June 2021 - Linux-stable-mirror

[PATCH v2 2/2] f2fs: Advertise encrypted casefolding in sysfs

by Daniel Rosenberg

Older kernels don't support encryption with casefolding. This adds the sysfs entry encrypted_casefold to show support for those combined features. Support for this feature was originally added by commit 7ad08a58bf67 ("f2fs: Handle casefolding with Encryption") Fixes: 7ad08a58bf67 ("f2fs: Handle casefolding with Encryption") Cc: stable(a)vger.kernel.org # v5.11+ Signed-off-by: Daniel Rosenberg <drosen(a)google.com> --- fs/f2fs/sysfs.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 09e3f258eb52..6604291a3cdf 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -161,6 +161,9 @@ static ssize_t features_show(struct f2fs_attr *a, if (f2fs_sb_has_compression(sbi)) len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "compression"); + if (f2fs_sb_has_casefold(sbi) && f2fs_sb_has_encrypt(sbi)) + len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "encrypted_casefold"); len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "pin_file"); len += scnprintf(buf + len, PAGE_SIZE - len, "\n"); @@ -579,6 +582,7 @@ enum feat_id { FEAT_CASEFOLD, FEAT_COMPRESSION, FEAT_TEST_DUMMY_ENCRYPTION_V2, + FEAT_ENCRYPTED_CASEFOLD, }; static ssize_t f2fs_feature_show(struct f2fs_attr *a, @@ -600,6 +604,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, case FEAT_CASEFOLD: case FEAT_COMPRESSION: case FEAT_TEST_DUMMY_ENCRYPTION_V2: + case FEAT_ENCRYPTED_CASEFOLD: return sprintf(buf, "supported\n"); } return 0; @@ -704,7 +709,10 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks); #ifdef CONFIG_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2, FEAT_TEST_DUMMY_ENCRYPTION_V2); -#endif +#ifdef CONFIG_UNICODE +F2FS_FEATURE_RO_ATTR(encrypted_casefold, FEAT_ENCRYPTED_CASEFOLD); +#endif /* CONFIG_UNICODE */ +#endif /* CONFIG_FS_ENCRYPTION */ #ifdef CONFIG_BLK_DEV_ZONED F2FS_FEATURE_RO_ATTR(block_zoned, FEAT_BLKZONED); #endif @@ -815,7 +823,10 @@ static struct attribute *f2fs_feat_attrs[] = { #ifdef CONFIG_FS_ENCRYPTION ATTR_LIST(encryption), ATTR_LIST(test_dummy_encryption_v2), -#endif +#ifdef CONFIG_UNICODE + ATTR_LIST(encrypted_casefold), +#endif /* CONFIG_UNICODE */ +#endif /* CONFIG_FS_ENCRYPTION */ #ifdef CONFIG_BLK_DEV_ZONED ATTR_LIST(block_zoned), #endif -- 2.32.0.rc0.204.g9fa02ecfa5-goog

4 years, 1 month

8
19
0 0

[PATCH v2 1/2] f2fs: Show casefolding support only when supported

by Daniel Rosenberg

The casefolding feature is only supported when CONFIG_UNICODE is set. This modifies the feature list f2fs presents under sysfs accordingly. Fixes: 5aba54302a46 ("f2fs: include charset encoding information in the superblock") Cc: stable(a)vger.kernel.org # v5.4+ Signed-off-by: Daniel Rosenberg <drosen(a)google.com> --- fs/f2fs/sysfs.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index dc71bc968c72..09e3f258eb52 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -720,7 +720,9 @@ F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND); F2FS_FEATURE_RO_ATTR(verity, FEAT_VERITY); #endif F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM); +#ifdef CONFIG_UNICODE F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD); +#endif #ifdef CONFIG_F2FS_FS_COMPRESSION F2FS_FEATURE_RO_ATTR(compression, FEAT_COMPRESSION); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compr_written_block, compr_written_block); @@ -829,7 +831,9 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(verity), #endif ATTR_LIST(sb_checksum), +#ifdef CONFIG_UNICODE ATTR_LIST(casefold), +#endif #ifdef CONFIG_F2FS_FS_COMPRESSION ATTR_LIST(compression), #endif -- 2.32.0.rc0.204.g9fa02ecfa5-goog

