From: Paolo Bonzini pbonzini@redhat.com

commit fb6d4d340e0532032c808a9933eaaa7b8de435ab upstream.

This is encoded as F3 0F C7 /7 with a register argument. The register argument is the second array in the group9 GroupDual, while F3 is the fourth element of a Prefix.

Reviewed-by: Wanpeng Li wanpeng.li@hotmail.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/cpuid.c | 7 ++++++- arch/x86/kvm/emulate.c | 22 +++++++++++++++++++++- arch/x86/kvm/vmx.c | 15 +++++++++++++++ 3 files changed, 42 insertions(+), 2 deletions(-)

--- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -291,13 +291,18 @@ static int __do_cpuid_ent_emulated(struc { switch (func) { case 0: - entry->eax = 1; /* only one leaf currently */ + entry->eax = 7; ++*nent; break; case 1: entry->ecx = F(MOVBE); ++*nent; break; + case 7: + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + if (index == 0) + entry->ecx = F(RDPID); + ++*nent; default: break; } --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3539,6 +3539,16 @@ static int em_cwd(struct x86_emulate_ctx return X86EMUL_CONTINUE; }

+static int em_rdpid(struct x86_emulate_ctxt *ctxt) +{ + u64 tsc_aux = 0; + + if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) + return emulate_gp(ctxt, 0); + ctxt->dst.val = tsc_aux; + return X86EMUL_CONTINUE; +} + static int em_rdtsc(struct x86_emulate_ctxt *ctxt) { u64 tsc = 0; @@ -4431,10 +4441,20 @@ static const struct opcode group8[] = { F(DstMem | SrcImmByte | Lock | PageTable, em_btc), };

+/* + * The "memory" destination is actually always a register, since we come + * from the register case of group9. + */ +static const struct gprefix pfx_0f_c7_7 = { + N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), +}; + + static const struct group_dual group9 = { { N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { - N, N, N, N, N, N, N, N, + N, N, N, N, N, N, N, + GP(0, &pfx_0f_c7_7), } };

static const struct opcode group11[] = { --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -12322,6 +12322,21 @@ static int vmx_check_intercept(struct kv struct x86_instruction_info *info, enum x86_intercept_stage stage) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + /* + * RDPID causes #UD if disabled through secondary execution controls. + * Because it is marked as EmulateOnUD, we need to intercept it here. + */ + if (info->intercept == x86_intercept_rdtscp && + !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + + /* TODO: check more intercepts... */ return X86EMUL_CONTINUE; }

From: Takashi Iwai tiwai@suse.de

commit 44eeb081b8630bb3ad3cd381d1ae1831463e48bb upstream.

Some code in HD-audio driver calls snprintf() in a loop and still expects that the return value were actually written size, while snprintf() returns the expected would-be length instead. When the given buffer limit were small, this leads to a buffer overflow.

Use scnprintf() for addressing those issues. It returns the actually written size unlike snprintf().

Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200218091409.27162-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/hda/hdmi_chmap.c | 2 +- sound/pci/hda/hda_codec.c | 2 +- sound/pci/hda/hda_eld.c | 2 +- sound/pci/hda/hda_sysfs.c | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-)

--- a/sound/hda/hdmi_chmap.c +++ b/sound/hda/hdmi_chmap.c @@ -249,7 +249,7 @@ void snd_hdac_print_channel_allocation(i

for (i = 0, j = 0; i < ARRAY_SIZE(cea_speaker_allocation_names); i++) { if (spk_alloc & (1 << i)) - j += snprintf(buf + j, buflen - j, " %s", + j += scnprintf(buf + j, buflen - j, " %s", cea_speaker_allocation_names[i]); } buf[j] = '\0'; /* necessary when j == 0 */ --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -4002,7 +4002,7 @@ void snd_print_pcm_bits(int pcm, char *b

for (i = 0, j = 0; i < ARRAY_SIZE(bits); i++) if (pcm & (AC_SUPPCM_BITS_8 << i)) - j += snprintf(buf + j, buflen - j, " %d", bits[i]); + j += scnprintf(buf + j, buflen - j, " %d", bits[i]);

buf[j] = '\0'; /* necessary when j == 0 */ } --- a/sound/pci/hda/hda_eld.c +++ b/sound/pci/hda/hda_eld.c @@ -373,7 +373,7 @@ static void hdmi_print_pcm_rates(int pcm

for (i = 0, j = 0; i < ARRAY_SIZE(alsa_rates); i++) if (pcm & (1 << i)) - j += snprintf(buf + j, buflen - j, " %d", + j += scnprintf(buf + j, buflen - j, " %d", alsa_rates[i]);

buf[j] = '\0'; /* necessary when j == 0 */ --- a/sound/pci/hda/hda_sysfs.c +++ b/sound/pci/hda/hda_sysfs.c @@ -221,7 +221,7 @@ static ssize_t init_verbs_show(struct de mutex_lock(&codec->user_mutex); for (i = 0; i < codec->init_verbs.used; i++) { struct hda_verb *v = snd_array_elem(&codec->init_verbs, i); - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "0x%02x 0x%03x 0x%04x\n", v->nid, v->verb, v->param); } @@ -271,7 +271,7 @@ static ssize_t hints_show(struct device mutex_lock(&codec->user_mutex); for (i = 0; i < codec->hints.used; i++) { struct hda_hint *hint = snd_array_elem(&codec->hints, i); - len += snprintf(buf + len, PAGE_SIZE - len, + len += scnprintf(buf + len, PAGE_SIZE - len, "%s = %s\n", hint->key, hint->val); } mutex_unlock(&codec->user_mutex);

From: Wenwen Wang wenwen@cs.uga.edu

commit fe2e082f5da5b4a0a92ae32978f81507ef37ec66 upstream.

In parse_tag_1_packet(), if tag 1 packet contains a key larger than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES, no cleanup is executed, leading to a memory leak on the allocated 'auth_tok_list_item'. To fix this issue, go to the label 'out_free' to perform the cleanup work.

Cc: stable@vger.kernel.org Fixes: dddfa461fc89 ("[PATCH] eCryptfs: Public key; packet management") Signed-off-by: Wenwen Wang wenwen@cs.uga.edu Signed-off-by: Tyler Hicks tyhicks@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ecryptfs/keystore.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1285,7 +1285,7 @@ parse_tag_1_packet(struct ecryptfs_crypt printk(KERN_ERR "Enter w/ first byte != 0x%.2x\n", ECRYPTFS_TAG_1_PACKET_TYPE); rc = -EINVAL; - goto out; + goto out_free; } /* Released: wipe_auth_tok_list called in ecryptfs_parse_packet_set or * at end of function upon failure */

From: Lyude Paul lyude@redhat.com

commit bf502391353b928e63096127e5fd8482080203f5 upstream.

This supports RMI4 and everything seems to work, including the touchpad buttons. So, let's enable this by default.

Signed-off-by: Lyude Paul lyude@redhat.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200204194322.112638-1-lyude@redhat.com Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/input/mouse/synaptics.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -172,6 +172,7 @@ static const char * const smbus_pnp_ids[ "LEN004a", /* W541 */ "LEN005b", /* P50 */ "LEN005e", /* T560 */ + "LEN006c", /* T470s */ "LEN0071", /* T480 */ "LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */ "LEN0073", /* X1 Carbon G5 (Elantech) */

From: Benjamin Tissoires benjamin.tissoires@redhat.com

commit 5179a9dfa9440c1781816e2c9a183d1d2512dc61 upstream.

The Yoga 11e is using LEN0049, but it doesn't have a trackstick.

Thus, there is no need to create a software top buttons row.

However, it seems that the device works under SMBus, so keep it as part of the smbus_pnp_ids.

Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200115013023.9710-1-benjamin.tissoires@redhat.co... Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/input/mouse/synaptics.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -149,7 +149,6 @@ static const char * const topbuttonpad_p "LEN0042", /* Yoga */ "LEN0045", "LEN0047", - "LEN0049", "LEN2000", /* S540 */ "LEN2001", /* Edge E431 */ "LEN2002", /* Edge E531 */ @@ -169,6 +168,7 @@ static const char * const smbus_pnp_ids[ /* all of the topbuttonpad_pnp_ids are valid, we just add some extras */ "LEN0048", /* X1 Carbon 3 */ "LEN0046", /* X250 */ + "LEN0049", /* Yoga 11e */ "LEN004a", /* W541 */ "LEN005b", /* P50 */ "LEN005e", /* T560 */

From: Suzuki K Poulose suzuki.poulose@arm.com

commit 7559950aef1ab8792c50797c6c5c7c5150a02460 upstream

We set the compat_elf_hwcap bits unconditionally on arm64 to include the VFP and NEON support. However, the FP/SIMD unit is optional on Arm v8 and thus could be missing. We already handle this properly in the kernel, but still advertise to the COMPAT applications that the VFP is available. Fix this to make sure we only advertise when we really have them.

Cc: stable@vger.kernel.org # v4.14 Cc: Will Deacon will@kernel.org Cc: Mark Rutland mark.rutland@arm.com Reviewed-by: Ard Biesheuvel ardb@kernel.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/cpufeature.c | 52 +++++++++++++++++++++++++++++----- 1 file changed, 45 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index c477fd34a9120..6b3bb67596ae8 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -41,9 +41,7 @@ EXPORT_SYMBOL_GPL(elf_hwcap); #define COMPAT_ELF_HWCAP_DEFAULT \ (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\ COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\ - COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\ - COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\ - COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\ + COMPAT_HWCAP_TLS|COMPAT_HWCAP_IDIV|\ COMPAT_HWCAP_LPAE) unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; unsigned int compat_elf_hwcap2 __read_mostly; @@ -1134,17 +1132,30 @@ static const struct arm64_cpu_capabilities arm64_features[] = { {}, };

-#define HWCAP_CAP(reg, field, s, min_value, cap_type, cap) \ - { \ - .desc = #cap, \ - .type = ARM64_CPUCAP_SYSTEM_FEATURE, \ + +#define HWCAP_CPUID_MATCH(reg, field, s, min_value) \ .matches = has_cpuid_feature, \ .sys_reg = reg, \ .field_pos = field, \ .sign = s, \ .min_field_value = min_value, \ + +#define __HWCAP_CAP(name, cap_type, cap) \ + .desc = name, \ + .type = ARM64_CPUCAP_SYSTEM_FEATURE, \ .hwcap_type = cap_type, \ .hwcap = cap, \ + +#define HWCAP_CAP(reg, field, s, min_value, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + HWCAP_CPUID_MATCH(reg, field, s, min_value) \ + } + +#define HWCAP_CAP_MATCH(match, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + .matches = match, \ }

static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { @@ -1177,8 +1188,35 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { {}, };

+#ifdef CONFIG_COMPAT +static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope) +{ + /* + * Check that all of MVFR1_EL1.{SIMDSP, SIMDInt, SIMDLS} are available, + * in line with that of arm32 as in vfp_init(). We make sure that the + * check is future proof, by making sure value is non-zero. + */ + u32 mvfr1; + + WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); + if (scope == SCOPE_SYSTEM) + mvfr1 = read_sanitised_ftr_reg(SYS_MVFR1_EL1); + else + mvfr1 = read_sysreg_s(SYS_MVFR1_EL1); + + return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDSP_SHIFT) && + cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDINT_SHIFT) && + cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDLS_SHIFT); +} +#endif + static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = { #ifdef CONFIG_COMPAT + HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON), + HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4), + /* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */ + HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP), + HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),

From: Suzuki K Poulose suzuki.poulose@arm.com

commit 52f73c383b2418f2d31b798e765ae7d596c35021 upstream

We detect the absence of FP/SIMD after an incapable CPU is brought up, and by then we have kernel threads running already with TIF_FOREIGN_FPSTATE set which could be set for early userspace applications (e.g, modprobe triggered from initramfs) and init. This could cause the applications to loop forever in do_nofity_resume() as we never clear the TIF flag, once we now know that we don't support FP.

Fix this by making sure that we clear the TIF_FOREIGN_FPSTATE flag for tasks which may have them set, as we would have done in the normal case, but avoiding touching the hardware state (since we don't support any).

Cc: stable@vger.kernel.org # v4.14 Cc: Will Deacon will@kernel.org Cc: Mark Rutland mark.rutland@arm.com Reviewed-by: Ard Biesheuvel ardb@kernel.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Acked-by: Marc Zyngier maz@kernel.org Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/fpsimd.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index f4fdf6420ac5c..4cd962f6c4302 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -206,8 +206,19 @@ void fpsimd_preserve_current_state(void) */ void fpsimd_restore_current_state(void) { - if (!system_supports_fpsimd()) + /* + * For the tasks that were created before we detected the absence of + * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(), + * e.g, init. This could be then inherited by the children processes. + * If we later detect that the system doesn't support FP/SIMD, + * we must clear the flag for all the tasks to indicate that the + * FPSTATE is clean (as we can't have one) to avoid looping for ever in + * do_notify_resume(). + */ + if (!system_supports_fpsimd()) { + clear_thread_flag(TIF_FOREIGN_FPSTATE); return; + }

local_bh_disable();

@@ -229,7 +240,7 @@ void fpsimd_restore_current_state(void) */ void fpsimd_update_current_state(struct fpsimd_state *state) { - if (!system_supports_fpsimd()) + if (WARN_ON(!system_supports_fpsimd())) return;

local_bh_disable();

From: Andreas Dilger adilger@dilger.ca

commit 14c9ca0583eee8df285d68a0e6ec71053efd2228 upstream.

Don't assume that the mmp_nodename and mmp_bdevname strings are NUL terminated, since they are filled in by snprintf(), which is not guaranteed to do so.

Link: https://lore.kernel.org/r/1580076215-1048-1-git-send-email-adilger@dilger.ca Signed-off-by: Andreas Dilger adilger@dilger.ca Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/mmp.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

--- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -120,10 +120,10 @@ void __dump_mmp_msg(struct super_block * { __ext4_warning(sb, function, line, "%s", msg); __ext4_warning(sb, function, line, - "MMP failure info: last update time: %llu, last update " - "node: %s, last update device: %s", - (long long unsigned int) le64_to_cpu(mmp->mmp_time), - mmp->mmp_nodename, mmp->mmp_bdevname); + "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s", + (unsigned long long)le64_to_cpu(mmp->mmp_time), + (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename, + (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname); }

/* @@ -154,6 +154,7 @@ static int kmmpd(void *data) mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval, EXT4_MMP_MIN_CHECK_INTERVAL); mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); + BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE); bdevname(bh->b_bdev, mmp->mmp_bdevname);

memcpy(mmp->mmp_nodename, init_utsname()->nodename, @@ -375,7 +376,8 @@ skip: /* * Start a kernel thread to update the MMP block periodically. */ - EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s", + EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s", + (int)sizeof(mmp->mmp_bdevname), bdevname(bh->b_bdev, mmp->mmp_bdevname)); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {

From: Jan Kara jack@suse.cz

commit 48a34311953d921235f4d7bbd2111690d2e469cf upstream.

DIR_INDEX has been introduced as a compat ext4 feature. That means that even kernels / tools that don't understand the feature may modify the filesystem. This works because for kernels not understanding indexed dir format, internal htree nodes appear just as empty directory entries. Index dir aware kernels then check the htree structure is still consistent before using the data. This all worked reasonably well until metadata checksums were introduced. The problem is that these effectively made DIR_INDEX only ro-compatible because internal htree nodes store checksums in a different place than normal directory blocks. Thus any modification ignorant to DIR_INDEX (or just clearing EXT4_INDEX_FL from the inode) will effectively cause checksum mismatch and trigger kernel errors. So we have to be more careful when dealing with indexed directories on filesystems with checksumming enabled.

1) We just disallow loading any directory inodes with EXT4_INDEX_FL when DIR_INDEX is not enabled. This is harsh but it should be very rare (it means someone disabled DIR_INDEX on existing filesystem and didn't run e2fsck), e2fsck can fix the problem, and we don't want to answer the difficult question: "Should we rather corrupt the directory more or should we ignore that DIR_INDEX feature is not set?"

2) When we find out htree structure is corrupted (but the filesystem and the directory should in support htrees), we continue just ignoring htree information for reading but we refuse to add new entries to the directory to avoid corrupting it more.

Link: https://lore.kernel.org/r/20200210144316.22081-1-jack@suse.cz Fixes: dbe89444042a ("ext4: Calculate and verify checksums for htree nodes") Reviewed-by: Andreas Dilger adilger@dilger.ca Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/dir.c | 14 ++++++++------ fs/ext4/ext4.h | 5 ++++- fs/ext4/inode.c | 12 ++++++++++++ fs/ext4/namei.c | 7 +++++++ 4 files changed, 31 insertions(+), 7 deletions(-)

--- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -125,12 +125,14 @@ static int ext4_readdir(struct file *fil if (err != ERR_BAD_DX_DIR) { return err; } - /* - * We don't set the inode dirty flag since it's not - * critical that it get flushed back to the disk. - */ - ext4_clear_inode_flag(file_inode(file), - EXT4_INODE_INDEX); + /* Can we just clear INDEX flag to ignore htree information? */ + if (!ext4_has_metadata_csum(sb)) { + /* + * We don't set the inode dirty flag since it's not + * critical that it gets flushed back to the disk. + */ + ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } }

if (ext4_has_inline_data(inode)) { --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2386,8 +2386,11 @@ void ext4_insert_dentry(struct inode *in struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) + if (!ext4_has_feature_dir_index(inode->i_sb)) { + /* ext4_iget() should have caught this... */ + WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } static const unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4817,6 +4817,18 @@ struct inode *ext4_iget(struct super_blo ret = -EFSCORRUPTED; goto bad_inode; } + /* + * If dir_index is not enabled but there's dir with INDEX flag set, + * we'd normally treat htree data as empty space. But with metadata + * checksumming that corrupts checksums so forbid that. + */ + if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { + EXT4_ERROR_INODE(inode, + "iget: Dir with htree data on filesystem without dir_index feature."); + ret = -EFSCORRUPTED; + goto bad_inode; + } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2094,6 +2094,13 @@ static int ext4_add_entry(handle_t *hand retval = ext4_dx_add_entry(handle, &fname, dir, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) goto out; + /* Can we just ignore htree data? */ + if (ext4_has_metadata_csum(sb)) { + EXT4_ERROR_INODE(dir, + "Directory has corrupted htree index."); + retval = -EFSCORRUPTED; + goto out; + } ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir);

From: Filipe Manana fdmanana@suse.com

commit ac05ca913e9f3871126d61da275bfe8516ff01ca upstream.

