) +{ + unsigned int *sealsp = memfd_file_seals_ptr(file); + + return sealsp ? *sealsp : 0; +} + #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 338a76ce9083..fb397918c43d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4101,6 +4101,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +static inline bool is_write_sealed(int seals) +{ + return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); +} + +/** + * is_readonly_sealed - Checks whether write-sealed but mapped read-only, + * in which case writes should be disallowing moving + * forwards. + * @seals: the seals to check + * @vm_flags: the VMA flags to check + * + * Returns whether readonly sealed, in which case writess should be disallowed + * going forward. + */ +static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) +{ + /* + * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (is_write_sealed(seals) && + ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) + return true; + + return false; +} + /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. @@ -4112,24 +4143,15 @@ static inline void mem_dump_obj(void *object) {} */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; + if (!is_write_sealed(seals)) + return 0; - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * write seals are active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; return 0; } diff --git a/mm/memfd.c b/mm/memfd.c index c17c3ea701a1..35a370d75c9a 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -170,7 +170,7 @@ static int memfd_wait_for_pins(struct address_space *mapping) return error; } -static unsigned int *memfd_file_seals_ptr(struct file *file) +unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; diff --git a/mm/mmap.c b/mm/mmap.c index d32b7e701058..16f8e8be01f8 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -47,6 +47,7 @@ #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> +#include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -368,6 +369,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (file) { struct inode *inode = file_inode(file); + unsigned int seals = memfd_file_seals(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) @@ -408,6 +410,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); + else if (is_readonly_sealed(seals, vm_flags)) + vm_flags &= ~VM_MAYWRITE; fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ))

2 days, 17 hours

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2025