4 years, 1 month

3
2
0 0

[v5.4.y, v4.19.y] nl80211: validate key indexes for cfg80211_registered_device

by Zubin Mithra

From: Anant Thazhemadam <anant.thazhemadam(a)gmail.com> commit 2d9463083ce92636a1bdd3e30d1236e3e95d859e upstream syzbot discovered a bug in which an OOB access was being made because an unsuitable key_idx value was wrongly considered to be acceptable while deleting a key in nl80211_del_key(). Since we don't know the cipher at the time of deletion, if cfg80211_validate_key_settings() were to be called directly in nl80211_del_key(), even valid keys would be wrongly determined invalid, and deletion wouldn't occur correctly. For this reason, a new function - cfg80211_valid_key_idx(), has been created, to determine if the key_idx value provided is valid or not. cfg80211_valid_key_idx() is directly called in 2 places - nl80211_del_key(), and cfg80211_validate_key_settings(). Reported-by: syzbot+49d4cab497c2142ee170(a)syzkaller.appspotmail.com Tested-by: syzbot+49d4cab497c2142ee170(a)syzkaller.appspotmail.com Suggested-by: Johannes Berg <johannes(a)sipsolutions.net> Signed-off-by: Anant Thazhemadam <anant.thazhemadam(a)gmail.com> Link: https://lore.kernel.org/r/20201204215825.129879-1-anant.thazhemadam@gmail.c… Cc: stable(a)vger.kernel.org [also disallow IGTK key IDs if no IGTK cipher is supported] Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Zubin Mithra <zsm(a)chromium.org> --- * Syzkaller triggered an OOB-read with the following stacktrace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xef/0x160 lib/dump_stack.c:118 print_address_description.constprop.0+0x17/0x311 mm/kasan/report.c:374 __kasan_report+0x145/0x18c mm/kasan/report.c:506 kasan_report+0x10/0x16 mm/kasan/common.c:634 ieee80211_key_free+0xb8/0xef net/mac80211/key.c:844 ieee80211_del_key+0x324/0x354 net/mac80211/cfg.c:532 rdev_del_key net/wireless/rdev-ops.h:107 [inline] nl80211_del_key+0x636/0x758 net/wireless/nl80211.c:4081 genl_family_rcv_msg+0xaa4/0xbb1 net/netlink/genetlink.c:629 genl_rcv_msg+0xce/0x127 net/netlink/genetlink.c:654 netlink_rcv_skb+0x23d/0x318 net/netlink/af_netlink.c:2478 genl_rcv+0x24/0x31 net/netlink/genetlink.c:665 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x432/0x556 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x943/0x9a8 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:638 [inline] sock_sendmsg+0xd5/0x10c net/socket.c:658 ____sys_sendmsg+0x4ea/0x641 net/socket.c:2298 ___sys_sendmsg+0x14a/0x1a9 net/socket.c:2352 __sys_sendmsg+0xf1/0x181 net/socket.c:2398 do_syscall_64+0x106/0x13f arch/x86/entry/common.c:299 entry_SYSCALL_64_after_hwframe+0x49/0xbe * This commit is present in 5.10.y. The crash does not occur on 4.14.y and older. * Tests run: syzkaller reproducer, Chrome OS tryjobs net/wireless/core.h | 2 ++ net/wireless/nl80211.c | 7 ++++--- net/wireless/util.c | 39 ++++++++++++++++++++++++++++++++++++++- 3 files changed, 44 insertions(+), 4 deletions(-) diff --git a/net/wireless/core.h b/net/wireless/core.h index d83c8e009448..17621d22fb17 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -433,6 +433,8 @@ void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev); /* internal helpers */ bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher); +bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev, + int key_idx, bool pairwise); int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5bb2316befb9..7b170ed6923e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3979,9 +3979,6 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (key.idx < 0) - return -EINVAL; - if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3997,6 +3994,10 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) key.type != NL80211_KEYTYPE_GROUP) return -EINVAL; + if (!cfg80211_valid_key_idx(rdev, key.idx, + key.type == NL80211_KEYTYPE_PAIRWISE)) + return -EINVAL; + if (!rdev->ops->del_key) return -EOPNOTSUPP; diff --git a/net/wireless/util.c b/net/wireless/util.c index 82244e2fc1f5..4eae6ad32851 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -229,11 +229,48 @@ bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher) return false; } +static bool +cfg80211_igtk_cipher_supported(struct cfg80211_registered_device *rdev) +{ + struct wiphy *wiphy = &rdev->wiphy; + int i; + + for (i = 0; i < wiphy->n_cipher_suites; i++) { + switch (wiphy->cipher_suites[i]) { + case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + return true; + } + } + + return false; +} + +bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev, + int key_idx, bool pairwise) +{ + int max_key_idx; + + if (pairwise) + max_key_idx = 3; + else if (cfg80211_igtk_cipher_supported(rdev)) + max_key_idx = 5; + else + max_key_idx = 3; + + if (key_idx < 0 || key_idx > max_key_idx) + return false; + + return true; +} + int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { - if (key_idx < 0 || key_idx > 5) + if (!cfg80211_valid_key_idx(rdev, key_idx, pairwise)) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) -- 2.20.0