We have a few cases where we allow an extent map that is in an extent map tree to be merged with other extents in the tree. Such cases include the unpinning of an extent after the respective ordered extent completed or after logging an extent during a fast fsync. This can lead to subtle and dangerous problems because when doing the merge some other task might be using the same extent map and as consequence see an inconsistent state of the extent map - for example sees the new length but has seen the old start offset.

With luck this triggers a BUG_ON(), and not some silent bug, such as the following one in __do_readpage():

$ cat -n fs/btrfs/extent_io.c 3061 static int __do_readpage(struct extent_io_tree *tree, 3062 struct page *page, (...) 3127 em = __get_extent_map(inode, page, pg_offset, cur, 3128 end - cur + 1, get_extent, em_cached); 3129 if (IS_ERR_OR_NULL(em)) { 3130 SetPageError(page); 3131 unlock_extent(tree, cur, end); 3132 break; 3133 } 3134 extent_offset = cur - em->start; 3135 BUG_ON(extent_map_end(em) <= cur); (...)

Consider the following example scenario, where we end up hitting the BUG_ON() in __do_readpage().

We have an inode with a size of 8KiB and 2 extent maps:

extent A: file offset 0, length 4KiB, disk_bytenr = X, persisted on disk by a previous transaction

extent B: file offset 4KiB, length 4KiB, disk_bytenr = X + 4KiB, not yet persisted but writeback started for it already. The extent map is pinned since there's writeback and an ordered extent in progress, so it can not be merged with extent map A yet

The following sequence of steps leads to the BUG_ON():

1) The ordered extent for extent B completes, the respective page gets its writeback bit cleared and the extent map is unpinned, at that point it is not yet merged with extent map A because it's in the list of modified extents;

2) Due to memory pressure, or some other reason, the MM subsystem releases the page corresponding to extent B - btrfs_releasepage() is called and returns 1, meaning the page can be released as it's not dirty, not under writeback anymore and the extent range is not locked in the inode's iotree. However the extent map is not released, either because we are not in a context that allows memory allocations to block or because the inode's size is smaller than 16MiB - in this case our inode has a size of 8KiB;

3) Task B needs to read extent B and ends up __do_readpage() through the btrfs_readpage() callback. At __do_readpage() it gets a reference to extent map B;

4) Task A, doing a fast fsync, calls clear_em_loggin() against extent map B while holding the write lock on the inode's extent map tree - this results in try_merge_map() being called and since it's possible to merge extent map B with extent map A now (the extent map B was removed from the list of modified extents), the merging begins - it sets extent map B's start offset to 0 (was 4KiB), but before it increments the map's length to 8KiB (4kb + 4KiB), task A is at:

BUG_ON(extent_map_end(em) <= cur);

The call to extent_map_end() sees the extent map has a start of 0 and a length still at 4KiB, so it returns 4KiB and 'cur' is 4KiB, so the BUG_ON() is triggered.

So it's dangerous to modify an extent map that is in the tree, because some other task might have got a reference to it before and still using it, and needs to see a consistent map while using it. Generally this is very rare since most paths that lookup and use extent maps also have the file range locked in the inode's iotree. The fsync path is pretty much the only exception where we don't do it to avoid serialization with concurrent reads.

Fix this by not allowing an extent map do be merged if if it's being used by tasks other then the one attempting to merge the extent map (when the reference count of the extent map is greater than 2).

Reported-by: ryusuke1925 st13s20@gm.ibaraki-ct.ac.jp Reported-by: Koki Mitani koki.mitani.xg@hco.ntt.co.jp Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=206211 CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik josef@toxicpanda.com Signed-off-by: Filipe Manana fdmanana@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/extent_map.c | 11 +++++++++++ 1 file changed, 11 insertions(+)

--- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -228,6 +228,17 @@ static void try_merge_map(struct extent_ struct extent_map *merge = NULL; struct rb_node *rb;

+ /* + * We can't modify an extent map that is in the tree and that is being + * used by another task, as it can cause that other task to see it in + * inconsistent state during the merging. We always have 1 reference for + * the tree and 1 for this task (which is unpinning the extent map or + * clearing the logging flag), so anything > 2 means it's being used by + * other tasks too. + */ + if (refcount_read(&em->refs) > 2) + return; + if (em->start != 0) { rb = rb_prev(&em->rb_node); if (rb)

From: David Sterba dsterba@suse.com

commit 10a3a3edc5b89a8cd095bc63495fb1e0f42047d9 upstream.

A remount to a read-write filesystem is not safe when there's tree-log to be replayed. Files that could be opened until now might be affected by the changes in the tree-log.

A regular mount is needed to replay the log so the filesystem presents the consistent view with the pending changes included.

CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Anand Jain anand.jain@oracle.com Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/super.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1801,6 +1801,8 @@ static int btrfs_remount(struct super_bl }

if (btrfs_super_log_root(fs_info->super_copy) != 0) { + btrfs_warn(fs_info, + "mount required to replay tree-log, cannot remount read-write"); ret = -EINVAL; goto restore; }

From: Sean Christopherson sean.j.christopherson@intel.com

commit 148d735eb55d32848c3379e460ce365f2c1cbe4b upstream.

Hardcode the EPT page-walk level for L2 to be 4 levels, as KVM's MMU currently also hardcodes the page walk level for nested EPT to be 4 levels. The L2 guest is all but guaranteed to soft hang on its first instruction when L1 is using EPT, as KVM will construct 4-level page tables and then tell hardware to use 5-level page tables.

Fixes: 855feb673640 ("KVM: MMU: Add 5 level EPT & Shadow page table support.") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/vmx/vmx.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2968,6 +2968,9 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu,

static int get_ept_level(struct kvm_vcpu *vcpu) { + /* Nested EPT currently only supports 4-level walks. */ + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return 4; if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4;

From: Herbert Xu herbert@gondor.apana.org.au

commit 07928d9bfc81640bab36f5190e8725894d93b659 upstream.

The function padata_flush_queues is fundamentally broken because it cannot force padata users to complete the request that is underway. IOW padata has to passively wait for the completion of any outstanding work.

As it stands flushing is used in two places. Its use in padata_stop is simply unnecessary because nothing depends on the queues to be flushed afterwards.

The other use in padata_replace is more substantial as we depend on it to free the old pd structure. This patch instead uses the pd->refcnt to dynamically free the pd structure once all requests are complete.

Fixes: 2b73b07ab8a4 ("padata: Flush the padata queues actively") Cc: stable@vger.kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Reviewed-by: Daniel Jordan daniel.m.jordan@oracle.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au [dj: leave "pd->pinst = pinst" assignment in padata_alloc_pd()] Signed-off-by: Daniel Jordan daniel.m.jordan@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/padata.c | 45 ++++++++++++--------------------------------- 1 file changed, 12 insertions(+), 33 deletions(-)

--- a/kernel/padata.c +++ b/kernel/padata.c @@ -34,6 +34,8 @@

#define MAX_OBJ_NUM 1000

+static void padata_free_pd(struct parallel_data *pd); + static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) { int cpu, target_cpu; @@ -292,6 +294,7 @@ static void padata_serial_worker(struct struct padata_serial_queue *squeue; struct parallel_data *pd; LIST_HEAD(local_list); + int cnt;

local_bh_disable(); squeue = container_of(serial_work, struct padata_serial_queue, work); @@ -301,6 +304,8 @@ static void padata_serial_worker(struct list_replace_init(&squeue->serial.list, &local_list); spin_unlock(&squeue->serial.lock);

+ cnt = 0; + while (!list_empty(&local_list)) { struct padata_priv *padata;

@@ -310,9 +315,12 @@ static void padata_serial_worker(struct list_del_init(&padata->list);

padata->serial(padata); - atomic_dec(&pd->refcnt); + cnt++; } local_bh_enable(); + + if (atomic_sub_and_test(cnt, &pd->refcnt)) + padata_free_pd(pd); }

/** @@ -435,7 +443,7 @@ static struct parallel_data *padata_allo setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); - atomic_set(&pd->refcnt, 0); + atomic_set(&pd->refcnt, 1); pd->pinst = pinst; spin_lock_init(&pd->lock);

@@ -460,31 +468,6 @@ static void padata_free_pd(struct parall kfree(pd); }

-/* Flush all objects out of the padata queues. */ -static void padata_flush_queues(struct parallel_data *pd) -{ - int cpu; - struct padata_parallel_queue *pqueue; - struct padata_serial_queue *squeue; - - for_each_cpu(cpu, pd->cpumask.pcpu) { - pqueue = per_cpu_ptr(pd->pqueue, cpu); - flush_work(&pqueue->work); - } - - del_timer_sync(&pd->timer); - - if (atomic_read(&pd->reorder_objects)) - padata_reorder(pd); - - for_each_cpu(cpu, pd->cpumask.cbcpu) { - squeue = per_cpu_ptr(pd->squeue, cpu); - flush_work(&squeue->work); - } - - BUG_ON(atomic_read(&pd->refcnt) != 0); -} - static void __padata_start(struct padata_instance *pinst) { pinst->flags |= PADATA_INIT; @@ -498,10 +481,6 @@ static void __padata_stop(struct padata_ pinst->flags &= ~PADATA_INIT;

synchronize_rcu(); - - get_online_cpus(); - padata_flush_queues(pinst->pd); - put_online_cpus(); }

/* Replace the internal control structure with a new one. */ @@ -522,8 +501,8 @@ static void padata_replace(struct padata if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu)) notification_mask |= PADATA_CPU_SERIAL;

- padata_flush_queues(pd_old); - padata_free_pd(pd_old); + if (atomic_dec_and_test(&pd_old->refcnt)) + padata_free_pd(pd_old);

if (notification_mask) blocking_notifier_call_chain(&pinst->cpumask_change_notifier,

From: Uwe Kleine-König u.kleine-koenig@pengutronix.de

commit 437768962f754d9501e5ba4d98b1f2a89dc62028 upstream.

Handling an irq that isn't enabled can have some undesired side effects. Some of these are mentioned in the newly introduced code comment. Some of the irq sources already had their handling right, some don't. Handle them all in the same consistent way.

The change for USR1_RRDY and USR1_AGTIM drops the check for dma_is_enabled. This is correct as UCR1_RRDYEN and UCR2_ATEN are always off if dma is enabled.

Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Reviewed-by: Shawn Guo shawnguo@kernel.org [Backport to v4.14] Signed-off-by: Frieder Schrempf frieder.schrempf@kontron.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/imx.c | 53 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 39 insertions(+), 14 deletions(-)

--- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -843,14 +843,42 @@ static void imx_mctrl_check(struct imx_p static irqreturn_t imx_int(int irq, void *dev_id) { struct imx_port *sport = dev_id; - unsigned int sts; - unsigned int sts2; + unsigned int usr1, usr2, ucr1, ucr2, ucr3, ucr4; irqreturn_t ret = IRQ_NONE;

- sts = readl(sport->port.membase + USR1); - sts2 = readl(sport->port.membase + USR2); + usr1 = readl(sport->port.membase + USR1); + usr2 = readl(sport->port.membase + USR2); + ucr1 = readl(sport->port.membase + UCR1); + ucr2 = readl(sport->port.membase + UCR2); + ucr3 = readl(sport->port.membase + UCR3); + ucr4 = readl(sport->port.membase + UCR4); + + /* + * Even if a condition is true that can trigger an irq only handle it if + * the respective irq source is enabled. This prevents some undesired + * actions, for example if a character that sits in the RX FIFO and that + * should be fetched via DMA is tried to be fetched using PIO. Or the + * receiver is currently off and so reading from URXD0 results in an + * exception. So just mask the (raw) status bits for disabled irqs. + */ + if ((ucr1 & UCR1_RRDYEN) == 0) + usr1 &= ~USR1_RRDY; + if ((ucr2 & UCR2_ATEN) == 0) + usr1 &= ~USR1_AGTIM; + if ((ucr1 & UCR1_TXMPTYEN) == 0) + usr1 &= ~USR1_TRDY; + if ((ucr4 & UCR4_TCEN) == 0) + usr2 &= ~USR2_TXDC; + if ((ucr3 & UCR3_DTRDEN) == 0) + usr1 &= ~USR1_DTRD; + if ((ucr1 & UCR1_RTSDEN) == 0) + usr1 &= ~USR1_RTSD; + if ((ucr3 & UCR3_AWAKEN) == 0) + usr1 &= ~USR1_AWAKE; + if ((ucr4 & UCR4_OREN) == 0) + usr2 &= ~USR2_ORE;

- if (sts & (USR1_RRDY | USR1_AGTIM)) { + if (usr1 & (USR1_RRDY | USR1_AGTIM)) { if (sport->dma_is_enabled) imx_dma_rxint(sport); else @@ -858,18 +886,15 @@ static irqreturn_t imx_int(int irq, void ret = IRQ_HANDLED; }

- if ((sts & USR1_TRDY && - readl(sport->port.membase + UCR1) & UCR1_TXMPTYEN) || - (sts2 & USR2_TXDC && - readl(sport->port.membase + UCR4) & UCR4_TCEN)) { + if ((usr1 & USR1_TRDY) || (usr2 & USR2_TXDC)) { imx_txint(irq, dev_id); ret = IRQ_HANDLED; }

- if (sts & USR1_DTRD) { + if (usr1 & USR1_DTRD) { unsigned long flags;

- if (sts & USR1_DTRD) + if (usr1 & USR1_DTRD) writel(USR1_DTRD, sport->port.membase + USR1);

spin_lock_irqsave(&sport->port.lock, flags); @@ -879,17 +904,17 @@ static irqreturn_t imx_int(int irq, void ret = IRQ_HANDLED; }

- if (sts & USR1_RTSD) { + if (usr1 & USR1_RTSD) { imx_rtsint(irq, dev_id); ret = IRQ_HANDLED; }

- if (sts & USR1_AWAKE) { + if (usr1 & USR1_AWAKE) { writel(USR1_AWAKE, sport->port.membase + USR1); ret = IRQ_HANDLED; }

- if (sts2 & USR2_ORE) { + if (usr2 & USR2_ORE) { sport->port.icount.overrun++; writel(USR2_ORE, sport->port.membase + USR2); ret = IRQ_HANDLED;

From: Leon Romanovsky leonro@mellanox.com

commit 1dd017882e01d2fcd9c5dbbf1eb376211111c393 upstream.

We don't need to set pkey as valid in case that user set only one of pkey index or port number, otherwise it will be resulted in NULL pointer dereference while accessing to uninitialized pkey list. The following crash from Syzkaller revealed it.

kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN PTI CPU: 1 PID: 14753 Comm: syz-executor.2 Not tainted 5.5.0-rc5 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 RIP: 0010:get_pkey_idx_qp_list+0x161/0x2d0 Code: 01 00 00 49 8b 5e 20 4c 39 e3 0f 84 b9 00 00 00 e8 e4 42 6e fe 48 8d 7b 10 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 01 0f 8e d0 00 00 00 48 8d 7d 04 48 b8 RSP: 0018:ffffc9000bc6f950 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff82c8bdec RDX: 0000000000000002 RSI: ffffc900030a8000 RDI: 0000000000000010 RBP: ffff888112c8ce80 R08: 0000000000000004 R09: fffff5200178df1f R10: 0000000000000001 R11: fffff5200178df1f R12: ffff888115dc4430 R13: ffff888115da8498 R14: ffff888115dc4410 R15: ffff888115da8000 FS: 00007f20777de700(0000) GS:ffff88811b100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2f721000 CR3: 00000001173ca002 CR4: 0000000000360ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: port_pkey_list_insert+0xd7/0x7c0 ib_security_modify_qp+0x6fa/0xfc0 _ib_modify_qp+0x8c4/0xbf0 modify_qp+0x10da/0x16d0 ib_uverbs_modify_qp+0x9a/0x100 ib_uverbs_write+0xaa5/0xdf0 __vfs_write+0x7c/0x100 vfs_write+0x168/0x4a0 ksys_write+0xc8/0x200 do_syscall_64+0x9c/0x390 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: d291f1a65232 ("IB/core: Enforce PKey security on QPs") Link: https://lore.kernel.org/r/20200212080651.GB679970@unreal Signed-off-by: Maor Gottlieb maorg@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Message-Id: 20200212080651.GB679970@unreal Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/infiniband/core/security.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-)

--- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -338,22 +338,16 @@ static struct ib_ports_pkeys *get_new_pp if (!new_pps) return NULL;

- if (qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) { - if (!qp_pps) { - new_pps->main.port_num = qp_attr->port_num; - new_pps->main.pkey_index = qp_attr->pkey_index; - } else { - new_pps->main.port_num = (qp_attr_mask & IB_QP_PORT) ? - qp_attr->port_num : - qp_pps->main.port_num; - - new_pps->main.pkey_index = - (qp_attr_mask & IB_QP_PKEY_INDEX) ? - qp_attr->pkey_index : - qp_pps->main.pkey_index; - } + if (qp_attr_mask & IB_QP_PORT) + new_pps->main.port_num = + (qp_pps) ? qp_pps->main.port_num : qp_attr->port_num; + if (qp_attr_mask & IB_QP_PKEY_INDEX) + new_pps->main.pkey_index = (qp_pps) ? qp_pps->main.pkey_index : + qp_attr->pkey_index; + if ((qp_attr_mask & IB_QP_PKEY_INDEX) && (qp_attr_mask & IB_QP_PORT)) new_pps->main.state = IB_PORT_PKEY_VALID; - } else if (qp_pps) { + + if (!(qp_attr_mask & (IB_QP_PKEY_INDEX || IB_QP_PORT)) && qp_pps) { new_pps->main.port_num = qp_pps->main.port_num; new_pps->main.pkey_index = qp_pps->main.pkey_index; if (qp_pps->main.state != IB_PORT_PKEY_NOT_VALID)

From: Kan Liang kan.liang@linux.intel.com

commit f861854e1b435b27197417f6f90d87188003cb24 upstream.

Perf doesn't take the left period into account when auto-reload is enabled with fixed period sampling mode in context switch.

Here is the MSR trace of the perf command as below. (The MSR trace is simplified from a ftrace log.)

#perf record -e cycles:p -c 2000000 -- ./triad_loop

//The MSR trace of task schedule out //perf disable all counters, disable PEBS, disable GP counter 0, //read GP counter 0, and re-enable all counters. //The counter 0 stops at 0xfffffff82840 write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value 0 write_msr: MSR_IA32_PEBS_ENABLE(3f1), value 0 write_msr: MSR_P6_EVNTSEL0(186), value 40003003c rdpmc: 0, value fffffff82840 write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value f000000ff

//The MSR trace of the same task schedule in again //perf disable all counters, enable and set GP counter 0, //enable PEBS, and re-enable all counters. //0xffffffe17b80 (-2000000) is written to GP counter 0. write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value 0 write_msr: MSR_IA32_PMC0(4c1), value ffffffe17b80 write_msr: MSR_P6_EVNTSEL0(186), value 40043003c write_msr: MSR_IA32_PEBS_ENABLE(3f1), value 1 write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value f000000ff

When the same task schedule in again, the counter should starts from previous left. However, it starts from the fixed period -2000000 again.