4 years, 1 month

2
1
0 0

[PATCH] mm/hugetlb: expand restore_reserve_on_error functionality

by Mike Kravetz

The routine restore_reserve_on_error is called to restore reservation information when an error occurs after page allocation. The routine alloc_huge_page modifies the mapping reserve map and potentially the reserve count during allocation. If code calling alloc_huge_page encounters an error after allocation and needs to free the page, the reservation information needs to be adjusted. Currently, restore_reserve_on_error only takes action on pages for which the reserve count was adjusted(HPageRestoreReserve flag). There is nothing wrong with these adjustments. However, alloc_huge_page ALWAYS modifies the reserve map during allocation even if the reserve count is not adjusted. This can cause issues as observed during development of this patch [1]. One specific series of operations causing an issue is: - Create a shared hugetlb mapping Reservations for all pages created by default - Fault in a page in the mapping Reservation exists so reservation count is decremented - Punch a hole in the file/mapping at index previously faulted Reservation and any associated pages will be removed - Allocate a page to fill the hole No reservation entry, so reserve count unmodified Reservation entry added to map by alloc_huge_page - Error after allocation and before instantiating the page Reservation entry remains in map - Allocate a page to fill the hole Reservation entry exists, so decrement reservation count This will cause a reservation count underflow as the reservation count was decremented twice for the same index. A user would observe a very large number for HugePages_Rsvd in /proc/meminfo. This would also likely cause subsequent allocations of hugetlb pages to fail as it would 'appear' that all pages are reserved. This sequence of operations is unlikely to happen, however they were easily reproduced and observed using hacked up code as described in [1]. Address the issue by having the routine restore_reserve_on_error take action on pages where HPageRestoreReserve is not set. In this case, we need to remove any reserve map entry created by alloc_huge_page. A new helper routine vma_del_reservation assists with this operation. There are three callers of alloc_huge_page which do not currently call restore_reserve_on error before freeing a page on error paths. Add those missing calls. [1] https://lore.kernel.org/linux-mm/20210528005029.88088-1-almasrymina@google.… Fixes: 96b96a96ddee ("mm/hugetlb: fix huge page reservation leak in private mapping error paths" Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com> Cc: <stable(a)vger.kernel.org> --- fs/hugetlbfs/inode.c | 1 + include/linux/hugetlb.h | 2 + mm/hugetlb.c | 120 ++++++++++++++++++++++++++++++++-------- 3 files changed, 100 insertions(+), 23 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 21f7a5c92e8a..926eeb9bf4eb 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -735,6 +735,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, __SetPageUptodate(page); error = huge_add_to_page_cache(page, mapping, index); if (unlikely(error)) { + restore_reserve_on_error(h, &pseudo_vma, addr, page); put_page(page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 44721df20e89..b375b31f60c4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -627,6 +627,8 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9a616b7a8563..36b691c3eabf 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2259,12 +2259,18 @@ static void return_unused_surplus_pages(struct hstate *h, * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. + * + * vma_del_reservation is used in error paths where an entry in the reserve + * map was created during huge page allocation and must be removed. It is to + * be called after calling vma_needs_reservation to determine if a reservation + * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, + VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, @@ -2308,11 +2314,21 @@ static long __vma_reservation_common(struct hstate *h, ret = region_del(resv, idx, idx + 1); } break; + case VMA_DEL_RESV: + if (vma->vm_flags & VM_MAYSHARE) { + region_abort(resv, idx, idx + 1, 1); + ret = region_del(resv, idx, idx + 1); + } else { + ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); + /* region_add calls of range 1 should never fail. */ + VM_BUG_ON(ret < 0); + } + break; default: BUG(); } - if (vma->vm_flags & VM_MAYSHARE) + if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. @@ -2360,25 +2376,39 @@ static long vma_add_reservation(struct hstate *h, return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } +static long vma_del_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) +{ + return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); +} + /* - * This routine is called to restore a reservation on error paths. In the - * specific error paths, a huge page was allocated (via alloc_huge_page) - * and is about to be freed. If a reservation for the page existed, - * alloc_huge_page would have consumed the reservation and set - * HPageRestoreReserve in the newly allocated page. When the page is freed - * via free_huge_page, the global reservation count will be incremented if - * HPageRestoreReserve is set. However, free_huge_page can not adjust the - * reserve map. Adjust the reserve map here to be consistent with global - * reserve count adjustments to be made by free_huge_page. + * This routine is called to restore reservation information on error paths. + * It should ONLY be called for pages allocated via alloc_huge_page(), and + * the hugetlb mutex should remain held when calling this routine. + * + * It handles two specific cases: + * 1) A reservation was in place and page consumed the reservation. + * HPageRestoreRsvCnt is set in the page. + * 2) No reservation was in place for the page, so HPageRestoreRsvCnt is + * not set. However, alloc_huge_page always updates the reserve map. + * + * In case 1, free_huge_page will increment the global reserve count. But, + * free_huge_page does not have enough context to adjust the reservation map. + * This case deals primarily with private mappings. Adjust the reserve map + * here to be consistent with global reserve count adjustments to be made + * by free_huge_page. Make sure the reserve map indicates there is a + * reservation present. + * + * In case 2, simply undo reserve map modifications done by alloc_huge_page. */ -static void restore_reserve_on_error(struct hstate *h, - struct vm_area_struct *vma, unsigned long address, - struct page *page) +void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, + unsigned long address, struct page *page) { - if (unlikely(HPageRestoreReserve(page))) { - long rc = vma_needs_reservation(h, vma, address); + long rc = vma_needs_reservation(h, vma, address); - if (unlikely(rc < 0)) { + if (HPageRestoreReserve(page)) { + if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear HPageRestoreReserve so that @@ -2391,16 +2421,57 @@ static void restore_reserve_on_error(struct hstate *h, * accounting of reserve counts. */ ClearHPageRestoreReserve(page); - } else if (rc) { - rc = vma_add_reservation(h, vma, address); - if (unlikely(rc < 0)) + else if (rc) + (void)vma_add_reservation(h, vma, address); + else + vma_end_reservation(h, vma, address); + } else { + if (!rc) { + /* + * This indicates there is an entry in the reserve map + * added by alloc_huge_page. We know it was added + * before the alloc_huge_page call, otherwise + * HPageRestoreReserve would be set on the page. + * Remove the entry so that a subsequent allocation + * does not consume a reservation. + */ + rc = vma_del_reservation(h, vma, address); + if (rc < 0) /* - * See above comment about rare out of - * memory condition. + * VERY rare out of memory condition. Since + * we can not delete the entry, set + * HPageRestoreReserve so that the reserve + * count will be incremented when the page + * is freed. This reserve will be consumed + * on a subsequent allocation. */ - ClearHPageRestoreReserve(page); + SetHPageRestoreReserve(page); + } else if (rc < 0) { + /* + * Rare out of memory condition from + * vma_needs_reservation call. Memory allocation is + * only attempted if a new entry is needed. Therefore, + * this implies there is not an entry in the + * reserve map. + * + * For shared mappings, no entry in the map indicates + * no reservation. We are done. + */ + if (!(vma->vm_flags & VM_MAYSHARE)) + /* + * For private mappings, no entry indicates + * a reservation is present. Since we can + * not add an entry, set SetHPageRestoreReserve + * on the page so reserve count will be + * incremented when freed. This reserve will + * be consumed on a subsequent allocation. + */ + SetHPageRestoreReserve(page); } else - vma_end_reservation(h, vma, address); + /* + * No reservation present, do nothing + */ + vma_end_reservation(h, vma, address); } } @@ -4176,6 +4247,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { + restore_reserve_on_error(h, vma, addr, + new); put_page(new); /* dst_entry won't change as in child */ goto again; @@ -5174,6 +5247,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, if (vm_shared || is_continue) unlock_page(page); out_release_nounlock: + restore_reserve_on_error(h, dst_vma, dst_addr, page); put_page(page); goto out; } -- 2.31.1

4 years, 1 month

2
4
0 0

Please apply commit ff40e0d41af ("ALSA: usb: update old-style...") to v4.19.y, v5.4.y

by Guenter Roeck

Hi, please apply commit ff40e0d41af1 ("ALSA: usb: update old-style static const declaration") to v4.19.y and to v5.4.y. It fixes commit a01df925d1bb ("ALSA: usb-audio: More constifications") which was applied to v5.6 and backported to v5.4.y and to v4.19.y. Thanks, Guenter

4 years, 1 month

2
1
0 0

[PATCH v2] x86/sev: Check whether SEV or SME is supported first

by Pu Wen

The first two bits of the CPUID leaf 0x8000001F EAX indicate whether SEV or SME is supported respectively. It's better to check whether SEV or SME is actually supported before checking the MSR_AMD64_SEV to see whether SEV or SME is enabled. This is both a bare-metal issue and a guest/VM issue. Since the first generation Hygon Dhyana CPU doesn't support MSR_AMD64_SEV, reading that MSR results in a #GP - either directly from hardware in the bare-metal case or via the hypervisor (because the RDMSR is actually intercepted) in the guest/VM case, resulting in a failed boot. And since this is very early in the boot phase, rdmsrl_safe()/native_read_msr_safe() can't be used. So by checking the CPUID information before attempting the RDMSR, this goes back to the behavior before the patch identified in the commit eab696d8e8b9. Fixes: eab696d8e8b9 ("x86/sev: Do not require Hypervisor CPUID bit for SEV guests") Cc: <stable(a)vger.kernel.org> # v5.10+ Signed-off-by: Pu Wen <puwen(a)hygon.cn> Acked-by: Tom Lendacky <thomas.lendacky(a)amd.com> --- v1->v2: - Provide more details with improved commit messages. arch/x86/mm/mem_encrypt_identity.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index a9639f663d25..470b20208430 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -504,10 +504,6 @@ void __init sme_enable(struct boot_params *bp) #define AMD_SME_BIT BIT(0) #define AMD_SEV_BIT BIT(1) - /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; - /* * Check for the SME/SEV feature: * CPUID Fn8000_001F[EAX] @@ -519,11 +515,16 @@ void __init sme_enable(struct boot_params *bp) eax = 0x8000001f; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); - if (!(eax & feature_mask)) + /* Check whether SEV or SME is supported */ + if (!(eax & (AMD_SEV_BIT | AMD_SME_BIT))) return; me_mask = 1UL << (ebx & 0x3f); + /* Check the SEV MSR whether SEV or SME is enabled */ + sev_status = __rdmsr(MSR_AMD64_SEV); + feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { /* -- 2.23.0

4 years, 1 month

2
1
0 0

[PATCH 5.4, 5.10] btrfs: tree-checker: do not error out if extent ref hash doesn't match

by David Sterba

From: Josef Bacik <josef(a)toxicpanda.com> commit 1119a72e223f3073a604f8fccb3a470ccd8a4416 upstream. The tree checker checks the extent ref hash at read and write time to make sure we do not corrupt the file system. Generally extent references go inline, but if we have enough of them we need to make an item, which looks like key.objectid = <bytenr> key.type = <BTRFS_EXTENT_DATA_REF_KEY|BTRFS_TREE_BLOCK_REF_KEY> key.offset = hash(tree, owner, offset) However if key.offset collide with an unrelated extent reference we'll simply key.offset++ until we get something that doesn't collide. Obviously this doesn't match at tree checker time, and thus we error while writing out the transaction. This is relatively easy to reproduce, simply do something like the following xfs_io -f -c "pwrite 0 1M" file offset=2 for i in {0..10000} do xfs_io -c "reflink file 0 ${offset}M 1M" file offset=$(( offset + 2 )) done xfs_io -c "reflink file 0 17999258914816 1M" file xfs_io -c "reflink file 0 35998517829632 1M" file xfs_io -c "reflink file 0 53752752058368 1M" file btrfs filesystem sync And the sync will error out because we'll abort the transaction. The magic values above are used because they generate hash collisions with the first file in the main subvol. The fix for this is to remove the hash value check from tree checker, as we have no idea which offset ours should belong to. Reported-by: Tuomas Lähdekorpi <tuomas.lahdekorpi(a)gmail.com> Fixes: 0785a9aacf9d ("btrfs: tree-checker: Add EXTENT_DATA_REF check") CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Reviewed-by: David Sterba <dsterba(a)suse.com> [ add comment] Signed-off-by: David Sterba <dsterba(a)suse.com> --- Generated on 5.4 where it applies cleanly and on 5.10 with line offset but otherwise clean. fs/btrfs/tree-checker.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 7d06842a3d74..368c43c6cbd0 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1285,22 +1285,14 @@ static int check_extent_data_ref(struct extent_buffer *leaf, return -EUCLEAN; } for (; ptr < end; ptr += sizeof(*dref)) { - u64 root_objectid; - u64 owner; u64 offset; - u64 hash; + /* + * We cannot check the extent_data_ref hash due to possible + * overflow from the leaf due to hash collisions. + */ dref = (struct btrfs_extent_data_ref *)ptr; - root_objectid = btrfs_extent_data_ref_root(leaf, dref); - owner = btrfs_extent_data_ref_objectid(leaf, dref); offset = btrfs_extent_data_ref_offset(leaf, dref); - hash = hash_extent_data_ref(root_objectid, owner, offset); - if (hash != key->offset) { - extent_err(leaf, slot, - "invalid extent data ref hash, item has 0x%016llx key has 0x%016llx", - hash, key->offset); - return -EUCLEAN; - } if (!IS_ALIGNED(offset, leaf->fs_info->sectorsize)) { extent_err(leaf, slot, "invalid extent data backref offset, have %llu expect aligned to %u", -- 2.31.1