A special variant of intel_pmu_save_and_restart() is used for auto-reload, which doesn't update the hwc->period_left. When the monitored task schedules in again, perf doesn't know the left period. The fixed period is used, which is inaccurate.

With auto-reload, the counter always has a negative counter value. So the left period is -value. Update the period_left in intel_pmu_save_and_restart_reload().

With the patch:

//The MSR trace of task schedule out write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value 0 write_msr: MSR_IA32_PEBS_ENABLE(3f1), value 0 write_msr: MSR_P6_EVNTSEL0(186), value 40003003c rdpmc: 0, value ffffffe25cbc write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value f000000ff

//The MSR trace of the same task schedule in again write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value 0 write_msr: MSR_IA32_PMC0(4c1), value ffffffe25cbc write_msr: MSR_P6_EVNTSEL0(186), value 40043003c write_msr: MSR_IA32_PEBS_ENABLE(3f1), value 1 write_msr: MSR_CORE_PERF_GLOBAL_CTRL(38f), value f000000ff

Fixes: d31fc13fdcb2 ("perf/x86/intel: Fix event update for auto-reload") Signed-off-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lkml.kernel.org/r/20200121190125.3389-1-kan.liang@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/events/intel/ds.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1368,6 +1368,8 @@ intel_pmu_save_and_restart_reload(struct old = ((s64)(prev_raw_count << shift) >> shift); local64_add(new - old + count * period, &event->count);

+ local64_set(&hwc->period_left, -new); + perf_event_update_userpage(event);

return 0;

From: zhangyi (F) yi.zhang@huawei.com

[ Upstream commit 6a66a7ded12baa6ebbb2e3e82f8cb91382814839 ]

There is no need to delay the clearing of b_modified flag to the transaction committing time when unmapping the journalled buffer, so just move it to the journal_unmap_buffer().

Link: https://lore.kernel.org/r/20200213063821.30455-2-yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: zhangyi (F) yi.zhang@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jbd2/commit.c | 43 +++++++++++++++---------------------------- fs/jbd2/transaction.c | 10 ++++++---- 2 files changed, 21 insertions(+), 32 deletions(-)

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 7dd6133925921..89cbf45a1dcda 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -973,34 +973,21 @@ void jbd2_journal_commit_transaction(journal_t *journal) * it. */

/* - * A buffer which has been freed while still being journaled by - * a previous transaction. - */ - if (buffer_freed(bh)) { - /* - * If the running transaction is the one containing - * "add to orphan" operation (b_next_transaction != - * NULL), we have to wait for that transaction to - * commit before we can really get rid of the buffer. - * So just clear b_modified to not confuse transaction - * credit accounting and refile the buffer to - * BJ_Forget of the running transaction. If the just - * committed transaction contains "add to orphan" - * operation, we can completely invalidate the buffer - * now. We are rather through in that since the - * buffer may be still accessible when blocksize < - * pagesize and it is attached to the last partial - * page. - */ - jh->b_modified = 0; - if (!jh->b_next_transaction) { - clear_buffer_freed(bh); - clear_buffer_jbddirty(bh); - clear_buffer_mapped(bh); - clear_buffer_new(bh); - clear_buffer_req(bh); - bh->b_bdev = NULL; - } + * A buffer which has been freed while still being journaled + * by a previous transaction, refile the buffer to BJ_Forget of + * the running transaction. If the just committed transaction + * contains "add to orphan" operation, we can completely + * invalidate the buffer now. We are rather through in that + * since the buffer may be still accessible when blocksize < + * pagesize and it is attached to the last partial page. + */ + if (buffer_freed(bh) && !jh->b_next_transaction) { + clear_buffer_freed(bh); + clear_buffer_jbddirty(bh); + clear_buffer_mapped(bh); + clear_buffer_new(bh); + clear_buffer_req(bh); + bh->b_bdev = NULL; }

if (buffer_jbddirty(bh)) { diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 7fe422eced89b..f2ff141a4479e 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2231,14 +2231,16 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, return -EBUSY; } /* - * OK, buffer won't be reachable after truncate. We just set - * j_next_transaction to the running transaction (if there is - * one) and mark buffer as freed so that commit code knows it - * should clear dirty bits when it is done with the buffer. + * OK, buffer won't be reachable after truncate. We just clear + * b_modified to not confuse transaction credit accounting, and + * set j_next_transaction to the running transaction (if there + * is one) and mark buffer as freed so that commit code knows + * it should clear dirty bits when it is done with the buffer. */ set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) jh->b_next_transaction = journal->j_running_transaction; + jh->b_modified = 0; jbd2_journal_put_journal_head(jh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh);

From: Allen Pais allen.pais@oracle.com

commit 35a79a63517981a8aea395497c548776347deda8 upstream.

alloc_workqueue is not checked for errors and as a result a potential NULL dereference could occur.

Link: https://lore.kernel.org/r/1568824618-4366-1-git-send-email-allen.pais@oracle... Signed-off-by: Allen Pais allen.pais@oracle.com Reviewed-by: Martin Wilck mwilck@suse.com Acked-by: Himanshu Madhani hmadhani@marvell.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com [Ajay: Modified to apply on v4.14.y] Signed-off-by: Ajay Kaher akaher@vmware.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/qla2xxx/qla_os.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3178,6 +3178,10 @@ qla2x00_probe_one(struct pci_dev *pdev, base_vha->mgmt_svr_loop_id, host->sg_tablesize);

ha->wq = alloc_workqueue("qla2xxx_wq", WQ_MEM_RECLAIM, 0); + if (unlikely(!ha->wq)) { + ret = -ENOMEM; + goto probe_failed; + }

if (ha->mqenable) { bool mq = false;

This reverts commit 57211b7366cc2abf784c35e537b256e7fcddc91e.

This patch isn't needed on 4.19 and older.

Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx/vmx.c | 8033 ---------------------------------------- 1 file changed, 8033 deletions(-) delete mode 100644 arch/x86/kvm/vmx/vmx.c