4 years, 1 month

2
1
0 0

[PATCH v2 1/5] arm64: kexec_file: Forbid non-crash kernels

by Marc Zyngier

It has been reported that kexec_file doesn't really work on arm64. It completely ignores any of the existing reservations, which results in the secondary kernel being loaded where the GICv3 LPI tables live, or even corrupting the ACPI tables. Since only crash kernels are imune to this as they use a reserved memory region, disable the non-crash kernel use case. Further patches will try and restore the functionality. Reported-by: Moritz Fischer <mdf(a)kernel.org> Signed-off-by: Marc Zyngier <maz(a)kernel.org> Cc: stable(a)vger.kernel.org # 5.10 --- arch/arm64/kernel/kexec_image.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index 9ec34690e255..acf9cd251307 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -145,3 +145,23 @@ const struct kexec_file_ops kexec_image_ops = { .verify_sig = image_verify_sig, #endif }; + +/** + * arch_kexec_locate_mem_hole - Find free memory to place the segments. + * @kbuf: Parameters for the memory search. + * + * On success, kbuf->mem will have the start address of the memory region found. + * + * Return: 0 on success, negative errno on error. + */ +int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf) +{ + /* + * For the time being, kexec_file_load isn't reliable except + * for crash kernel. Say sorry to the user. + */ + if (kbuf->image->type != KEXEC_TYPE_CRASH) + return -EADDRNOTAVAIL; + + return kexec_locate_mem_hole(kbuf); +} -- 2.30.2

4 years, 1 month

3
3
0 0

[PATCH v2 1/7] fuse: Fix crash in fuse_dentry_automount() error path

by Greg Kurz

If fuse_fill_super_submount() returns an error, the error path triggers a crash: [ 26.206673] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] [ 26.226362] RIP: 0010:__list_del_entry_valid+0x25/0x90 [...] [ 26.247938] Call Trace: [ 26.248300] fuse_mount_remove+0x2c/0x70 [fuse] [ 26.248892] virtio_kill_sb+0x22/0x160 [virtiofs] [ 26.249487] deactivate_locked_super+0x36/0xa0 [ 26.250077] fuse_dentry_automount+0x178/0x1a0 [fuse] The crash happens because fuse_mount_remove() assumes that the FUSE mount was already added to list under the FUSE connection, but this only done after fuse_fill_super_submount() has returned success. This means that until fuse_fill_super_submount() has returned success, the FUSE mount isn't actually owned by the superblock. We should thus reclaim ownership by clearing sb->s_fs_info, which will skip the call to fuse_mount_remove(), and perform rollback, like virtio_fs_get_tree() already does for the root sb. Fixes: bf109c64040f ("fuse: implement crossmounts") Cc: mreitz(a)redhat.com Cc: stable(a)vger.kernel.org # v5.10+ Signed-off-by: Greg Kurz <groug(a)kaod.org> Reviewed-by: Max Reitz <mreitz(a)redhat.com> --- fs/fuse/dir.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 1b6c001a7dd1..01559061cbfb 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -339,8 +339,12 @@ static struct vfsmount *fuse_dentry_automount(struct path *path) /* Initialize superblock, making @mp_fi its root */ err = fuse_fill_super_submount(sb, mp_fi); - if (err) + if (err) { + fuse_conn_put(fc); + kfree(fm); + sb->s_fs_info = NULL; goto out_put_sb; + } sb->s_flags |= SB_ACTIVE; fsc->root = dget(sb->s_root); -- 2.31.1

4 years, 1 month

1
0
0 0

[PATCH net 9/9] wireguard: allowedips: free empty intermediate nodes when removing single node