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c deleted file mode 100644 index 3791ce8d269e0..0000000000000 --- a/arch/x86/kvm/vmx/vmx.c +++ /dev/null @@ -1,8033 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Kernel-based Virtual Machine driver for Linux - * - * This module enables machines with Intel VT-x extensions to run virtual - * machines without emulation or binary translation. - * - * Copyright (C) 2006 Qumranet, Inc. - * Copyright 2010 Red Hat, Inc. and/or its affiliates. - * - * Authors: - * Avi Kivity avi@qumranet.com - * Yaniv Kamay yaniv@qumranet.com - */ - -#include <linux/frame.h> -#include <linux/highmem.h> -#include <linux/hrtimer.h> -#include <linux/kernel.h> -#include <linux/kvm_host.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/mod_devicetable.h> -#include <linux/mm.h> -#include <linux/sched.h> -#include <linux/sched/smt.h> -#include <linux/slab.h> -#include <linux/tboot.h> -#include <linux/trace_events.h> - -#include <asm/apic.h> -#include <asm/asm.h> -#include <asm/cpu.h> -#include <asm/debugreg.h> -#include <asm/desc.h> -#include <asm/fpu/internal.h> -#include <asm/io.h> -#include <asm/irq_remapping.h> -#include <asm/kexec.h> -#include <asm/perf_event.h> -#include <asm/mce.h> -#include <asm/mmu_context.h> -#include <asm/mshyperv.h> -#include <asm/spec-ctrl.h> -#include <asm/virtext.h> -#include <asm/vmx.h> - -#include "capabilities.h" -#include "cpuid.h" -#include "evmcs.h" -#include "irq.h" -#include "kvm_cache_regs.h" -#include "lapic.h" -#include "mmu.h" -#include "nested.h" -#include "ops.h" -#include "pmu.h" -#include "trace.h" -#include "vmcs.h" -#include "vmcs12.h" -#include "vmx.h" -#include "x86.h" - -MODULE_AUTHOR("Qumranet"); -MODULE_LICENSE("GPL"); - -static const struct x86_cpu_id vmx_cpu_id[] = { - X86_FEATURE_MATCH(X86_FEATURE_VMX), - {} -}; -MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id); - -bool __read_mostly enable_vpid = 1; -module_param_named(vpid, enable_vpid, bool, 0444); - -static bool __read_mostly enable_vnmi = 1; -module_param_named(vnmi, enable_vnmi, bool, S_IRUGO); - -bool __read_mostly flexpriority_enabled = 1; -module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); - -bool __read_mostly enable_ept = 1; -module_param_named(ept, enable_ept, bool, S_IRUGO); - -bool __read_mostly enable_unrestricted_guest = 1; -module_param_named(unrestricted_guest, - enable_unrestricted_guest, bool, S_IRUGO); - -bool __read_mostly enable_ept_ad_bits = 1; -module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); - -static bool __read_mostly emulate_invalid_guest_state = true; -module_param(emulate_invalid_guest_state, bool, S_IRUGO); - -static bool __read_mostly fasteoi = 1; -module_param(fasteoi, bool, S_IRUGO); - -static bool __read_mostly enable_apicv = 1; -module_param(enable_apicv, bool, S_IRUGO); - -/* - * If nested=1, nested virtualization is supported, i.e., guests may use - * VMX and be a hypervisor for its own guests. If nested=0, guests may not - * use VMX instructions. - */ -static bool __read_mostly nested = 1; -module_param(nested, bool, S_IRUGO); - -bool __read_mostly enable_pml = 1; -module_param_named(pml, enable_pml, bool, S_IRUGO); - -static bool __read_mostly dump_invalid_vmcs = 0; -module_param(dump_invalid_vmcs, bool, 0644); - -#define MSR_BITMAP_MODE_X2APIC 1 -#define MSR_BITMAP_MODE_X2APIC_APICV 2 - -#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL - -/* Guest_tsc -> host_tsc conversion requires 64-bit division. */ -static int __read_mostly cpu_preemption_timer_multi; -static bool __read_mostly enable_preemption_timer = 1; -#ifdef CONFIG_X86_64 -module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); -#endif - -#define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) -#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE -#define KVM_VM_CR0_ALWAYS_ON \ - (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | \ - X86_CR0_WP | X86_CR0_PG | X86_CR0_PE) -#define KVM_CR4_GUEST_OWNED_BITS \ - (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD) - -#define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE -#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) -#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE) - -#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM)) - -#define MSR_IA32_RTIT_STATUS_MASK (~(RTIT_STATUS_FILTEREN | \ - RTIT_STATUS_CONTEXTEN | RTIT_STATUS_TRIGGEREN | \ - RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \ - RTIT_STATUS_BYTECNT)) - -#define MSR_IA32_RTIT_OUTPUT_BASE_MASK \ - (~((1UL << cpuid_query_maxphyaddr(vcpu)) - 1) | 0x7f) - -/* - * These 2 parameters are used to config the controls for Pause-Loop Exiting: - * ple_gap: upper bound on the amount of time between two successive - * executions of PAUSE in a loop. Also indicate if ple enabled. - * According to test, this time is usually smaller than 128 cycles. - * ple_window: upper bound on the amount of time a guest is allowed to execute - * in a PAUSE loop. Tests indicate that most spinlocks are held for - * less than 2^12 cycles - * Time is measured based on a counter that runs at the same rate as the TSC, - * refer SDM volume 3b section 21.6.13 & 22.1.3. - */ -static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP; -module_param(ple_gap, uint, 0444); - -static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; -module_param(ple_window, uint, 0444); - -/* Default doubles per-vcpu window every exit. */ -static unsigned int ple_window_grow = KVM_DEFAULT_PLE_WINDOW_GROW; -module_param(ple_window_grow, uint, 0444); - -/* Default resets per-vcpu window every exit to ple_window. */ -static unsigned int ple_window_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK; -module_param(ple_window_shrink, uint, 0444); - -/* Default is to compute the maximum so we can never overflow. */ -static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX; -module_param(ple_window_max, uint, 0444); - -/* Default is SYSTEM mode, 1 for host-guest mode */ -int __read_mostly pt_mode = PT_MODE_SYSTEM; -module_param(pt_mode, int, S_IRUGO); - -static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); -static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); -static DEFINE_MUTEX(vmx_l1d_flush_mutex); - -/* Storage for pre module init parameter parsing */ -static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO; - -static const struct { - const char *option; - bool for_parse; -} vmentry_l1d_param[] = { - [VMENTER_L1D_FLUSH_AUTO] = {"auto", true}, - [VMENTER_L1D_FLUSH_NEVER] = {"never", true}, - [VMENTER_L1D_FLUSH_COND] = {"cond", true}, - [VMENTER_L1D_FLUSH_ALWAYS] = {"always", true}, - [VMENTER_L1D_FLUSH_EPT_DISABLED] = {"EPT disabled", false}, - [VMENTER_L1D_FLUSH_NOT_REQUIRED] = {"not required", false}, -}; - -#define L1D_CACHE_ORDER 4 -static void *vmx_l1d_flush_pages; - -static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) -{ - struct page *page; - unsigned int i; - - if (!boot_cpu_has_bug(X86_BUG_L1TF)) { - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; - return 0; - } - - if (!enable_ept) { - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; - return 0; - } - - if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) { - u64 msr; - - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr); - if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) { - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; - return 0; - } - } - - /* If set to auto use the default l1tf mitigation method */ - if (l1tf == VMENTER_L1D_FLUSH_AUTO) { - switch (l1tf_mitigation) { - case L1TF_MITIGATION_OFF: - l1tf = VMENTER_L1D_FLUSH_NEVER; - break; - case L1TF_MITIGATION_FLUSH_NOWARN: - case L1TF_MITIGATION_FLUSH: - case L1TF_MITIGATION_FLUSH_NOSMT: - l1tf = VMENTER_L1D_FLUSH_COND; - break; - case L1TF_MITIGATION_FULL: - case L1TF_MITIGATION_FULL_FORCE: - l1tf = VMENTER_L1D_FLUSH_ALWAYS; - break; - } - } else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) { - l1tf = VMENTER_L1D_FLUSH_ALWAYS; - } - - if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages && - !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) { - /* - * This allocation for vmx_l1d_flush_pages is not tied to a VM - * lifetime and so should not be charged to a memcg. - */ - page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER); - if (!page) - return -ENOMEM; - vmx_l1d_flush_pages = page_address(page); - - /* - * Initialize each page with a different pattern in - * order to protect against KSM in the nested - * virtualization case. - */ - for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) { - memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1, - PAGE_SIZE); - } - } - - l1tf_vmx_mitigation = l1tf; - - if (l1tf != VMENTER_L1D_FLUSH_NEVER) - static_branch_enable(&vmx_l1d_should_flush); - else - static_branch_disable(&vmx_l1d_should_flush); - - if (l1tf == VMENTER_L1D_FLUSH_COND) - static_branch_enable(&vmx_l1d_flush_cond); - else - static_branch_disable(&vmx_l1d_flush_cond); - return 0; -} - -static int vmentry_l1d_flush_parse(const char *s) -{ - unsigned int i; - - if (s) { - for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) { - if (vmentry_l1d_param[i].for_parse && - sysfs_streq(s, vmentry_l1d_param[i].option)) - return i; - } - } - return -EINVAL; -} - -static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp) -{ - int l1tf, ret; - - l1tf = vmentry_l1d_flush_parse(s); - if (l1tf < 0) - return l1tf; - - if (!boot_cpu_has(X86_BUG_L1TF)) - return 0; - - /* - * Has vmx_init() run already? If not then this is the pre init - * parameter parsing. In that case just store the value and let - * vmx_init() do the proper setup after enable_ept has been - * established. - */ - if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) { - vmentry_l1d_flush_param = l1tf; - return 0; - } - - mutex_lock(&vmx_l1d_flush_mutex); - ret = vmx_setup_l1d_flush(l1tf); - mutex_unlock(&vmx_l1d_flush_mutex); - return ret; -} - -static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp) -{ - if (WARN_ON_ONCE(l1tf_vmx_mitigation >= ARRAY_SIZE(vmentry_l1d_param))) - return sprintf(s, "???\n"); - - return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option); -} - -static const struct kernel_param_ops vmentry_l1d_flush_ops = { - .set = vmentry_l1d_flush_set, - .get = vmentry_l1d_flush_get, -}; -module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644); - -static bool guest_state_valid(struct kvm_vcpu *vcpu); -static u32 vmx_segment_access_rights(struct kvm_segment *var); -static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type); - -void vmx_vmexit(void); - -#define vmx_insn_failed(fmt...) \ -do { \ - WARN_ONCE(1, fmt); \ - pr_warn_ratelimited(fmt); \ -} while (0) - -asmlinkage void vmread_error(unsigned long field, bool fault) -{ - if (fault) - kvm_spurious_fault(); - else - vmx_insn_failed("kvm: vmread failed: field=%lx\n", field); -} - -noinline void vmwrite_error(unsigned long field, unsigned long value) -{ - vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%d\n", - field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); -} - -noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) -{ - vmx_insn_failed("kvm: vmclear failed: %p/%llx\n", vmcs, phys_addr); -} - -noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) -{ - vmx_insn_failed("kvm: vmptrld failed: %p/%llx\n", vmcs, phys_addr); -} - -noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) -{ - vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", - ext, vpid, gva); -} - -noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) -{ - vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", - ext, eptp, gpa); -} - -static DEFINE_PER_CPU(struct vmcs *, vmxarea); -DEFINE_PER_CPU(struct vmcs *, current_vmcs); -/* - * We maintain a per-CPU linked-list of VMCS loaded on that CPU. This is needed - * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it. - */ -static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); - -/* - * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we - * can find which vCPU should be waken up. - */ -static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); -static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); - -static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); -static DEFINE_SPINLOCK(vmx_vpid_lock); - -struct vmcs_config vmcs_config; -struct vmx_capability vmx_capability; - -#define VMX_SEGMENT_FIELD(seg) \ - [VCPU_SREG_##seg] = { \ - .selector = GUEST_##seg##_SELECTOR, \ - .base = GUEST_##seg##_BASE, \ - .limit = GUEST_##seg##_LIMIT, \ - .ar_bytes = GUEST_##seg##_AR_BYTES, \ - } - -static const struct kvm_vmx_segment_field { - unsigned selector; - unsigned base; - unsigned limit; - unsigned ar_bytes; -} kvm_vmx_segment_fields[] = { - VMX_SEGMENT_FIELD(CS), - VMX_SEGMENT_FIELD(DS), - VMX_SEGMENT_FIELD(ES), - VMX_SEGMENT_FIELD(FS), - VMX_SEGMENT_FIELD(GS), - VMX_SEGMENT_FIELD(SS), - VMX_SEGMENT_FIELD(TR), - VMX_SEGMENT_FIELD(LDTR), -}; - -u64 host_efer; -static unsigned long host_idt_base; - -/* - * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm - * will emulate SYSCALL in legacy mode if the vendor string in guest - * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To - * support this emulation, IA32_STAR must always be included in - * vmx_msr_index[], even in i386 builds. - */ -const u32 vmx_msr_index[] = { -#ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, -#endif - MSR_EFER, MSR_TSC_AUX, MSR_STAR, - MSR_IA32_TSX_CTRL, -}; - -#if IS_ENABLED(CONFIG_HYPERV) -static bool __read_mostly enlightened_vmcs = true; -module_param(enlightened_vmcs, bool, 0444); - -/* check_ept_pointer() should be under protection of ept_pointer_lock. */ -static void check_ept_pointer_match(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - u64 tmp_eptp = INVALID_PAGE; - int i; - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (!VALID_PAGE(tmp_eptp)) { - tmp_eptp = to_vmx(vcpu)->ept_pointer; - } else if (tmp_eptp != to_vmx(vcpu)->ept_pointer) { - to_kvm_vmx(kvm)->ept_pointers_match - = EPT_POINTERS_MISMATCH; - return; - } - } - - to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH; -} - -static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, - void *data) -{ - struct kvm_tlb_range *range = data; - - return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn, - range->pages); -} - -static inline int __hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_vcpu *vcpu, struct kvm_tlb_range *range) -{ - u64 ept_pointer = to_vmx(vcpu)->ept_pointer; - - /* - * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs address - * of the base of EPT PML4 table, strip off EPT configuration - * information. - */ - if (range) - return hyperv_flush_guest_mapping_range(ept_pointer & PAGE_MASK, - kvm_fill_hv_flush_list_func, (void *)range); - else - return hyperv_flush_guest_mapping(ept_pointer & PAGE_MASK); -} - -static int hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_tlb_range *range) -{ - struct kvm_vcpu *vcpu; - int ret = 0, i; - - spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); - - if (to_kvm_vmx(kvm)->ept_pointers_match == EPT_POINTERS_CHECK) - check_ept_pointer_match(kvm); - - if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) { - kvm_for_each_vcpu(i, vcpu, kvm) { - /* If ept_pointer is invalid pointer, bypass flush request. */ - if (VALID_PAGE(to_vmx(vcpu)->ept_pointer)) - ret |= __hv_remote_flush_tlb_with_range( - kvm, vcpu, range); - } - } else { - ret = __hv_remote_flush_tlb_with_range(kvm, - kvm_get_vcpu(kvm, 0), range); - } - - spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); - return ret; -} -static int hv_remote_flush_tlb(struct kvm *kvm) -{ - return hv_remote_flush_tlb_with_range(kvm, NULL); -} - -static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) -{ - struct hv_enlightened_vmcs *evmcs; - struct hv_partition_assist_pg **p_hv_pa_pg = - &vcpu->kvm->arch.hyperv.hv_pa_pg; - /* - * Synthetic VM-Exit is not enabled in current code and so All - * evmcs in singe VM shares same assist page. - */ - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); - - if (!*p_hv_pa_pg) - return -ENOMEM; - - evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; - - evmcs->partition_assist_page = - __pa(*p_hv_pa_pg); - evmcs->hv_vm_id = (unsigned long)vcpu->kvm; - evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; - - return 0; -} - -#endif /* IS_ENABLED(CONFIG_HYPERV) */ - -/* - * Comment's format: document - errata name - stepping - processor name. - * Refer from - * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp - */ -static u32 vmx_preemption_cpu_tfms[] = { -/* 323344.pdf - BA86 - D0 - Xeon 7500 Series */ -0x000206E6, -/* 323056.pdf - AAX65 - C2 - Xeon L3406 */ -/* 322814.pdf - AAT59 - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */ -/* 322911.pdf - AAU65 - C2 - i5-600, i3-500 Desktop and Pentium G6950 */ -0x00020652, -/* 322911.pdf - AAU65 - K0 - i5-600, i3-500 Desktop and Pentium G6950 */ -0x00020655, -/* 322373.pdf - AAO95 - B1 - Xeon 3400 Series */ -/* 322166.pdf - AAN92 - B1 - i7-800 and i5-700 Desktop */ -/* - * 320767.pdf - AAP86 - B1 - - * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile - */ -0x000106E5, -/* 321333.pdf - AAM126 - C0 - Xeon 3500 */ -0x000106A0, -/* 321333.pdf - AAM126 - C1 - Xeon 3500 */ -0x000106A1, -/* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */ -0x000106A4, - /* 321333.pdf - AAM126 - D0 - Xeon 3500 */ - /* 321324.pdf - AAK139 - D0 - Xeon 5500 */ - /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */ -0x000106A5, - /* Xeon E3-1220 V2 */ -0x000306A8, -}; - -static inline bool cpu_has_broken_vmx_preemption_timer(void) -{ - u32 eax = cpuid_eax(0x00000001), i; - - /* Clear the reserved bits */ - eax &= ~(0x3U << 14 | 0xfU << 28); - for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++) - if (eax == vmx_preemption_cpu_tfms[i]) - return true; - - return false; -} - -static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) -{ - return flexpriority_enabled && lapic_in_kernel(vcpu); -} - -static inline bool report_flexpriority(void) -{ - return flexpriority_enabled; -} - -static inline int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - for (i = 0; i < vmx->nmsrs; ++i) - if (vmx_msr_index[vmx->guest_msrs[i].index] == msr) - return i; - return -1; -} - -struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - i = __find_msr_index(vmx, msr); - if (i >= 0) - return &vmx->guest_msrs[i]; - return NULL; -} - -static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data) -{ - int ret = 0; - - u64 old_msr_data = msr->data; - msr->data = data; - if (msr - vmx->guest_msrs < vmx->save_nmsrs) { - preempt_disable(); - ret = kvm_set_shared_msr(msr->index, msr->data, - msr->mask); - preempt_enable(); - if (ret) - msr->data = old_msr_data; - } - return ret; -} - -void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) -{ - vmcs_clear(loaded_vmcs->vmcs); - if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) - vmcs_clear(loaded_vmcs->shadow_vmcs); - loaded_vmcs->cpu = -1; - loaded_vmcs->launched = 0; -} - -#ifdef CONFIG_KEXEC_CORE -/* - * This bitmap is used to indicate whether the vmclear - * operation is enabled on all cpus. All disabled by - * default. - */ -static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE; - -static inline void crash_enable_local_vmclear(int cpu) -{ - cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline void crash_disable_local_vmclear(int cpu) -{ - cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static inline int crash_local_vmclear_enabled(int cpu) -{ - return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap); -} - -static void crash_vmclear_local_loaded_vmcss(void) -{ - int cpu = raw_smp_processor_id(); - struct loaded_vmcs *v; - - if (!crash_local_vmclear_enabled(cpu)) - return; - - list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) - vmcs_clear(v->vmcs); -} -#else -static inline void crash_enable_local_vmclear(int cpu) { } -static inline void crash_disable_local_vmclear(int cpu) { } -#endif /* CONFIG_KEXEC_CORE */ - -static void __loaded_vmcs_clear(void *arg) -{ - struct loaded_vmcs *loaded_vmcs = arg; - int cpu = raw_smp_processor_id(); - - if (loaded_vmcs->cpu != cpu) - return; /* vcpu migration can race with cpu offline */ - if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs) - per_cpu(current_vmcs, cpu) = NULL; - crash_disable_local_vmclear(cpu); - list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link); - - /* - * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link - * is before setting loaded_vmcs->vcpu to -1 which is done in - * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist - * then adds the vmcs into percpu list before it is deleted. - */ - smp_wmb(); - - loaded_vmcs_init(loaded_vmcs); - crash_enable_local_vmclear(cpu); -} - -void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) -{ - int cpu = loaded_vmcs->cpu; - - if (cpu != -1) - smp_call_function_single(cpu, - __loaded_vmcs_clear, loaded_vmcs, 1); -} - -static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg, - unsigned field) -{ - bool ret; - u32 mask = 1 << (seg * SEG_FIELD_NR + field); - - if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) { - kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS); - vmx->segment_cache.bitmask = 0; - } - ret = vmx->segment_cache.bitmask & mask; - vmx->segment_cache.bitmask |= mask; - return ret; -} - -static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg) -{ - u16 *p = &vmx->segment_cache.seg[seg].selector; - - if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL)) - *p = vmcs_read16(kvm_vmx_segment_fields[seg].selector); - return *p; -} - -static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg) -{ - ulong *p = &vmx->segment_cache.seg[seg].base; - - if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE)) - *p = vmcs_readl(kvm_vmx_segment_fields[seg].base); - return *p; -} - -static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg) -{ - u32 *p = &vmx->segment_cache.seg[seg].limit; - - if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT)) - *p = vmcs_read32(kvm_vmx_segment_fields[seg].limit); - return *p; -} - -static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg) -{ - u32 *p = &vmx->segment_cache.seg[seg].ar; - - if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR)) - *p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes); - return *p; -} - -void update_exception_bitmap(struct kvm_vcpu *vcpu) -{ - u32 eb; - - eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << DB_VECTOR) | (1u << AC_VECTOR); - /* - * Guest access to VMware backdoor ports could legitimately - * trigger #GP because of TSS I/O permission bitmap. - * We intercept those #GP and allow access to them anyway - * as VMware does. - */ - if (enable_vmware_backdoor) - eb |= (1u << GP_VECTOR); - if ((vcpu->guest_debug & - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) - eb |= 1u << BP_VECTOR; - if (to_vmx(vcpu)->rmode.vm86_active) - eb = ~0; - if (enable_ept) - eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ - - /* When we are running a nested L2 guest and L1 specified for it a - * certain exception bitmap, we must trap the same exceptions and pass - * them to L1. When running L2, we will only handle the exceptions - * specified above if L1 did not want them. - */ - if (is_guest_mode(vcpu)) - eb |= get_vmcs12(vcpu)->exception_bitmap; - - vmcs_write32(EXCEPTION_BITMAP, eb); -} - -/* - * Check if MSR is intercepted for currently loaded MSR bitmap. - */ -static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) -{ - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) - return true; - - msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; -} - -static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, - unsigned long entry, unsigned long exit) -{ - vm_entry_controls_clearbit(vmx, entry); - vm_exit_controls_clearbit(vmx, exit); -} - -int vmx_find_msr_index(struct vmx_msrs *m, u32 msr) -{ - unsigned int i; - - for (i = 0; i < m->nr; ++i) { - if (m->val[i].index == msr) - return i; - } - return -ENOENT; -} - -static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr) -{ - int i; - struct msr_autoload *m = &vmx->msr_autoload; - - switch (msr) { - case MSR_EFER: - if (cpu_has_load_ia32_efer()) { - clear_atomic_switch_msr_special(vmx, - VM_ENTRY_LOAD_IA32_EFER, - VM_EXIT_LOAD_IA32_EFER); - return; - } - break; - case MSR_CORE_PERF_GLOBAL_CTRL: - if (cpu_has_load_perf_global_ctrl()) { - clear_atomic_switch_msr_special(vmx, - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL); - return; - } - break; - } - i = vmx_find_msr_index(&m->guest, msr); - if (i < 0) - goto skip_guest; - --m->guest.nr; - m->guest.val[i] = m->guest.val[m->guest.nr]; - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); - -skip_guest: - i = vmx_find_msr_index(&m->host, msr); - if (i < 0) - return; - - --m->host.nr; - m->host.val[i] = m->host.val[m->host.nr]; - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); -} - -static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx, - unsigned long entry, unsigned long exit, - unsigned long guest_val_vmcs, unsigned long host_val_vmcs, - u64 guest_val, u64 host_val) -{ - vmcs_write64(guest_val_vmcs, guest_val); - if (host_val_vmcs != HOST_IA32_EFER) - vmcs_write64(host_val_vmcs, host_val); - vm_entry_controls_setbit(vmx, entry); - vm_exit_controls_setbit(vmx, exit); -} - -static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, - u64 guest_val, u64 host_val, bool entry_only) -{ - int i, j = 0; - struct msr_autoload *m = &vmx->msr_autoload; - - switch (msr) { - case MSR_EFER: - if (cpu_has_load_ia32_efer()) { - add_atomic_switch_msr_special(vmx, - VM_ENTRY_LOAD_IA32_EFER, - VM_EXIT_LOAD_IA32_EFER, - GUEST_IA32_EFER, - HOST_IA32_EFER, - guest_val, host_val); - return; - } - break; - case MSR_CORE_PERF_GLOBAL_CTRL: - if (cpu_has_load_perf_global_ctrl()) { - add_atomic_switch_msr_special(vmx, - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL, - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL, - GUEST_IA32_PERF_GLOBAL_CTRL, - HOST_IA32_PERF_GLOBAL_CTRL, - guest_val, host_val); - return; - } - break; - case MSR_IA32_PEBS_ENABLE: - /* PEBS needs a quiescent period after being disabled (to write - * a record). Disabling PEBS through VMX MSR swapping doesn't - * provide that period, so a CPU could write host's record into - * guest's memory. - */ - wrmsrl(MSR_IA32_PEBS_ENABLE, 0); - } - - i = vmx_find_msr_index(&m->guest, msr); - if (!entry_only) - j = vmx_find_msr_index(&m->host, msr); - - if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) || - (j < 0 && m->host.nr == NR_LOADSTORE_MSRS)) { - printk_once(KERN_WARNING "Not enough msr switch entries. " - "Can't add msr %x\n", msr); - return; - } - if (i < 0) { - i = m->guest.nr++; - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr); - } - m->guest.val[i].index = msr; - m->guest.val[i].value = guest_val; - - if (entry_only) - return; - - if (j < 0) { - j = m->host.nr++; - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr); - } - m->host.val[j].index = msr; - m->host.val[j].value = host_val; -} - -static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) -{ - u64 guest_efer = vmx->vcpu.arch.efer; - u64 ignore_bits = 0; - - /* Shadow paging assumes NX to be available. */ - if (!enable_ept) - guest_efer |= EFER_NX; - - /* - * LMA and LME handled by hardware; SCE meaningless outside long mode. - */ - ignore_bits |= EFER_SCE; -#ifdef CONFIG_X86_64 - ignore_bits |= EFER_LMA | EFER_LME; - /* SCE is meaningful only in long mode on Intel */ - if (guest_efer & EFER_LMA) - ignore_bits &= ~(u64)EFER_SCE; -#endif - - /* - * On EPT, we can't emulate NX, so we must switch EFER atomically. - * On CPUs that support "load IA32_EFER", always switch EFER - * atomically, since it's faster than switching it manually. - */ - if (cpu_has_load_ia32_efer() || - (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - if (!(guest_efer & EFER_LMA)) - guest_efer &= ~EFER_LME; - if (guest_efer != host_efer) - add_atomic_switch_msr(vmx, MSR_EFER, - guest_efer, host_efer, false); - else - clear_atomic_switch_msr(vmx, MSR_EFER); - return false; - } else { - clear_atomic_switch_msr(vmx, MSR_EFER); - - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; - - return true; - } -} - -#ifdef CONFIG_X86_32 -/* - * On 32-bit kernels, VM exits still load the FS and GS bases from the - * VMCS rather than the segment table. KVM uses this helper to figure - * out the current bases to poke them into the VMCS before entry. - */ -static unsigned long segment_base(u16 selector) -{ - struct desc_struct *table; - unsigned long v; - - if (!(selector & ~SEGMENT_RPL_MASK)) - return 0; - - table = get_current_gdt_ro(); - - if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { - u16 ldt_selector = kvm_read_ldt(); - - if (!(ldt_selector & ~SEGMENT_RPL_MASK)) - return 0; - - table = (struct desc_struct *)segment_base(ldt_selector); - } - v = get_desc_base(&table[selector >> 3]); - return v; -} -#endif - -static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range) -{ - u32 i; - - wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status); - wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); - wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); - wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); - for (i = 0; i < addr_range; i++) { - wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); - wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); - } -} - -static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range) -{ - u32 i; - - rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status); - rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base); - rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask); - rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match); - for (i = 0; i < addr_range; i++) { - rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]); - rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]); - } -} - -static void pt_guest_enter(struct vcpu_vmx *vmx) -{ - if (pt_mode == PT_MODE_SYSTEM) - return; - - /* - * GUEST_IA32_RTIT_CTL is already set in the VMCS. - * Save host state before VM entry. - */ - rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); - if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { - wrmsrl(MSR_IA32_RTIT_CTL, 0); - pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range); - pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range); - } -} - -static void pt_guest_exit(struct vcpu_vmx *vmx) -{ - if (pt_mode == PT_MODE_SYSTEM) - return; - - if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) { - pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range); - pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range); - } - - /* Reload host state (IA32_RTIT_CTL will be cleared on VM exit). */ - wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); -} - -void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base) -{ - if (unlikely(fs_sel != host->fs_sel)) { - if (!(fs_sel & 7)) - vmcs_write16(HOST_FS_SELECTOR, fs_sel); - else - vmcs_write16(HOST_FS_SELECTOR, 0); - host->fs_sel = fs_sel; - } - if (unlikely(gs_sel != host->gs_sel)) { - if (!(gs_sel & 7)) - vmcs_write16(HOST_GS_SELECTOR, gs_sel); - else - vmcs_write16(HOST_GS_SELECTOR, 0); - host->gs_sel = gs_sel; - } - if (unlikely(fs_base != host->fs_base)) { - vmcs_writel(HOST_FS_BASE, fs_base); - host->fs_base = fs_base; - } - if (unlikely(gs_base != host->gs_base)) { - vmcs_writel(HOST_GS_BASE, gs_base); - host->gs_base = gs_base; - } -} - -void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct vmcs_host_state *host_state; -#ifdef CONFIG_X86_64 - int cpu = raw_smp_processor_id(); -#endif - unsigned long fs_base, gs_base; - u16 fs_sel, gs_sel; - int i; - - vmx->req_immediate_exit = false; - - /* - * Note that guest MSRs to be saved/restored can also be changed - * when guest state is loaded. This happens when guest transitions - * to/from long-mode by setting MSR_EFER.LMA. - */ - if (!vmx->guest_msrs_ready) { - vmx->guest_msrs_ready = true; - for (i = 0; i < vmx->save_nmsrs; ++i) - kvm_set_shared_msr(vmx->guest_msrs[i].index, - vmx->guest_msrs[i].data, - vmx->guest_msrs[i].mask); - - } - if (vmx->guest_state_loaded) - return; - - host_state = &vmx->loaded_vmcs->host_state; - - /* - * Set host fs and gs selectors. Unfortunately, 22.2.3 does not - * allow segment selectors with cpl > 0 or ti == 1. - */ - host_state->ldt_sel = kvm_read_ldt(); - -#ifdef CONFIG_X86_64 - savesegment(ds, host_state->ds_sel); - savesegment(es, host_state->es_sel); - - gs_base = cpu_kernelmode_gs_base(cpu); - if (likely(is_64bit_mm(current->mm))) { - save_fsgs_for_kvm(); - fs_sel = current->thread.fsindex; - gs_sel = current->thread.gsindex; - fs_base = current->thread.fsbase; - vmx->msr_host_kernel_gs_base = current->thread.gsbase; - } else { - savesegment(fs, fs_sel); - savesegment(gs, gs_sel); - fs_base = read_msr(MSR_FS_BASE); - vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); - } - - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); -#else - savesegment(fs, fs_sel); - savesegment(gs, gs_sel); - fs_base = segment_base(fs_sel); - gs_base = segment_base(gs_sel); -#endif - - vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); - vmx->guest_state_loaded = true; -} - -static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) -{ - struct vmcs_host_state *host_state; - - if (!vmx->guest_state_loaded) - return; - - host_state = &vmx->loaded_vmcs->host_state; - - ++vmx->vcpu.stat.host_state_reload; - -#ifdef CONFIG_X86_64 - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); -#endif - if (host_state->ldt_sel || (host_state->gs_sel & 7)) { - kvm_load_ldt(host_state->ldt_sel); -#ifdef CONFIG_X86_64 - load_gs_index(host_state->gs_sel); -#else - loadsegment(gs, host_state->gs_sel); -#endif - } - if (host_state->fs_sel & 7) - loadsegment(fs, host_state->fs_sel); -#ifdef CONFIG_X86_64 - if (unlikely(host_state->ds_sel | host_state->es_sel)) { - loadsegment(ds, host_state->ds_sel); - loadsegment(es, host_state->es_sel); - } -#endif - invalidate_tss_limit(); -#ifdef CONFIG_X86_64 - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); -#endif - load_fixmap_gdt(raw_smp_processor_id()); - vmx->guest_state_loaded = false; - vmx->guest_msrs_ready = false; -} - -#ifdef CONFIG_X86_64 -static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) -{ - preempt_disable(); - if (vmx->guest_state_loaded) - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); - preempt_enable(); - return vmx->msr_guest_kernel_gs_base; -} - -static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) -{ - preempt_disable(); - if (vmx->guest_state_loaded) - wrmsrl(MSR_KERNEL_GS_BASE, data); - preempt_enable(); - vmx->msr_guest_kernel_gs_base = data; -} -#endif - -static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) -{ - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - - /* - * In case of hot-plug or hot-unplug, we may have to undo - * vmx_vcpu_pi_put even if there is no assigned device. And we - * always keep PI.NDST up to date for simplicity: it makes the - * code easier, and CPU migration is not a fast path. - */ - if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) - return; - - /* - * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change - * PI.NDST: pi_post_block is the one expected to change PID.NDST and the - * wakeup handler expects the vCPU to be on the blocked_vcpu_list that - * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up - * correctly. - */ - if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) { - pi_clear_sn(pi_desc); - goto after_clear_sn; - } - - /* The full case. */ - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - new.sn = 0; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - -after_clear_sn: - - /* - * Clear SN before reading the bitmap. The VT-d firmware - * writes the bitmap and reads SN atomically (5.2.3 in the - * spec), so it doesn't really have a memory barrier that - * pairs with this, but we cannot do that and we need one. - */ - smp_mb__after_atomic(); - - if (!pi_is_pir_empty(pi_desc)) - pi_set_on(pi_desc); -} - -void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - bool already_loaded = vmx->loaded_vmcs->cpu == cpu; - - if (!already_loaded) { - loaded_vmcs_clear(vmx->loaded_vmcs); - local_irq_disable(); - crash_disable_local_vmclear(cpu); - - /* - * Read loaded_vmcs->cpu should be before fetching - * loaded_vmcs->loaded_vmcss_on_cpu_link. - * See the comments in __loaded_vmcs_clear(). - */ - smp_rmb(); - - list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link, - &per_cpu(loaded_vmcss_on_cpu, cpu)); - crash_enable_local_vmclear(cpu); - local_irq_enable(); - } - - if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { - per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; - vmcs_load(vmx->loaded_vmcs->vmcs); - indirect_branch_prediction_barrier(); - } - - if (!already_loaded) { - void *gdt = get_current_gdt_ro(); - unsigned long sysenter_esp; - - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - - /* - * Linux uses per-cpu TSS and GDT, so set these when switching - * processors. See 22.2.4. - */ - vmcs_writel(HOST_TR_BASE, - (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); - vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ - - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); - vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - - vmx->loaded_vmcs->cpu = cpu; - } - - /* Setup TSC multiplier */ - if (kvm_has_tsc_control && - vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) - decache_tsc_multiplier(vmx); -} - -/* - * Switches to specified vcpu, until a matching vcpu_put(), but assumes - * vcpu mutex is already taken. - */ -void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - vmx_vcpu_load_vmcs(vcpu, cpu); - - vmx_vcpu_pi_load(vcpu, cpu); - - vmx->host_pkru = read_pkru(); - vmx->host_debugctlmsr = get_debugctlmsr(); -} - -static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) -{ - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) - return; - - /* Set SN when the vCPU is preempted */ - if (vcpu->preempted) - pi_set_sn(pi_desc); -} - -static void vmx_vcpu_put(struct kvm_vcpu *vcpu) -{ - vmx_vcpu_pi_put(vcpu); - - vmx_prepare_switch_to_host(to_vmx(vcpu)); -} - -static bool emulation_required(struct kvm_vcpu *vcpu) -{ - return emulate_invalid_guest_state && !guest_state_valid(vcpu); -} - -static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); - -unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long rflags, save_rflags; - - if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) { - kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); - rflags = vmcs_readl(GUEST_RFLAGS); - if (vmx->rmode.vm86_active) { - rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS; - save_rflags = vmx->rmode.save_rflags; - rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; - } - vmx->rflags = rflags; - } - return vmx->rflags; -} - -void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long old_rflags; - - if (enable_unrestricted_guest) { - kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS); - vmx->rflags = rflags; - vmcs_writel(GUEST_RFLAGS, rflags); - return; - } - - old_rflags = vmx_get_rflags(vcpu); - vmx->rflags = rflags; - if (vmx->rmode.vm86_active) { - vmx->rmode.save_rflags = rflags; - rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; - } - vmcs_writel(GUEST_RFLAGS, rflags); - - if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) - vmx->emulation_required = emulation_required(vcpu); -} - -u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) -{ - u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); - int ret = 0; - - if (interruptibility & GUEST_INTR_STATE_STI) - ret |= KVM_X86_SHADOW_INT_STI; - if (interruptibility & GUEST_INTR_STATE_MOV_SS) - ret |= KVM_X86_SHADOW_INT_MOV_SS; - - return ret; -} - -void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) -{ - u32 interruptibility_old = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); - u32 interruptibility = interruptibility_old; - - interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS); - - if (mask & KVM_X86_SHADOW_INT_MOV_SS) - interruptibility |= GUEST_INTR_STATE_MOV_SS; - else if (mask & KVM_X86_SHADOW_INT_STI) - interruptibility |= GUEST_INTR_STATE_STI; - - if ((interruptibility != interruptibility_old)) - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility); -} - -static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long value; - - /* - * Any MSR write that attempts to change bits marked reserved will - * case a #GP fault. - */ - if (data & vmx->pt_desc.ctl_bitmask) - return 1; - - /* - * Any attempt to modify IA32_RTIT_CTL while TraceEn is set will - * result in a #GP unless the same write also clears TraceEn. - */ - if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) && - ((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN)) - return 1; - - /* - * WRMSR to IA32_RTIT_CTL that sets TraceEn but clears this bit - * and FabricEn would cause #GP, if - * CPUID.(EAX=14H, ECX=0):ECX.SNGLRGNOUT[bit 2] = 0 - */ - if ((data & RTIT_CTL_TRACEEN) && !(data & RTIT_CTL_TOPA) && - !(data & RTIT_CTL_FABRIC_EN) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output)) - return 1; - - /* - * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that - * utilize encodings marked reserved will casue a #GP fault. - */ - value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods); - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) && - !test_bit((data & RTIT_CTL_MTC_RANGE) >> - RTIT_CTL_MTC_RANGE_OFFSET, &value)) - return 1; - value = intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cycle_thresholds); - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) && - !test_bit((data & RTIT_CTL_CYC_THRESH) >> - RTIT_CTL_CYC_THRESH_OFFSET, &value)) - return 1; - value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_periods); - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc) && - !test_bit((data & RTIT_CTL_PSB_FREQ) >> - RTIT_CTL_PSB_FREQ_OFFSET, &value)) - return 1; - - /* - * If ADDRx_CFG is reserved or the encodings is >2 will - * cause a #GP fault. - */ - value = (data & RTIT_CTL_ADDR0) >> RTIT_CTL_ADDR0_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 1)) || (value > 2)) - return 1; - value = (data & RTIT_CTL_ADDR1) >> RTIT_CTL_ADDR1_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 2)) || (value > 2)) - return 1; - value = (data & RTIT_CTL_ADDR2) >> RTIT_CTL_ADDR2_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 3)) || (value > 2)) - return 1; - value = (data & RTIT_CTL_ADDR3) >> RTIT_CTL_ADDR3_OFFSET; - if ((value && (vmx->pt_desc.addr_range < 4)) || (value > 2)) - return 1; - - return 0; -} - -static int skip_emulated_instruction(struct kvm_vcpu *vcpu) -{ - unsigned long rip; - - /* - * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on - * undefined behavior: Intel's SDM doesn't mandate the VMCS field be - * set when EPT misconfig occurs. In practice, real hardware updates - * VM_EXIT_INSTRUCTION_LEN on EPT misconfig, but other hypervisors - * (namely Hyper-V) don't set it due to it being undefined behavior, - * i.e. we end up advancing IP with some random value. - */ - if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || - to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { - rip = kvm_rip_read(vcpu); - rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - kvm_rip_write(vcpu, rip); - } else { - if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) - return 0; - } - - /* skipping an emulated instruction also counts */ - vmx_set_interrupt_shadow(vcpu, 0); - - return 1; -} - -static void vmx_clear_hlt(struct kvm_vcpu *vcpu) -{ - /* - * Ensure that we clear the HLT state in the VMCS. We don't need to - * explicitly skip the instruction because if the HLT state is set, - * then the instruction is already executing and RIP has already been - * advanced. - */ - if (kvm_hlt_in_guest(vcpu->kvm) && - vmcs_read32(GUEST_ACTIVITY_STATE) == GUEST_ACTIVITY_HLT) - vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); -} - -static void vmx_queue_exception(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned nr = vcpu->arch.exception.nr; - bool has_error_code = vcpu->arch.exception.has_error_code; - u32 error_code = vcpu->arch.exception.error_code; - u32 intr_info = nr | INTR_INFO_VALID_MASK; - - kvm_deliver_exception_payload(vcpu); - - if (has_error_code) { - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); - intr_info |= INTR_INFO_DELIVER_CODE_MASK; - } - - if (vmx->rmode.vm86_active) { - int inc_eip = 0; - if (kvm_exception_is_soft(nr)) - inc_eip = vcpu->arch.event_exit_inst_len; - kvm_inject_realmode_interrupt(vcpu, nr, inc_eip); - return; - } - - WARN_ON_ONCE(vmx->emulation_required); - - if (kvm_exception_is_soft(nr)) { - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmx->vcpu.arch.event_exit_inst_len); - intr_info |= INTR_TYPE_SOFT_EXCEPTION; - } else - intr_info |= INTR_TYPE_HARD_EXCEPTION; - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); - - vmx_clear_hlt(vcpu); -} - -static bool vmx_rdtscp_supported(void) -{ - return cpu_has_vmx_rdtscp(); -} - -static bool vmx_invpcid_supported(void) -{ - return cpu_has_vmx_invpcid(); -} - -/* - * Swap MSR entry in host/guest MSR entry array. - */ -static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) -{ - struct shared_msr_entry tmp; - - tmp = vmx->guest_msrs[to]; - vmx->guest_msrs[to] = vmx->guest_msrs[from]; - vmx->guest_msrs[from] = tmp; -} - -/* - * Set up the vmcs to automatically save and restore system - * msrs. Don't touch the 64-bit msrs if the guest is in legacy - * mode, as fiddling with msrs is very expensive. - */ -static void setup_msrs(struct vcpu_vmx *vmx) -{ - int save_nmsrs, index; - - save_nmsrs = 0; -#ifdef CONFIG_X86_64 - /* - * The SYSCALL MSRs are only needed on long mode guests, and only - * when EFER.SCE is set. - */ - if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) { - index = __find_msr_index(vmx, MSR_STAR); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_LSTAR); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_SYSCALL_MASK); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - } -#endif - index = __find_msr_index(vmx, MSR_EFER); - if (index >= 0 && update_transition_efer(vmx, index)) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_TSC_AUX); - if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - - vmx->save_nmsrs = save_nmsrs; - vmx->guest_msrs_ready = false; - - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(&vmx->vcpu); -} - -static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - - if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) - return vcpu->arch.tsc_offset - vmcs12->tsc_offset; - - return vcpu->arch.tsc_offset; -} - -static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - u64 g_tsc_offset = 0; - - /* - * We're here if L1 chose not to trap WRMSR to TSC. According - * to the spec, this should set L1's TSC; The offset that L1 - * set for L2 remains unchanged, and still needs to be added - * to the newly set TSC to get L2's TSC. - */ - if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) - g_tsc_offset = vmcs12->tsc_offset; - - trace_kvm_write_tsc_offset(vcpu->vcpu_id, - vcpu->arch.tsc_offset - g_tsc_offset, - offset); - vmcs_write64(TSC_OFFSET, offset + g_tsc_offset); - return offset + g_tsc_offset; -} - -/* - * nested_vmx_allowed() checks whether a guest should be allowed to use VMX - * instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for - * all guests if the "nested" module option is off, and can also be disabled - * for a single guest by disabling its VMX cpuid bit. - */ -bool nested_vmx_allowed(struct kvm_vcpu *vcpu) -{ - return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX); -} - -static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, - uint64_t val) -{ - uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits; - - return !