by Jason A. Donenfeld

When removing single nodes, it's possible that that node's parent is an empty intermediate node, in which case, it too should be removed. Otherwise the trie fills up and never is fully emptied, leading to gradual memory leaks over time for tries that are modified often. There was originally code to do this, but was removed during refactoring in 2016 and never reworked. Now that we have proper parent pointers from the previous commits, we can implement this properly. In order to reduce branching and expensive comparisons, we want to keep the double pointer for parent assignment (which lets us easily chain up to the root), but we still need to actually get the parent's base address. So encode the bit number into the last two bits of the pointer, and pack and unpack it as needed. This is a little bit clumsy but is the fastest and less memory wasteful of the compromises. Note that we align the root struct here to a minimum of 4, because it's embedded into a larger struct, and we're relying on having the bottom two bits for our flag, which would only be 16-bit aligned on m68k. The existing macro-based helpers were a bit unwieldy for adding the bit packing to, so this commit replaces them with safer and clearer ordinary functions. We add a test to the randomized/fuzzer part of the selftests, to free the randomized tries by-peer, refuzz it, and repeat, until it's supposed to be empty, and then then see if that actually resulted in the whole thing being emptied. That combined with kmemcheck should hopefully make sure this commit is doing what it should. Along the way this resulted in various other cleanups of the tests and fixes for recent graphviz. Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Cc: stable(a)vger.kernel.org Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com> --- drivers/net/wireguard/allowedips.c | 102 ++++++------ drivers/net/wireguard/allowedips.h | 4 +- drivers/net/wireguard/selftest/allowedips.c | 162 ++++++++++---------- 3 files changed, 137 insertions(+), 131 deletions(-) diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index c540dce8d224..b7197e80f226 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -30,8 +30,11 @@ static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src, node->bitlen = bits; memcpy(node->bits, src, bits / 8U); } -#define CHOOSE_NODE(parent, key) \ - parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1] + +static inline u8 choose(struct allowedips_node *node, const u8 *key) +{ + return (key[node->bit_at_a] >> node->bit_at_b) & 1; +} static void push_rcu(struct allowedips_node **stack, struct allowedips_node __rcu *p, unsigned int *len) @@ -112,7 +115,7 @@ static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits, found = node; if (node->cidr == bits) break; - node = rcu_dereference_bh(CHOOSE_NODE(node, key)); + node = rcu_dereference_bh(node->bit[choose(node, key)]); } return found; } @@ -144,8 +147,7 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key, u8 cidr, u8 bits, struct allowedips_node **rnode, struct mutex *lock) { - struct allowedips_node *node = rcu_dereference_protected(trie, - lockdep_is_held(lock)); + struct allowedips_node *node = rcu_dereference_protected(trie, lockdep_is_held(lock)); struct allowedips_node *parent = NULL; bool exact = false; @@ -155,13 +157,24 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key, exact = true; break; } - node = rcu_dereference_protected(CHOOSE_NODE(parent, key), - lockdep_is_held(lock)); + node = rcu_dereference_protected(parent->bit[choose(parent, key)], lockdep_is_held(lock)); } *rnode = parent; return exact; } +static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node) +{ + node->parent_bit_packed = (unsigned long)parent | bit; + rcu_assign_pointer(*parent, node); +} + +static inline void choose_and_connect_node(struct allowedips_node *parent, struct allowedips_node *node) +{ + u8 bit = choose(parent, node->bits); + connect_node(&parent->bit[bit], bit, node); +} + static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, u8 cidr, struct wg_peer *peer, struct mutex *lock) { @@ -177,8 +190,7 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, RCU_INIT_POINTER(node->peer, peer); list_add_tail(&node->peer_list, &peer->allowedips_list); copy_and_assign_cidr(node, key, cidr, bits); - rcu_assign_pointer(node->parent_bit, trie); - rcu_assign_pointer(*trie, node); + connect_node(trie, 2, node); return 0; } if (node_placement(*trie, key, cidr, bits, &node, lock)) { @@ -197,10 +209,10 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, if (!node) { down = rcu_dereference_protected(*trie, lockdep_is_held(lock)); } else { - down = rcu_dereference_protected(CHOOSE_NODE(node, key), lockdep_is_held(lock)); + const u8 bit = choose(node, key); + down = rcu_dereference_protected(node->bit[bit], lockdep_is_held(lock)); if (!down) { - rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(node, key)); - rcu_assign_pointer(CHOOSE_NODE(node, key), newnode); + connect_node(&node->bit[bit], bit, newnode); return 0; } } @@ -208,15 +220,11 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, parent = node; if (newnode->cidr == cidr) { - rcu_assign_pointer(down->parent_bit, &CHOOSE_NODE(newnode, down->bits)); - rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down); - if (!parent) { - rcu_assign_pointer(newnode->parent_bit, trie); - rcu_assign_pointer(*trie, newnode); - } else { - rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(parent, newnode->bits)); - rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits), newnode); - } + choose_and_connect_node(newnode, down); + if (!parent) + connect_node(trie, 2, newnode); + else + choose_and_connect_node(parent, newnode); return 0; } @@ -229,17 +237,12 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, INIT_LIST_HEAD(&node->peer_list); copy_and_assign_cidr(node, newnode->bits, cidr, bits); - rcu_assign_pointer(down->parent_bit, &CHOOSE_NODE(node, down->bits)); - rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down); - rcu_assign_pointer(newnode->parent_bit, &CHOOSE_NODE(node, newnode->bits)); - rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode); - if (!parent) { - rcu_assign_pointer(node->parent_bit, trie); - rcu_assign_pointer(*trie, node); - } else { - rcu_assign_pointer(node->parent_bit, &CHOOSE_NODE(parent, node->bits)); - rcu_assign_pointer(CHOOSE_NODE(parent, node->bits), node); - } + choose_and_connect_node(node, down); + choose_and_connect_node(node, newnode); + if (!parent) + connect_node(trie, 2, node); + else + choose_and_connect_node(parent, node); return 0; } @@ -297,7 +300,8 @@ int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip, void wg_allowedips_remove_by_peer(struct allowedips *table, struct wg_peer *peer, struct mutex *lock) { - struct allowedips_node *node, *child, *tmp; + struct allowedips_node *node, *child, **parent_bit, *parent, *tmp; + bool free_parent; if (list_empty(&peer->allowedips_list)) return; @@ -307,19 +311,29 @@ void wg_allowedips_remove_by_peer(struct allowedips *table, RCU_INIT_POINTER(node->peer, NULL); if (node->bit[0] && node->bit[1]) continue; - child = rcu_dereference_protected( - node->bit[!rcu_access_pointer(node->bit[0])], - lockdep_is_held(lock)); + child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])], + lockdep_is_held(lock)); if (child) - child->parent_bit = node->parent_bit; - *rcu_dereference_protected(node->parent_bit, lockdep_is_held(lock)) = child; + child->parent_bit_packed = node->parent_bit_packed; + parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL); + *parent_bit = child; + parent = (void *)parent_bit - + offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]); + free_parent = !rcu_access_pointer(node->bit[0]) && + !rcu_access_pointer(node->bit[1]) && + (node->parent_bit_packed & 3) <= 1 && + !rcu_access_pointer(parent->peer); + if (free_parent) + child = rcu_dereference_protected( + parent->bit[!(node->parent_bit_packed & 1)], + lockdep_is_held(lock)); call_rcu(&node->rcu, node_free_rcu); - - /* TODO: Note that we currently don't walk up and down in order to - * free any potential filler nodes. This means that this function - * doesn't free up as much as it could, which could be revisited - * at some point. - */ + if (!free_parent) + continue; + if (child) + child->parent_bit_packed = parent->parent_bit_packed; + *(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child; + call_rcu(&parent->rcu, node_free_rcu); } } diff --git a/drivers/net/wireguard/allowedips.h b/drivers/net/wireguard/allowedips.h index 32d611aaf3cc..2346c797eb4d 100644 --- a/drivers/net/wireguard/allowedips.h +++ b/drivers/net/wireguard/allowedips.h @@ -19,7 +19,7 @@ struct allowedips_node { u8 bits[16] __aligned(__alignof(u64)); /* Keep rarely used members at bottom to be beyond cache line. */ - struct allowedips_node *__rcu *parent_bit; + unsigned long parent_bit_packed; union { struct list_head peer_list; struct rcu_head rcu; @@ -30,7 +30,7 @@ struct allowedips { struct allowedips_node __rcu *root4; struct allowedips_node __rcu *root6; u64 seq; -}; +} __aligned(4); /* We pack the lower 2 bits of &root, but m68k only gives 16-bit alignment. */ void wg_allowedips_init(struct allowedips *table); void wg_allowedips_free(struct allowedips *table, struct mutex *mutex); diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 0d2a43a2d400..e173204ae7d7 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -19,32 +19,22 @@ #include <linux/siphash.h> -static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits, - u8 cidr) -{ - swap_endian(dst, src, bits); - memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8); - if (cidr) - dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8); -} - static __init void print_node(struct allowedips_node *node, u8 bits) { char *fmt_connection = KERN_DEBUG "\t\"%p/%d\" -> \"%p/%d\";\n"; - char *fmt_declaration = KERN_DEBUG - "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n"; + char *fmt_declaration = KERN_DEBUG "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n"; + u8 ip1[16], ip2[16], cidr1, cidr2; char *style = "dotted"; - u8 ip1[16], ip2[16]; u32 color = 0; + if (node == NULL) + return; if (bits == 32) { fmt_connection = KERN_DEBUG "\t\"%pI4/%d\" -> \"%pI4/%d\";\n"; - fmt_declaration = KERN_DEBUG - "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n"; + fmt_declaration = KERN_DEBUG "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n"; } else if (bits == 128) { fmt_connection = KERN_DEBUG "\t\"%pI6/%d\" -> \"%pI6/%d\";\n"; - fmt_declaration = KERN_DEBUG - "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n"; + fmt_declaration = KERN_DEBUG "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n"; } if (node->peer) { hsiphash_key_t key = { { 0 } }; @@ -55,24 +45,20 @@ static __init void print_node(struct allowedips_node *node, u8 bits) hsiphash_1u32(0xabad1dea, &key) % 200; style = "bold"; } - swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr); - printk(fmt_declaration, ip1, node->cidr, style, color); + wg_allowedips_read_node(node, ip1, &cidr1); + printk(fmt_declaration, ip1, cidr1, style, color); if (node->bit[0]) { - swap_endian_and_apply_cidr(ip2, - rcu_dereference_raw(node->bit[0])->bits, bits, - node->cidr); - printk(fmt_connection, ip1, node->cidr, ip2, - rcu_dereference_raw(node->bit[0])->cidr); - print_node(rcu_dereference_raw(node->bit[0]), bits); + wg_allowedips_read_node(rcu_dereference_raw(node->bit[0]), ip2, &cidr2); + printk(fmt_connection, ip1, cidr1, ip2, cidr2); } if (node->bit[1]) { - swap_endian_and_apply_cidr(ip2, - rcu_dereference_raw(node->bit[1])->bits, - bits, node->cidr); - printk(fmt_connection, ip1, node->cidr, ip2, - rcu_dereference_raw(node->bit[1])->cidr); - print_node(rcu_dereference_raw(node->bit[1]), bits); + wg_allowedips_read_node(rcu_dereference_raw(node->bit[1]), ip2, &cidr2); + printk(fmt_connection, ip1, cidr1, ip2, cidr2); } + if (node->bit[0]) + print_node(rcu_dereference_raw(node->bit[0]), bits); + if (node->bit[1]) + print_node(rcu_dereference_raw(node->bit[1]), bits); } static __init void print_tree(struct allowedips_node __rcu *top, u8 bits) @@ -121,8 +107,8 @@ static __init inline union nf_inet_addr horrible_cidr_to_mask(u8 cidr) { union nf_inet_addr mask; - memset(&mask, 0x00, 128 / 8); - memset(&mask, 0xff, cidr / 8); + memset(&mask, 0, sizeof(mask)); + memset(&mask.all, 0xff, cidr / 8); if (cidr % 32) mask.all[cidr / 32] = (__force u32)htonl( (0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL); @@ -149,42 +135,36 @@ horrible_mask_self(struct horrible_allowedips_node *node) } static __init inline bool -horrible_match_v4(const struct horrible_allowedips_node *node, - struct in_addr *ip) +horrible_match_v4(const struct horrible_allowedips_node *node, struct in_addr *ip) { return (ip->s_addr & node->mask.ip) == node->ip.ip; } static __init inline bool -horrible_match_v6(const struct horrible_allowedips_node *node, - struct in6_addr *ip) +horrible_match_v6(const struct horrible_allowedips_node *node, struct in6_addr *ip) { - return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == - node->ip.ip6[0] && - (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == - node->ip.ip6[1] && - (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == - node->ip.ip6[2] && + return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == node->ip.ip6[0] && + (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == node->ip.ip6[1] && + (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == node->ip.ip6[2] && (ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3]; } static __init void -horrible_insert_ordered(struct horrible_allowedips *table, - struct horrible_allowedips_node *node) +horrible_insert_ordered(struct horrible_allowedips *table, struct horrible_allowedips_node *node) { struct horrible_allowedips_node *other = NULL, *where = NULL; u8 my_cidr = horrible_mask_to_cidr(node->mask); hlist_for_each_entry(other, &table->head, table) { - if (!memcmp(&other->mask, &node->mask, - sizeof(union nf_inet_addr)) && - !memcmp(&other->ip, &node->ip, - sizeof(union nf_inet_addr)) && - other->ip_version == node->ip_version) { + if (other->ip_version == node->ip_version && + !memcmp(&other->mask, &node->mask, sizeof(union nf_inet_addr)) && + !memcmp(&other->ip, &node->ip, sizeof(union nf_inet_addr))) { other->value = node->value; kfree(node); return; } + } + hlist_for_each_entry(other, &table->head, table) { where = other; if (horrible_mask_to_cidr(other->mask) <= my_cidr) break; @@ -201,8 +181,7 @@ static __init int horrible_allowedips_insert_v4(struct horrible_allowedips *table, struct in_addr *ip, u8 cidr, void *value) { - struct horrible_allowedips_node *node = kzalloc(sizeof(*node), - GFP_KERNEL); + struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL); if (unlikely(!node)) return -ENOMEM; @@ -219,8 +198,7 @@ static __init int horrible_allowedips_insert_v6(struct horrible_allowedips *table, struct in6_addr *ip, u8 cidr, void *value) { - struct horrible_allowedips_node *node = kzalloc(sizeof(*node), - GFP_KERNEL); + struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL); if (unlikely(!node)) return -ENOMEM; @@ -234,39 +212,43 @@ horrible_allowedips_insert_v6(struct horrible_allowedips *table, } static __init void * -horrible_allowedips_lookup_v4(struct horrible_allowedips *table, - struct in_addr *ip) +horrible_allowedips_lookup_v4(struct horrible_allowedips *table, struct in_addr *ip) { struct horrible_allowedips_node *node; - void *ret = NULL; hlist_for_each_entry(node, &table->head, table) { - if (node->ip_version != 4) - continue; - if (horrible_match_v4(node, ip)) { - ret = node->value; - break; - } + if (node->ip_version == 4 && horrible_match_v4(node, ip)) + return node->value; } - return ret; + return NULL; } static __init void * -horrible_allowedips_lookup_v6(struct horrible_allowedips *table, - struct in6_addr *ip) +horrible_allowedips_lookup_v6(struct horrible_allowedips *table, struct in6_addr *ip) { struct horrible_allowedips_node *node; - void *ret = NULL; hlist_for_each_entry(node, &table->head, table) { - if (node->ip_version != 6) + if (node->ip_version == 6 && horrible_match_v6(node, ip)) + return node->value; + } + return NULL; +} + + +static __init void +horrible_allowedips_remove_by_value(struct horrible_allowedips *table, void *value) +{ + struct horrible_allowedips_node *node; + struct hlist_node *h; + + hlist_for_each_entry_safe(node, h, &table->head, table) { + if (node->value != value) continue; - if (horrible_match_v6(node, ip)) { - ret = node->value; - break; - } + hlist_del(&node->table); + kfree(node); } - return ret; + } static __init bool randomized_test(void) @@ -397,23 +379,33 @@ static __init bool randomized_test(void) print_tree(t.root6, 128); } - for (i = 0; i < NUM_QUERIES; ++i) { - prandom_bytes(ip, 4); - if (lookup(t.root4, 32, ip) != - horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) { - pr_err("allowedips random self-test: FAIL\n"); - goto free; + for (j = 0;; ++j) { + for (i = 0; i < NUM_QUERIES; ++i) { + prandom_bytes(ip, 4); + if (lookup(t.root4, 32, ip) != horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) { + horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip); + pr_err("allowedips random v4 self-test: FAIL\n"); + goto free; + } + prandom_bytes(ip, 16); + if (lookup(t.root6, 128, ip) != horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) { + pr_err("allowedips random v6 self-test: FAIL\n"); + goto free; + } } + if (j >= NUM_PEERS) + break; + mutex_lock(&mutex); + wg_allowedips_remove_by_peer(&t, peers[j], &mutex); + mutex_unlock(&mutex); + horrible_allowedips_remove_by_value(&h, peers[j]); } - for (i = 0; i < NUM_QUERIES; ++i) { - prandom_bytes(ip, 16); - if (lookup(t.root6, 128, ip) != - horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) { - pr_err("allowedips random self-test: FAIL\n"); - goto free; - } + if (t.root4 || t.root6) { + pr_err("allowedips random self-test removal: FAIL\n"); + goto free; } + ret = true; free: -- 2.31.1

4 years, 1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2021