(val & ~valid_bits); -} - -static int vmx_get_msr_feature(struct kvm_msr_entry *msr) -{ - switch (msr->index) { - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - if (!nested) - return 1; - return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); - default: - return 1; - } -} - -/* - * Reads an msr value (of 'msr_index') into 'pdata'. - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct shared_msr_entry *msr; - u32 index; - - switch (msr_info->index) { -#ifdef CONFIG_X86_64 - case MSR_FS_BASE: - msr_info->data = vmcs_readl(GUEST_FS_BASE); - break; - case MSR_GS_BASE: - msr_info->data = vmcs_readl(GUEST_GS_BASE); - break; - case MSR_KERNEL_GS_BASE: - msr_info->data = vmx_read_guest_kernel_gs_base(vmx); - break; -#endif - case MSR_EFER: - return kvm_get_msr_common(vcpu, msr_info); - case MSR_IA32_TSX_CTRL: - if (!msr_info->host_initiated && - !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) - return 1; - goto find_shared_msr; - case MSR_IA32_UMWAIT_CONTROL: - if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) - return 1; - - msr_info->data = vmx->msr_ia32_umwait_control; - break; - case MSR_IA32_SPEC_CTRL: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) - return 1; - - msr_info->data = to_vmx(vcpu)->spec_ctrl; - break; - case MSR_IA32_SYSENTER_CS: - msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); - break; - case MSR_IA32_SYSENTER_EIP: - msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP); - break; - case MSR_IA32_SYSENTER_ESP: - msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); - break; - case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported() || - (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) - return 1; - msr_info->data = vmcs_read64(GUEST_BNDCFGS); - break; - case MSR_IA32_MCG_EXT_CTL: - if (!msr_info->host_initiated && - !(vmx->msr_ia32_feature_control & - FEATURE_CONTROL_LMCE)) - return 1; - msr_info->data = vcpu->arch.mcg_ext_ctl; - break; - case MSR_IA32_FEATURE_CONTROL: - msr_info->data = vmx->msr_ia32_feature_control; - break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - if (!nested_vmx_allowed(vcpu)) - return 1; - return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, - &msr_info->data); - case MSR_IA32_RTIT_CTL: - if (pt_mode != PT_MODE_HOST_GUEST) - return 1; - msr_info->data = vmx->pt_desc.guest.ctl; - break; - case MSR_IA32_RTIT_STATUS: - if (pt_mode != PT_MODE_HOST_GUEST) - return 1; - msr_info->data = vmx->pt_desc.guest.status; - break; - case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cr3_filtering)) - return 1; - msr_info->data = vmx->pt_desc.guest.cr3_match; - break; - case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) - return 1; - msr_info->data = vmx->pt_desc.guest.output_base; - break; - case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) - return 1; - msr_info->data = vmx->pt_desc.guest.output_mask; - break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || - (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges))) - return 1; - if (is_noncanonical_address(data, vcpu)) - return 1; - if (index % 2) - msr_info->data = vmx->pt_desc.guest.addr_b[index / 2]; - else - msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; - break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - goto find_shared_msr; - default: - find_shared_msr: - msr = find_msr_entry(vmx, msr_info->index); - if (msr) { - msr_info->data = msr->data; - break; - } - return kvm_get_msr_common(vcpu, msr_info); - } - - return 0; -} - -/* - * Writes msr value into the appropriate "register". - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct shared_msr_entry *msr; - int ret = 0; - u32 msr_index = msr_info->index; - u64 data = msr_info->data; - u32 index; - - switch (msr_index) { - case MSR_EFER: - ret = kvm_set_msr_common(vcpu, msr_info); - break; -#ifdef CONFIG_X86_64 - case MSR_FS_BASE: - vmx_segment_cache_clear(vmx); - vmcs_writel(GUEST_FS_BASE, data); - break; - case MSR_GS_BASE: - vmx_segment_cache_clear(vmx); - vmcs_writel(GUEST_GS_BASE, data); - break; - case MSR_KERNEL_GS_BASE: - vmx_write_guest_kernel_gs_base(vmx, data); - break; -#endif - case MSR_IA32_SYSENTER_CS: - if (is_guest_mode(vcpu)) - get_vmcs12(vcpu)->guest_sysenter_cs = data; - vmcs_write32(GUEST_SYSENTER_CS, data); - break; - case MSR_IA32_SYSENTER_EIP: - if (is_guest_mode(vcpu)) - get_vmcs12(vcpu)->guest_sysenter_eip = data; - vmcs_writel(GUEST_SYSENTER_EIP, data); - break; - case MSR_IA32_SYSENTER_ESP: - if (is_guest_mode(vcpu)) - get_vmcs12(vcpu)->guest_sysenter_esp = data; - vmcs_writel(GUEST_SYSENTER_ESP, data); - break; - case MSR_IA32_DEBUGCTLMSR: - if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & - VM_EXIT_SAVE_DEBUG_CONTROLS) - get_vmcs12(vcpu)->guest_ia32_debugctl = data; - - ret = kvm_set_msr_common(vcpu, msr_info); - break; - - case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported() || - (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) - return 1; - if (is_noncanonical_address(data & PAGE_MASK, vcpu) || - (data & MSR_IA32_BNDCFGS_RSVD)) - return 1; - vmcs_write64(GUEST_BNDCFGS, data); - break; - case MSR_IA32_UMWAIT_CONTROL: - if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx)) - return 1; - - /* The reserved bit 1 and non-32 bit [63:32] should be zero */ - if (data & (BIT_ULL(1) | GENMASK_ULL(63, 32))) - return 1; - - vmx->msr_ia32_umwait_control = data; - break; - case MSR_IA32_SPEC_CTRL: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) - return 1; - - /* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) - return 1; - - vmx->spec_ctrl = data; - - if (!data) - break; - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. We update the vmcs01 here for L1 as well - * since it will end up touching the MSR anyway now. - */ - vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, - MSR_IA32_SPEC_CTRL, - MSR_TYPE_RW); - break; - case MSR_IA32_TSX_CTRL: - if (!msr_info->host_initiated && - !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR)) - return 1; - if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) - return 1; - goto find_shared_msr; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. - */ - vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, - MSR_TYPE_W); - break; - case MSR_IA32_CR_PAT: - if (!kvm_pat_valid(data)) - return 1; - - if (is_guest_mode(vcpu) && - get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT) - get_vmcs12(vcpu)->guest_ia32_pat = data; - - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - vmcs_write64(GUEST_IA32_PAT, data); - vcpu->arch.pat = data; - break; - } - ret = kvm_set_msr_common(vcpu, msr_info); - break; - case MSR_IA32_TSC_ADJUST: - ret = kvm_set_msr_common(vcpu, msr_info); - break; - case MSR_IA32_MCG_EXT_CTL: - if ((!msr_info->host_initiated && - !(to_vmx(vcpu)->msr_ia32_feature_control & - FEATURE_CONTROL_LMCE)) || - (data & ~MCG_EXT_CTL_LMCE_EN)) - return 1; - vcpu->arch.mcg_ext_ctl = data; - break; - case MSR_IA32_FEATURE_CONTROL: - if (!vmx_feature_control_msr_valid(vcpu, data) || - (to_vmx(vcpu)->msr_ia32_feature_control & - FEATURE_CONTROL_LOCKED && !msr_info->host_initiated)) - return 1; - vmx->msr_ia32_feature_control = data; - if (msr_info->host_initiated && data == 0) - vmx_leave_nested(vcpu); - break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - if (!msr_info->host_initiated) - return 1; /* they are read-only */ - if (!nested_vmx_allowed(vcpu)) - return 1; - return vmx_set_vmx_msr(vcpu, msr_index, data); - case MSR_IA32_RTIT_CTL: - if ((pt_mode != PT_MODE_HOST_GUEST) || - vmx_rtit_ctl_check(vcpu, data) || - vmx->nested.vmxon) - return 1; - vmcs_write64(GUEST_IA32_RTIT_CTL, data); - vmx->pt_desc.guest.ctl = data; - pt_update_intercept_for_msr(vmx); - break; - case MSR_IA32_RTIT_STATUS: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (data & MSR_IA32_RTIT_STATUS_MASK)) - return 1; - vmx->pt_desc.guest.status = data; - break; - case MSR_IA32_RTIT_CR3_MATCH: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_cr3_filtering)) - return 1; - vmx->pt_desc.guest.cr3_match = data; - break; - case MSR_IA32_RTIT_OUTPUT_BASE: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output)) || - (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK)) - return 1; - vmx->pt_desc.guest.output_base = data; - break; - case MSR_IA32_RTIT_OUTPUT_MASK: - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (!intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_topa_output) && - !intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_single_range_output))) - return 1; - vmx->pt_desc.guest.output_mask = data; - break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; - if ((pt_mode != PT_MODE_HOST_GUEST) || - (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) || - (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges))) - return 1; - if (is_noncanonical_address(data, vcpu)) - return 1; - if (index % 2) - vmx->pt_desc.guest.addr_b[index / 2] = data; - else - vmx->pt_desc.guest.addr_a[index / 2] = data; - break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - /* Check reserved bit, higher 32 bits should be zero */ - if ((data >> 32) != 0) - return 1; - goto find_shared_msr; - - default: - find_shared_msr: - msr = find_msr_entry(vmx, msr_index); - if (msr) - ret = vmx_set_guest_msr(vmx, msr, data); - else - ret = kvm_set_msr_common(vcpu, msr_info); - } - - return ret; -} - -static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) -{ - kvm_register_mark_available(vcpu, reg); - - switch (reg) { - case VCPU_REGS_RSP: - vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); - break; - case VCPU_REGS_RIP: - vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP); - break; - case VCPU_EXREG_PDPTR: - if (enable_ept) - ept_save_pdptrs(vcpu); - break; - case VCPU_EXREG_CR3: - if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - break; - default: - WARN_ON_ONCE(1); - break; - } -} - -static __init int cpu_has_kvm_support(void) -{ - return cpu_has_vmx(); -} - -static __init int vmx_disabled_by_bios(void) -{ - u64 msr; - - rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); - if (msr & FEATURE_CONTROL_LOCKED) { - /* launched w/ TXT and VMX disabled */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) - && tboot_enabled()) - return 1; - /* launched w/o TXT and VMX only enabled w/ TXT */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) - && (msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX) - && !tboot_enabled()) { - printk(KERN_WARNING "kvm: disable TXT in the BIOS or " - "activate TXT before enabling KVM\n"); - return 1; - } - /* launched w/o TXT and VMX disabled */ - if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX) - && !tboot_enabled()) - return 1; - } - - return 0; -} - -static void kvm_cpu_vmxon(u64 addr) -{ - cr4_set_bits(X86_CR4_VMXE); - intel_pt_handle_vmx(1); - - asm volatile ("vmxon %0" : : "m"(addr)); -} - -static int hardware_enable(void) -{ - int cpu = raw_smp_processor_id(); - u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - u64 old, test_bits; - - if (cr4_read_shadow() & X86_CR4_VMXE) - return -EBUSY; - - /* - * This can happen if we hot-added a CPU but failed to allocate - * VP assist page for it. - */ - if (static_branch_unlikely(&enable_evmcs) && - !hv_get_vp_assist_page(cpu)) - return -EFAULT; - - INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); - INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); - spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - - /* - * Now we can enable the vmclear operation in kdump - * since the loaded_vmcss_on_cpu list on this cpu - * has been initialized. - * - * Though the cpu is not in VMX operation now, there - * is no problem to enable the vmclear operation - * for the loaded_vmcss_on_cpu list is empty! - */ - crash_enable_local_vmclear(cpu); - - rdmsrl(MSR_IA32_FEATURE_CONTROL, old); - - test_bits = FEATURE_CONTROL_LOCKED; - test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - if (tboot_enabled()) - test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX; - - if ((old & test_bits) != test_bits) { - /* enable and lock */ - wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits); - } - kvm_cpu_vmxon(phys_addr); - if (enable_ept) - ept_sync_global(); - - return 0; -} - -static void vmclear_local_loaded_vmcss(void) -{ - int cpu = raw_smp_processor_id(); - struct loaded_vmcs *v, *n; - - list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) - __loaded_vmcs_clear(v); -} - - -/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot() - * tricks. - */ -static void kvm_cpu_vmxoff(void) -{ - asm volatile (__ex("vmxoff")); - - intel_pt_handle_vmx(0); - cr4_clear_bits(X86_CR4_VMXE); -} - -static void hardware_disable(void) -{ - vmclear_local_loaded_vmcss(); - kvm_cpu_vmxoff(); -} - -static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, - u32 msr, u32 *result) -{ - u32 vmx_msr_low, vmx_msr_high; - u32 ctl = ctl_min | ctl_opt; - - rdmsr(msr, vmx_msr_low, vmx_msr_high); - - ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */ - ctl |= vmx_msr_low; /* bit == 1 in low word ==> must be one */ - - /* Ensure minimum (required) set of control bits are supported. */ - if (ctl_min & ~ctl) - return -EIO; - - *result = ctl; - return 0; -} - -static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, - struct vmx_capability *vmx_cap) -{ - u32 vmx_msr_low, vmx_msr_high; - u32 min, opt, min2, opt2; - u32 _pin_based_exec_control = 0; - u32 _cpu_based_exec_control = 0; - u32 _cpu_based_2nd_exec_control = 0; - u32 _vmexit_control = 0; - u32 _vmentry_control = 0; - - memset(vmcs_conf, 0, sizeof(*vmcs_conf)); - min = CPU_BASED_HLT_EXITING | -#ifdef CONFIG_X86_64 - CPU_BASED_CR8_LOAD_EXITING | - CPU_BASED_CR8_STORE_EXITING | -#endif - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETTING | - CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING | - CPU_BASED_INVLPG_EXITING | - CPU_BASED_RDPMC_EXITING; - - opt = CPU_BASED_TPR_SHADOW | - CPU_BASED_USE_MSR_BITMAPS | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, - &_cpu_based_exec_control) < 0) - return -EIO; -#ifdef CONFIG_X86_64 - if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) - _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING & - ~CPU_BASED_CR8_STORE_EXITING; -#endif - if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) { - min2 = 0; - opt2 = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_ENABLE_VPID | - SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST | - SECONDARY_EXEC_PAUSE_LOOP_EXITING | - SECONDARY_EXEC_DESC | - SECONDARY_EXEC_RDTSCP | - SECONDARY_EXEC_ENABLE_INVPCID | - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_SHADOW_VMCS | - SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_RDSEED_EXITING | - SECONDARY_EXEC_RDRAND_EXITING | - SECONDARY_EXEC_ENABLE_PML | - SECONDARY_EXEC_TSC_SCALING | - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | - SECONDARY_EXEC_PT_USE_GPA | - SECONDARY_EXEC_PT_CONCEAL_VMX | - SECONDARY_EXEC_ENABLE_VMFUNC | - SECONDARY_EXEC_ENCLS_EXITING; - if (adjust_vmx_controls(min2, opt2, - MSR_IA32_VMX_PROCBASED_CTLS2, - &_cpu_based_2nd_exec_control) < 0) - return -EIO; - } -#ifndef CONFIG_X86_64 - if (!(_cpu_based_2nd_exec_control & - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) - _cpu_based_exec_control &= ~CPU_BASED_TPR_SHADOW; -#endif - - if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) - _cpu_based_2nd_exec_control &= ~( - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - - rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, - &vmx_cap->ept, &vmx_cap->vpid); - - if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { - /* CR3 accesses and invlpg don't need to cause VM Exits when EPT - enabled */ - _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_INVLPG_EXITING); - } else if (vmx_cap->ept) { - vmx_cap->ept = 0; - pr_warn_once("EPT CAP should not exist if not support " - "1-setting enable EPT VM-execution control\n"); - } - if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && - vmx_cap->vpid) { - vmx_cap->vpid = 0; - pr_warn_once("VPID CAP should not exist if not support " - "1-setting enable VPID VM-execution control\n"); - } - - min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT; -#ifdef CONFIG_X86_64 - min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; -#endif - opt = VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_EXIT_LOAD_IA32_PAT | - VM_EXIT_LOAD_IA32_EFER | - VM_EXIT_CLEAR_BNDCFGS | - VM_EXIT_PT_CONCEAL_PIP | - VM_EXIT_CLEAR_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, - &_vmexit_control) < 0) - return -EIO; - - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR | - PIN_BASED_VMX_PREEMPTION_TIMER; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, - &_pin_based_exec_control) < 0) - return -EIO; - - if (cpu_has_broken_vmx_preemption_timer()) - _pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; - if (!(_cpu_based_2nd_exec_control & - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)) - _pin_based_exec_control &= ~PIN_BASED_POSTED_INTR; - - min = VM_ENTRY_LOAD_DEBUG_CONTROLS; - opt = VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | - VM_ENTRY_LOAD_IA32_PAT | - VM_ENTRY_LOAD_IA32_EFER | - VM_ENTRY_LOAD_BNDCFGS | - VM_ENTRY_PT_CONCEAL_PIP | - VM_ENTRY_LOAD_IA32_RTIT_CTL; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, - &_vmentry_control) < 0) - return -EIO; - - /* - * Some cpus support VM_{ENTRY,EXIT}_IA32_PERF_GLOBAL_CTRL but they - * can't be used due to an errata where VM Exit may incorrectly clear - * IA32_PERF_GLOBAL_CTRL[34:32]. Workaround the errata by using the - * MSR load mechanism to switch IA32_PERF_GLOBAL_CTRL. - */ - if (boot_cpu_data.x86 == 0x6) { - switch (boot_cpu_data.x86_model) { - case 26: /* AAK155 */ - case 30: /* AAP115 */ - case 37: /* AAT100 */ - case 44: /* BC86,AAY89,BD102 */ - case 46: /* BA97 */ - _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - _vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " - "does not work properly. Using workaround\n"); - break; - default: - break; - } - } - - - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); - - /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ - if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) - return -EIO; - -#ifdef CONFIG_X86_64 - /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ - if (vmx_msr_high & (1u<<16)) - return -EIO; -#endif - - /* Require Write-Back (WB) memory type for VMCS accesses. */ - if (((vmx_msr_high >> 18) & 15) != 6) - return -EIO; - - vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->order = get_order(vmcs_conf->size); - vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - - vmcs_conf->revision_id = vmx_msr_low; - - vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; - vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; - vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; - vmcs_conf->vmexit_ctrl = _vmexit_control; - vmcs_conf->vmentry_ctrl = _vmentry_control; - - if (static_branch_unlikely(&enable_evmcs)) - evmcs_sanitize_exec_ctrls(vmcs_conf); - - return 0; -} - -struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) -{ - int node = cpu_to_node(cpu); - struct page *pages; - struct vmcs *vmcs; - - pages = __alloc_pages_node(node, flags, vmcs_config.order); - if (!pages) - return NULL; - vmcs = page_address(pages); - memset(vmcs, 0, vmcs_config.size); - - /* KVM supports Enlightened VMCS v1 only */ - if (static_branch_unlikely(&enable_evmcs)) - vmcs->hdr.revision_id = KVM_EVMCS_VERSION; - else - vmcs->hdr.revision_id = vmcs_config.revision_id; - - if (shadow) - vmcs->hdr.shadow_vmcs = 1; - return vmcs; -} - -void free_vmcs(struct vmcs *vmcs) -{ - free_pages((unsigned long)vmcs, vmcs_config.order); -} - -/* - * Free a VMCS, but before that VMCLEAR it on the CPU where it was last loaded - */ -void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) -{ - if (!loaded_vmcs->vmcs) - return; - loaded_vmcs_clear(loaded_vmcs); - free_vmcs(loaded_vmcs->vmcs); - loaded_vmcs->vmcs = NULL; - if (loaded_vmcs->msr_bitmap) - free_page((unsigned long)loaded_vmcs->msr_bitmap); - WARN_ON(loaded_vmcs->shadow_vmcs != NULL); -} - -int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) -{ - loaded_vmcs->vmcs = alloc_vmcs(false); - if (!loaded_vmcs->vmcs) - return -ENOMEM; - - loaded_vmcs->shadow_vmcs = NULL; - loaded_vmcs->hv_timer_soft_disabled = false; - loaded_vmcs_init(loaded_vmcs); - - if (cpu_has_vmx_msr_bitmap()) { - loaded_vmcs->msr_bitmap = (unsigned long *) - __get_free_page(GFP_KERNEL_ACCOUNT); - if (!loaded_vmcs->msr_bitmap) - goto out_vmcs; - memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); - - if (IS_ENABLED(CONFIG_HYPERV) && - static_branch_unlikely(&enable_evmcs) && - (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { - struct hv_enlightened_vmcs *evmcs = - (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs; - - evmcs->hv_enlightenments_control.msr_bitmap = 1; - } - } - - memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); - memset(&loaded_vmcs->controls_shadow, 0, - sizeof(struct vmcs_controls_shadow)); - - return 0; - -out_vmcs: - free_loaded_vmcs(loaded_vmcs); - return -ENOMEM; -} - -static void free_kvm_area(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - free_vmcs(per_cpu(vmxarea, cpu)); - per_cpu(vmxarea, cpu) = NULL; - } -} - -static __init int alloc_kvm_area(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct vmcs *vmcs; - - vmcs = alloc_vmcs_cpu(false, cpu, GFP_KERNEL); - if (!vmcs) { - free_kvm_area(); - return -ENOMEM; - } - - /* - * When eVMCS is enabled, alloc_vmcs_cpu() sets - * vmcs->revision_id to KVM_EVMCS_VERSION instead of - * revision_id reported by MSR_IA32_VMX_BASIC. - * - * However, even though not explicitly documented by - * TLFS, VMXArea passed as VMXON argument should - * still be marked with revision_id reported by - * physical CPU. - */ - if (static_branch_unlikely(&enable_evmcs)) - vmcs->hdr.revision_id = vmcs_config.revision_id; - - per_cpu(vmxarea, cpu) = vmcs; - } - return 0; -} - -static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, - struct kvm_segment *save) -{ - if (!emulate_invalid_guest_state) { - /* - * CS and SS RPL should be equal during guest entry according - * to VMX spec, but in reality it is not always so. Since vcpu - * is in the middle of the transition from real mode to - * protected mode it is safe to assume that RPL 0 is a good - * default value. - */ - if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) - save->selector &= ~SEGMENT_RPL_MASK; - save->dpl = save->selector & SEGMENT_RPL_MASK; - save->s = 1; - } - vmx_set_segment(vcpu, save, seg); -} - -static void enter_pmode(struct kvm_vcpu *vcpu) -{ - unsigned long flags; - struct vcpu_vmx *vmx = to_vmx(vcpu); - - /* - * Update real mode segment cache. It may be not up-to-date if sement - * register was written while vcpu was in a guest mode. - */ - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); - - vmx->rmode.vm86_active = 0; - - vmx_segment_cache_clear(vmx); - - vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); - - flags = vmcs_readl(GUEST_RFLAGS); - flags &= RMODE_GUEST_OWNED_EFLAGS_BITS; - flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS; - vmcs_writel(GUEST_RFLAGS, flags); - - vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | - (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); - - update_exception_bitmap(vcpu); - - fix_pmode_seg(vcpu, VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); - fix_pmode_seg(vcpu, VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); - fix_pmode_seg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); - fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); - fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); - fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); -} - -static void fix_rmode_seg(int seg, struct kvm_segment *save) -{ - const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - struct kvm_segment var = *save; - - var.dpl = 0x3; - if (seg == VCPU_SREG_CS) - var.type = 0x3; - - if (!emulate_invalid_guest_state) { - var.selector = var.base >> 4; - var.base = var.base & 0xffff0; - var.limit = 0xffff; - var.g = 0; - var.db = 0; - var.present = 1; - var.s = 1; - var.l = 0; - var.unusable = 0; - var.type = 0x3; - var.avl = 0; - if (save->base & 0xf) - printk_once(KERN_WARNING "kvm: segment base is not " - "paragraph aligned when entering " - "protected mode (seg=%d)", seg); - } - - vmcs_write16(sf->selector, var.selector); - vmcs_writel(sf->base, var.base); - vmcs_write32(sf->limit, var.limit); - vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); -} - -static void enter_rmode(struct kvm_vcpu *vcpu) -{ - unsigned long flags; - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_vmx *kvm_vmx = to_kvm_vmx(vcpu->kvm); - - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_SS], VCPU_SREG_SS); - vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_CS], VCPU_SREG_CS); - - vmx->rmode.vm86_active = 1; - - /* - * Very old userspace does not call KVM_SET_TSS_ADDR before entering - * vcpu. Warn the user that an update is overdue. - */ - if (!kvm_vmx->tss_addr) - printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " - "called before entering vcpu\n"); - - vmx_segment_cache_clear(vmx); - - vmcs_writel(GUEST_TR_BASE, kvm_vmx->tss_addr); - vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); - vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); - - flags = vmcs_readl(GUEST_RFLAGS); - vmx->rmode.save_rflags = flags; - - flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM; - - vmcs_writel(GUEST_RFLAGS, flags); - vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); - update_exception_bitmap(vcpu); - - fix_rmode_seg(VCPU_SREG_SS, &vmx->rmode.segs[VCPU_SREG_SS]); - fix_rmode_seg(VCPU_SREG_CS, &vmx->rmode.segs[VCPU_SREG_CS]); - fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]); - fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); - fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); - fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); - - kvm_mmu_reset_context(vcpu); -} - -void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); - - if (!msr) - return; - - vcpu->arch.efer = efer; - if (efer & EFER_LMA) { - vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); - msr->data = efer; - } else { - vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); - - msr->data = efer & ~EFER_LME; - } - setup_msrs(vmx); -} - -#ifdef CONFIG_X86_64 - -static void enter_lmode(struct kvm_vcpu *vcpu) -{ - u32 guest_tr_ar; - - vmx_segment_cache_clear(to_vmx(vcpu)); - - guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); - if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) { - pr_debug_ratelimited("%s: tss fixup for long mode. \n", - __func__); - vmcs_write32(GUEST_TR_AR_BYTES, - (guest_tr_ar & ~VMX_AR_TYPE_MASK) - | VMX_AR_TYPE_BUSY_64_TSS); - } - vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); -} - -static void exit_lmode(struct kvm_vcpu *vcpu) -{ - vm_entry_controls_clearbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); - vmx_set_efer(vcpu, vcpu->arch.efer & ~EFER_LMA); -} - -#endif - -static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) -{ - int vpid = to_vmx(vcpu)->vpid; - - if (!vpid_sync_vcpu_addr(vpid, addr)) - vpid_sync_context(vpid); - - /* - * If VPIDs are not supported or enabled, then the above is a no-op. - * But we don't really need a TLB flush in that case anyway, because - * each VM entry/exit includes an implicit flush when VPID is 0. - */ -} - -static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) -{ - ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; - - vcpu->arch.cr0 &= ~cr0_guest_owned_bits; - vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits; -} - -static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) -{ - ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; - - vcpu->arch.cr4 &= ~cr4_guest_owned_bits; - vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits; -} - -static void ept_load_pdptrs(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - - if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR)) - return; - - if (is_pae_paging(vcpu)) { - vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]); - vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]); - vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]); - vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]); - } -} - -void ept_save_pdptrs(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - - if (is_pae_paging(vcpu)) { - mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); - mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); - mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); - mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); - } - - kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); -} - -static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, - unsigned long cr0, - struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) - vmx_cache_reg(vcpu, VCPU_EXREG_CR3); - if (!(cr0 & X86_CR0_PG)) { - /* From paging/starting to nonpaging */ - exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING); - vcpu->arch.cr0 = cr0; - vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); - } else if (!is_paging(vcpu)) { - /* From nonpaging to paging */ - exec_controls_clearbit(vmx, CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_CR3_STORE_EXITING); - vcpu->arch.cr0 = cr0; - vmx_set_cr4(vcpu, kvm_read_cr4(vcpu)); - } - - if (!(cr0 & X86_CR0_WP)) - *hw_cr0 &= ~X86_CR0_WP; -} - -void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long hw_cr0; - - hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF); - if (enable_unrestricted_guest) - hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST; - else { - hw_cr0 |= KVM_VM_CR0_ALWAYS_ON; - - if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) - enter_pmode(vcpu); - - if (!vmx->rmode.vm86_active && !(cr0 & X86_CR0_PE)) - enter_rmode(vcpu); - } - -#ifdef CONFIG_X86_64 - if (vcpu->arch.efer & EFER_LME) { - if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) - enter_lmode(vcpu); - if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) - exit_lmode(vcpu); - } -#endif - - if (enable_ept && !enable_unrestricted_guest) - ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); - - vmcs_writel(CR0_READ_SHADOW, cr0); - vmcs_writel(GUEST_CR0, hw_cr0); - vcpu->arch.cr0 = cr0; - - /* depends on vcpu->arch.cr0 to be set to a new value */ - vmx->emulation_required = emulation_required(vcpu); -} - -static int get_ept_level(struct kvm_vcpu *vcpu) -{ - if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) - return 5; - return 4; -} - -u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) -{ - u64 eptp = VMX_EPTP_MT_WB; - - eptp |= (get_ept_level(vcpu) == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4; - - if (enable_ept_ad_bits && - (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu))) - eptp |= VMX_EPTP_AD_ENABLE_BIT; - eptp |= (root_hpa & PAGE_MASK); - - return eptp; -} - -void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) -{ - struct kvm *kvm = vcpu->kvm; - bool update_guest_cr3 = true; - unsigned long guest_cr3; - u64 eptp; - - guest_cr3 = cr3; - if (enable_ept) { - eptp = construct_eptp(vcpu, cr3); - vmcs_write64(EPT_POINTER, eptp); - - if (kvm_x86_ops->tlb_remote_flush) { - spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock); - to_vmx(vcpu)->ept_pointer = eptp; - to_kvm_vmx(kvm)->ept_pointers_match - = EPT_POINTERS_CHECK; - spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); - } - - /* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */ - if (is_guest_mode(vcpu)) - update_guest_cr3 = false; - else if (!enable_unrestricted_guest && !is_paging(vcpu)) - guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; - else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - guest_cr3 = vcpu->arch.cr3; - else /* vmcs01.GUEST_CR3 is already up-to-date. */ - update_guest_cr3 = false; - ept_load_pdptrs(vcpu); - } - - if (update_guest_cr3) - vmcs_writel(GUEST_CR3, guest_cr3); -} - -int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * Pass through host's Machine Check Enable value to hw_cr4, which - * is in force while we are in guest mode. Do not let guests control - * this bit, even if host CR4.MCE == 0. - */ - unsigned long hw_cr4; - - hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE); - if (enable_unrestricted_guest) - hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST; - else if (vmx->rmode.vm86_active) - hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON; - else - hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; - - if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) { - if (cr4 & X86_CR4_UMIP) { - secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC); - hw_cr4 &= ~X86_CR4_UMIP; - } else if (!is_guest_mode(vcpu) || - !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) { - secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_DESC); - } - } - - if (cr4 & X86_CR4_VMXE) { - /* - * To use VMXON (and later other VMX instructions), a guest - * must first be able to turn on cr4.VMXE (see handle_vmon()). - * So basically the check on whether to allow nested VMX - * is here. We operate under the default treatment of SMM, - * so VMX cannot be enabled under SMM. - */ - if (!nested_vmx_allowed(vcpu) || is_smm(vcpu)) - return 1; - } - - if (vmx->nested.vmxon && !nested_cr4_valid(vcpu, cr4)) - return 1; - - vcpu->arch.cr4 = cr4; - - if (!enable_unrestricted_guest) { - if (enable_ept) { - if (!is_paging(vcpu)) { - hw_cr4 &= ~X86_CR4_PAE; - hw_cr4 |= X86_CR4_PSE; - } else if (!(cr4 & X86_CR4_PAE)) { - hw_cr4 &= ~X86_CR4_PAE; - } - } - - /* - * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in - * hardware. To emulate this behavior, SMEP/SMAP/PKU needs - * to be manually disabled when guest switches to non-paging - * mode. - * - * If !enable_unrestricted_guest, the CPU is always running - * with CR0.PG=1 and CR4 needs to be modified. - * If enable_unrestricted_guest, the CPU automatically - * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0. - */ - if (!is_paging(vcpu)) - hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); - } - - vmcs_writel(CR4_READ_SHADOW, cr4); - vmcs_writel(GUEST_CR4, hw_cr4); - return 0; -} - -void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 ar; - - if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { - *var = vmx->rmode.segs[seg]; - if (seg == VCPU_SREG_TR - || var->selector == vmx_read_guest_seg_selector(vmx, seg)) - return; - var->base = vmx_read_guest_seg_base(vmx, seg); - var->selector = vmx_read_guest_seg_selector(vmx, seg); - return; - } - var->base = vmx_read_guest_seg_base(vmx, seg); - var->limit = vmx_read_guest_seg_limit(vmx, seg); - var->selector = vmx_read_guest_seg_selector(vmx, seg); - ar = vmx_read_guest_seg_ar(vmx, seg); - var->unusable = (ar >> 16) & 1; - var->type = ar & 15; - var->s = (ar >> 4) & 1; - var->dpl = (ar >> 5) & 3; - /* - * Some userspaces do not preserve unusable property. Since usable - * segment has to be present according to VMX spec we can use present - * property to amend userspace bug by making unusable segment always - * nonpresent. vmx_segment_access_rights() already marks nonpresent - * segment as unusable. - */ - var->present = !var->unusable; - var->avl = (ar >> 12) & 1; - var->l = (ar >> 13) & 1; - var->db = (ar >> 14) & 1; - var->g = (ar >> 15) & 1; -} - -static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment s; - - if (to_vmx(vcpu)->rmode.vm86_active) { - vmx_get_segment(vcpu, &s, seg); - return s.base; - } - return vmx_read_guest_seg_base(to_vmx(vcpu), seg); -} - -int vmx_get_cpl(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (unlikely(vmx->rmode.vm86_active)) - return 0; - else { - int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); - return VMX_AR_DPL(ar); - } -} - -static u32 vmx_segment_access_rights(struct kvm_segment *var) -{ - u32 ar; - - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } - - return ar; -} - -void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - - vmx_segment_cache_clear(vmx); - - if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { - vmx->rmode.segs[seg] = *var; - if (seg == VCPU_SREG_TR) - vmcs_write16(sf->selector, var->selector); - else if (var->s) - fix_rmode_seg(seg, &vmx->rmode.segs[seg]); - goto out; - } - - vmcs_writel(sf->base, var->base); - vmcs_write32(sf->limit, var->limit); - vmcs_write16(sf->selector, var->selector); - - /* - * Fix the "Accessed" bit in AR field of segment registers for older - * qemu binaries. - * IA32 arch specifies that at the time of processor reset the - * "Accessed" bit in the AR field of segment registers is 1. And qemu - * is setting it to 0 in the userland code. This causes invalid guest - * state vmexit when "unrestricted guest" mode is turned on. - * Fix for this setup issue in cpu_reset is being pushed in the qemu - * tree. Newer qemu binaries with that qemu fix would not need this - * kvm hack. - */ - if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR)) - var->type |= 0x1; /* Accessed */ - - vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var)); - -out: - vmx->emulation_required = emulation_required(vcpu); -} - -static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) -{ - u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS); - - *db = (ar >> 14) & 1; - *l = (ar >> 13) & 1; -} - -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) -{ - dt->size = vmcs_read32(GUEST_IDTR_LIMIT); - dt->address = vmcs_readl(GUEST_IDTR_BASE); -} - -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) -{ - vmcs_write32(GUEST_IDTR_LIMIT, dt->size); - vmcs_writel(GUEST_IDTR_BASE, dt->address); -} - -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) -{ - dt->size = vmcs_read32(GUEST_GDTR_LIMIT); - dt->address = vmcs_readl(GUEST_GDTR_BASE); -} - -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) -{ - vmcs_write32(GUEST_GDTR_LIMIT, dt->size); - vmcs_writel(GUEST_GDTR_BASE, dt->address); -} - -static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment var; - u32 ar; - - vmx_get_segment(vcpu, &var, seg); - var.dpl = 0x3; - if (seg == VCPU_SREG_CS) - var.type = 0x3; - ar = vmx_segment_access_rights(&var); - - if (var.base != (var.selector << 4)) - return false; - if (var.limit != 0xffff) - return false; - if (ar != 0xf3) - return false; - - return true; -} - -static bool code_segment_valid(struct kvm_vcpu *vcpu) -{ - struct kvm_segment cs; - unsigned int cs_rpl; - - vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); - cs_rpl = cs.selector & SEGMENT_RPL_MASK; - - if (cs.unusable) - return false; - if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK)) - return false; - if (!cs.s) - return false; - if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) { - if (cs.dpl > cs_rpl) - return false; - } else { - if (cs.dpl != cs_rpl) - return false; - } - if (!cs.present) - return false; - - /* TODO: Add Reserved field check, this'll require a new member in the kvm_segment_field structure */ - return true; -} - -static bool stack_segment_valid(struct kvm_vcpu *vcpu) -{ - struct kvm_segment ss; - unsigned int ss_rpl; - - vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - ss_rpl = ss.selector & SEGMENT_RPL_MASK; - - if (ss.unusable) - return true; - if (ss.type != 3 && ss.type != 7) - return false; - if (!ss.s) - return false; - if (ss.dpl != ss_rpl) /* DPL != RPL */ - return false; - if (!ss.present) - return false; - - return true; -} - -static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment var; - unsigned int rpl; - - vmx_get_segment(vcpu, &var, seg); - rpl = var.selector & SEGMENT_RPL_MASK; - - if (var.unusable) - return true; - if (!var.s) - return false; - if (!var.present) - return false; - if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) { - if (var.dpl < rpl) /* DPL < RPL */ - return false; - } - - /* TODO: Add other members to kvm_segment_field to allow checking for other access - * rights flags - */ - return true; -} - -static bool tr_valid(struct kvm_vcpu *vcpu) -{ - struct kvm_segment tr; - - vmx_get_segment(vcpu, &tr, VCPU_SREG_TR); - - if (tr.unusable) - return false; - if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */ - return false; - if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ - return false; - if (!tr.present) - return false; - - return true; -} - -static bool ldtr_valid(struct kvm_vcpu *vcpu) -{ - struct kvm_segment ldtr; - - vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR); - - if (ldtr.unusable) - return true; - if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */ - return false; - if (ldtr.type != 2) - return false; - if (!ldtr.present) - return false; - - return true; -} - -static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) -{ - struct kvm_segment cs, ss; - - vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); - vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - - return ((cs.selector & SEGMENT_RPL_MASK) == - (ss.selector & SEGMENT_RPL_MASK)); -} - -/* - * Check if guest state is valid. Returns true if valid, false if - * not. - * We assume that registers are always usable - */ -static bool guest_state_valid(struct kvm_vcpu *vcpu) -{ - if (enable_unrestricted_guest) - return true; - - /* real mode guest state checks */ - if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) { - if (!rmode_segment_valid(vcpu, VCPU_SREG_CS)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_SS)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_DS)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_ES)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_FS)) - return false; - if (!rmode_segment_valid(vcpu, VCPU_SREG_GS)) - return false; - } else { - /* protected mode guest state checks */ - if (!cs_ss_rpl_check(vcpu)) - return false; - if (!code_segment_valid(vcpu)) - return false; - if (!stack_segment_valid(vcpu)) - return false; - if (!data_segment_valid(vcpu, VCPU_SREG_DS)) - return false; - if (!data_segment_valid(vcpu, VCPU_SREG_ES)) - return false; - if (!data_segment_valid(vcpu, VCPU_SREG_FS)) - return false; - if (!data_segment_valid(vcpu, VCPU_SREG_GS)) - return false; - if (!tr_valid(vcpu)) - return false; - if (!ldtr_valid(vcpu)) - return false; - } - /* TODO: - * - Add checks on RIP - * - Add checks on RFLAGS - */ - - return true; -} - -static int init_rmode_tss(struct kvm *kvm) -{ - gfn_t fn; - u16 data = 0; - int idx, r; - - idx = srcu_read_lock(&kvm->srcu); - fn = to_kvm_vmx(kvm)->tss_addr >> PAGE_SHIFT; - r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); - if (r < 0) - goto out; - data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE; - r = kvm_write_guest_page(kvm, fn++, &data, - TSS_IOPB_BASE_OFFSET, sizeof(u16)); - if (r < 0) - goto out; - r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE); - if (r < 0) - goto out; - r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); - if (r < 0) - goto out; - data = ~0; - r = kvm_write_guest_page(kvm, fn, &data, - RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1, - sizeof(u8)); -out: - srcu_read_unlock(&kvm->srcu, idx); - return r; -} - -static int init_rmode_identity_map(struct kvm *kvm) -{ - struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm); - int i, idx, r = 0; - kvm_pfn_t identity_map_pfn; - u32 tmp; - - /* Protect kvm_vmx->ept_identity_pagetable_done. */ - mutex_lock(&kvm->slots_lock); - - if (likely(kvm_vmx->ept_identity_pagetable_done)) - goto out2; - - if (!kvm_vmx->ept_identity_map_addr) - kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; - identity_map_pfn = kvm_vmx->ept_identity_map_addr >> PAGE_SHIFT; - - r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, - kvm_vmx->ept_identity_map_addr, PAGE_SIZE); - if (r < 0) - goto out2; - - idx = srcu_read_lock(&kvm->srcu); - r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE); - if (r < 0) - goto out; - /* Set up identity-mapping pagetable for EPT in real mode */ - for (i = 0; i < PT32_ENT_PER_PAGE; i++) { - tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | - _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); - r = kvm_write_guest_page(kvm, identity_map_pfn, - &tmp, i * sizeof(tmp), sizeof(tmp)); - if (r < 0) - goto out; - } - kvm_vmx->ept_identity_pagetable_done = true; - -out: - srcu_read_unlock(&kvm->srcu, idx); - -out2: - mutex_unlock(&kvm->slots_lock); - return r; -} - -static void seg_setup(int seg) -{ - const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - unsigned int ar; - - vmcs_write16(sf->selector, 0); - vmcs_writel(sf->base, 0); - vmcs_write32(sf->limit, 0xffff); - ar = 0x93; - if (seg == VCPU_SREG_CS) - ar |= 0x08; /* code segment */ - - vmcs_write32(sf->ar_bytes, ar); -} - -static int alloc_apic_access_page(struct kvm *kvm) -{ - struct page *page; - int r = 0; - - mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_page_done) - goto out; - r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); - if (r) - goto out; - - page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) { - r = -EFAULT; - goto out; - } - - /* - * Do not pin the page in memory, so that memory hot-unplug - * is able to migrate it. - */ - put_page(page); - kvm->arch.apic_access_page_done = true; -out: - mutex_unlock(&kvm->slots_lock); - return r; -} - -int allocate_vpid(void) -{ - int vpid; - - if (!enable_vpid) - return 0; - spin_lock(&vmx_vpid_lock); - vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); - if (vpid < VMX_NR_VPIDS) - __set_bit(vpid, vmx_vpid_bitmap); - else - vpid = 0; - spin_unlock(&vmx_vpid_lock); - return vpid; -} - -void free_vpid(int vpid) -{ - if (!enable_vpid || vpid == 0) - return; - spin_lock(&vmx_vpid_lock); - __clear_bit(vpid, vmx_vpid_bitmap); - spin_unlock(&vmx_vpid_lock); -} - -static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) -{ - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) - return; - - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); - - /* - * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals - * have the write-low and read-high bitmap offsets the wrong way round. - * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. - */ - if (msr <= 0x1fff) { - if (type & MSR_TYPE_R) - /* read-low */ - __clear_bit(msr, msr_bitmap + 0x000 / f); - - if (type & MSR_TYPE_W) - /* write-low */ - __clear_bit(msr, msr_bitmap + 0x800 / f); - - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - if (type & MSR_TYPE_R) - /* read-high */ - __clear_bit(msr, msr_bitmap + 0x400 / f); - - if (type & MSR_TYPE_W) - /* write-high */ - __clear_bit(msr, msr_bitmap + 0xc00 / f); - - } -} - -static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type) -{ - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) - return; - - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); - - /* - * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals - * have the write-low and read-high bitmap offsets the wrong way round. - * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff. - */ - if (msr <= 0x1fff) { - if (type & MSR_TYPE_R) - /* read-low */ - __set_bit(msr, msr_bitmap + 0x000 / f); - - if (type & MSR_TYPE_W) - /* write-low */ - __set_bit(msr, msr_bitmap + 0x800 / f); - - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - if (type & MSR_TYPE_R) - /* read-high */ - __set_bit(msr, msr_bitmap + 0x400 / f); - - if (type & MSR_TYPE_W) - /* write-high */ - __set_bit(msr, msr_bitmap + 0xc00 / f); - - } -} - -static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap, - u32 msr, int type, bool value) -{ - if (value) - vmx_enable_intercept_for_msr(msr_bitmap, msr, type); - else - vmx_disable_intercept_for_msr(msr_bitmap, msr, type); -} - -static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) -{ - u8 mode = 0; - - if (cpu_has_secondary_exec_ctrls() && - (secondary_exec_controls_get(to_vmx(vcpu)) & - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { - mode |= MSR_BITMAP_MODE_X2APIC; - if (enable_apicv && kvm_vcpu_apicv_active(vcpu)) - mode |= MSR_BITMAP_MODE_X2APIC_APICV; - } - - return mode; -} - -static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap, - u8 mode) -{ - int msr; - - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0; - msr_bitmap[word + (0x800 / sizeof(long))] = ~0; - } - - if (mode & MSR_BITMAP_MODE_X2APIC) { - /* - * TPR reads and writes can be virtualized even if virtual interrupt - * delivery is not in use. - */ - vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW); - if (mode & MSR_BITMAP_MODE_X2APIC_APICV) { - vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W); - vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W); - } - } -} - -void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; - u8 mode = vmx_msr_bitmap_mode(vcpu); - u8 changed = mode ^ vmx->msr_bitmap_mode; - - if (!changed) - return; - - if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) - vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); - - vmx->msr_bitmap_mode = mode; -} - -void pt_update_intercept_for_msr(struct vcpu_vmx *vmx) -{ - unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; - bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN); - u32 i; - - vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_STATUS, - MSR_TYPE_RW, flag); - vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_BASE, - MSR_TYPE_RW, flag); - vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_MASK, - MSR_TYPE_RW, flag); - vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_CR3_MATCH, - MSR_TYPE_RW, flag); - for (i = 0; i < vmx->pt_desc.addr_range; i++) { - vmx_set_intercept_for_msr(msr_bitmap, - MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag); - vmx_set_intercept_for_msr(msr_bitmap, - MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag); - } -} - -static bool vmx_get_enable_apicv(struct kvm *kvm) -{ - return enable_apicv; -} - -static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - void *vapic_page; - u32 vppr; - int rvi; - - if (WARN_ON_ONCE(!is_guest_mode(vcpu)) || - !nested_cpu_has_vid(get_vmcs12(vcpu)) || - WARN_ON_ONCE(!vmx->nested.virtual_apic_map.gfn)) - return false; - - rvi = vmx_get_rvi(); - - vapic_page = vmx->nested.virtual_apic_map.hva; - vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); - - return ((rvi & 0xf0) > (vppr & 0xf0)); -} - -static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, - bool nested) -{ -#ifdef CONFIG_SMP - int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR; - - if (vcpu->mode == IN_GUEST_MODE) { - /* - * The vector of interrupt to be delivered to vcpu had - * been set in PIR before this function. - * - * Following cases will be reached in this block, and - * we always send a notification event in all cases as - * explained below. - * - * Case 1: vcpu keeps in non-root mode. Sending a - * notification event posts the interrupt to vcpu. - * - * Case 2: vcpu exits to root mode and is still - * runnable. PIR will be synced to vIRR before the - * next vcpu entry. Sending a notification event in - * this case has no effect, as vcpu is not in root - * mode. - * - * Case 3: vcpu exits to root mode and is blocked. - * vcpu_block() has already synced PIR to vIRR and - * never blocks vcpu if vIRR is not cleared. Therefore, - * a blocked vcpu here does not wait for any requested - * interrupts in PIR, and sending a notification event - * which has no effect is safe here. - */ - - apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); - return true; - } -#endif - return false; -} - -static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, - int vector) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (is_guest_mode(vcpu) && - vector == vmx->nested.posted_intr_nv) { - /* - * If a posted intr is not recognized by hardware, - * we will accomplish it in the next vmentry. - */ - vmx->nested.pi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); - /* the PIR and ON have been set by L1. */ - if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true)) - kvm_vcpu_kick(vcpu); - return 0; - } - return -1; -} -/* - * Send interrupt to vcpu via posted interrupt way. - * 1. If target vcpu is running(non-root mode), send posted interrupt - * notification to vcpu and hardware will sync PIR to vIRR atomically. - * 2. If target vcpu isn't running(root mode), kick it to pick up the - * interrupt from PIR in next vmentry. - */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - int r; - - r = vmx_deliver_nested_posted_interrupt(vcpu, vector); - if (!r) - return; - - if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; - - /* If a previous notification has sent the IPI, nothing to do. */ - if (pi_test_and_set_on(&vmx->pi_desc)) - return; - - if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) - kvm_vcpu_kick(vcpu); -} - -/* - * Set up the vmcs's constant host-state fields, i.e., host-state fields that - * will not change in the lifetime of the guest. - * Note that host-state that does change is set elsewhere. E.g., host-state - * that is set differently for each CPU is set in vmx_vcpu_load(), not here. - */ -void vmx_set_constant_host_state(struct vcpu_vmx *vmx) -{ - u32 low32, high32; - unsigned long tmpl; - unsigned long cr0, cr3, cr4; - - cr0 = read_cr0(); - WARN_ON(cr0 & X86_CR0_TS); - vmcs_writel(HOST_CR0, cr0); /* 22.2.3 */ - - /* - * Save the most likely value for this task's CR3 in the VMCS. - * We can't use __get_current_cr3_fast() because we're not atomic. - */ - cr3 = __read_cr3(); - vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->loaded_vmcs->host_state.cr3 = cr3; - - /* Save the most likely value for this task's CR4 in the VMCS. */ - cr4 = cr4_read_shadow(); - vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->loaded_vmcs->host_state.cr4 = cr4; - - vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ -#ifdef CONFIG_X86_64 - /* - * Load null selectors, so we can avoid reloading them in - * vmx_prepare_switch_to_host(), in case userspace uses - * the null selectors too (the expected case). - */ - vmcs_write16(HOST_DS_SELECTOR, 0); - vmcs_write16(HOST_ES_SELECTOR, 0); -#else - vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ - vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */ -#endif - vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ - vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ - - vmcs_writel(HOST_IDTR_BASE, host_idt_base); /* 22.2.4 */ - - vmcs_writel(HOST_RIP, (unsigned long)vmx_vmexit); /* 22.2.5 */ - - rdmsr(MSR_IA32_SYSENTER_CS, low32, high32); - vmcs_write32(HOST_IA32_SYSENTER_CS, low32); - rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); - vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ - - if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) { - rdmsr(MSR_IA32_CR_PAT, low32, high32); - vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32)); - } - - if (cpu_has_load_ia32_efer()) - vmcs_write64(HOST_IA32_EFER, host_efer); -} - -void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) -{ - vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS; - if (enable_ept) - vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE; - if (is_guest_mode(&vmx->vcpu)) - vmx->vcpu.arch.cr4_guest_owned_bits &= - ~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask; - vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits); -} - -u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) -{ - u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; - - if (!kvm_vcpu_apicv_active(&vmx->vcpu)) - pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; - - if (!enable_vnmi) - pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS; - - if (!enable_preemption_timer) - pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER; - - return pin_based_exec_ctrl; -} - -static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - if (cpu_has_secondary_exec_ctrls()) { - if (kvm_vcpu_apicv_active(vcpu)) - secondary_exec_controls_setbit(vmx, - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - else - secondary_exec_controls_clearbit(vmx, - SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - } - - if (cpu_has_vmx_msr_bitmap()) - vmx_update_msr_bitmap(vcpu); -} - -u32 vmx_exec_control(struct vcpu_vmx *vmx) -{ - u32 exec_control = vmcs_config.cpu_based_exec_ctrl; - - if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) - exec_control &= ~CPU_BASED_MOV_DR_EXITING; - - if (!cpu_need_tpr_shadow(&vmx->vcpu)) { - exec_control &= ~CPU_BASED_TPR_SHADOW; -#ifdef CONFIG_X86_64 - exec_control |= CPU_BASED_CR8_STORE_EXITING | - CPU_BASED_CR8_LOAD_EXITING; -#endif - } - if (!enable_ept) - exec_control |= CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_CR3_LOAD_EXITING | - CPU_BASED_INVLPG_EXITING; - if (kvm_mwait_in_guest(vmx->vcpu.kvm)) - exec_control &= ~(CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING); - if (kvm_hlt_in_guest(vmx->vcpu.kvm)) - exec_control &= ~CPU_BASED_HLT_EXITING; - return exec_control; -} - - -static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) -{ - struct kvm_vcpu *vcpu = &vmx->vcpu; - - u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; - - if (pt_mode == PT_MODE_SYSTEM) - exec_control &= ~(SECONDARY_EXEC_PT_USE_GPA | SECONDARY_EXEC_PT_CONCEAL_VMX); - if (!cpu_need_virtualize_apic_accesses(vcpu)) - exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - if (vmx->vpid == 0) - exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; - if (!enable_ept) { - exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; - enable_unrestricted_guest = 0; - } - if (!enable_unrestricted_guest) - exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; - if (kvm_pause_in_guest(vmx->vcpu.kvm)) - exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; - if (!kvm_vcpu_apicv_active(vcpu)) - exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); - exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; - - /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, - * in vmx_set_cr4. */ - exec_control &= ~SECONDARY_EXEC_DESC; - - /* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD - (handle_vmptrld). - We can NOT enable shadow_vmcs here because we don't have yet - a current VMCS12 - */ - exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - - if (!enable_pml) - exec_control &= ~SECONDARY_EXEC_ENABLE_PML; - - if (vmx_xsaves_supported()) { - /* Exposing XSAVES only when XSAVE is exposed */ - bool xsaves_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVES); - - vcpu->arch.xsaves_enabled = xsaves_enabled; - - if (!xsaves_enabled) - exec_control &= ~SECONDARY_EXEC_XSAVES; - - if (nested) { - if (xsaves_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_XSAVES; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_XSAVES; - } - } - - if (vmx_rdtscp_supported()) { - bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP); - if (!rdtscp_enabled) - exec_control &= ~SECONDARY_EXEC_RDTSCP; - - if (nested) { - if (rdtscp_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_RDTSCP; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_RDTSCP; - } - } - - if (vmx_invpcid_supported()) { - /* Exposing INVPCID only when PCID is exposed */ - bool invpcid_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) && - guest_cpuid_has(vcpu, X86_FEATURE_PCID); - - if (!invpcid_enabled) { - exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; - guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID); - } - - if (nested) { - if (invpcid_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_INVPCID; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_ENABLE_INVPCID; - } - } - - if (vmx_rdrand_supported()) { - bool rdrand_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDRAND); - if (rdrand_enabled) - exec_control &= ~SECONDARY_EXEC_RDRAND_EXITING; - - if (nested) { - if (rdrand_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_RDRAND_EXITING; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_RDRAND_EXITING; - } - } - - if (vmx_rdseed_supported()) { - bool rdseed_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDSEED); - if (rdseed_enabled) - exec_control &= ~SECONDARY_EXEC_RDSEED_EXITING; - - if (nested) { - if (rdseed_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_RDSEED_EXITING; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_RDSEED_EXITING; - } - } - - if (vmx_waitpkg_supported()) { - bool waitpkg_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_WAITPKG); - - if (!waitpkg_enabled) - exec_control &= ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; - - if (nested) { - if (waitpkg_enabled) - vmx->nested.msrs.secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; - else - vmx->nested.msrs.secondary_ctls_high &= - ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; - } - } - - vmx->secondary_exec_control = exec_control; -} - -static void ept_set_mmio_spte_mask(void) -{ - /* - * EPT Misconfigurations can be generated if the value of bits 2:0 - * of an EPT paging-structure entry is 110b (write/execute). - */ - kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, - VMX_EPT_MISCONFIG_WX_VALUE, 0); -} - -#define VMX_XSS_EXIT_BITMAP 0 - -/* - * Noting that the initialization of Guest-state Area of VMCS is in - * vmx_vcpu_reset(). - */ -static void init_vmcs(struct vcpu_vmx *vmx) -{ - if (nested) - nested_vmx_set_vmcs_shadowing_bitmap(); - - if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap)); - - vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ - - /* Control */ - pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); - - exec_controls_set(vmx, vmx_exec_control(vmx)); - - if (cpu_has_secondary_exec_ctrls()) { - vmx_compute_secondary_exec_control(vmx); - secondary_exec_controls_set(vmx, vmx->secondary_exec_control); - } - - if (kvm_vcpu_apicv_active(&vmx->vcpu)) { - vmcs_write64(EOI_EXIT_BITMAP0, 0); - vmcs_write64(EOI_EXIT_BITMAP1, 0); - vmcs_write64(EOI_EXIT_BITMAP2, 0); - vmcs_write64(EOI_EXIT_BITMAP3, 0); - - vmcs_write16(GUEST_INTR_STATUS, 0); - - vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); - vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); - } - - if (!kvm_pause_in_guest(vmx->vcpu.kvm)) { - vmcs_write32(PLE_GAP, ple_gap); - vmx->ple_window = ple_window; - vmx->ple_window_dirty = true; - } - - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0); - vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ - - vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */ - vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */ - vmx_set_constant_host_state(vmx); - vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */ - vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */ - - if (cpu_has_vmx_vmfunc()) - vmcs_write64(VM_FUNCTION_CONTROL, 0); - - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); - vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val)); - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); - vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val)); - - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) - vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - - vm_exit_controls_set(vmx, vmx_vmexit_ctrl()); - - /* 22.2.1, 20.8.1 */ - vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - - vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; - vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); - - set_cr4_guest_host_mask(vmx); - - if (vmx->vpid != 0) - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - - if (vmx_xsaves_supported()) - vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP); - - if (enable_pml) { - vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); - } - - if (cpu_has_vmx_encls_vmexit()) - vmcs_write64(ENCLS_EXITING_BITMAP, -1ull); - - if (pt_mode == PT_MODE_HOST_GUEST) { - memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc)); - /* Bit[6~0] are forced to 1, writes are ignored. */ - vmx->pt_desc.guest.output_mask = 0x7F; - vmcs_write64(GUEST_IA32_RTIT_CTL, 0); - } -} - -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct msr_data apic_base_msr; - u64 cr0; - - vmx->rmode.vm86_active = 0; - vmx->spec_ctrl = 0; - - vmx->msr_ia32_umwait_control = 0; - - vcpu->arch.microcode_version = 0x100000000ULL; - vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); - vmx->hv_deadline_tsc = -1; - kvm_set_cr8(vcpu, 0); - - if (!init_event) { - apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(vcpu)) - apic_base_msr.data |= MSR_IA32_APICBASE_BSP; - apic_base_msr.host_initiated = true; - kvm_set_apic_base(vcpu, &apic_base_msr); - } - - vmx_segment_cache_clear(vmx); - - seg_setup(VCPU_SREG_CS); - vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); - - seg_setup(VCPU_SREG_DS); - seg_setup(VCPU_SREG_ES); - seg_setup(VCPU_SREG_FS); - seg_setup(VCPU_SREG_GS); - seg_setup(VCPU_SREG_SS); - - vmcs_write16(GUEST_TR_SELECTOR, 0); - vmcs_writel(GUEST_TR_BASE, 0); - vmcs_write32(GUEST_TR_LIMIT, 0xffff); - vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); - - vmcs_write16(GUEST_LDTR_SELECTOR, 0); - vmcs_writel(GUEST_LDTR_BASE, 0); - vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); - vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - - if (!init_event) { - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - } - - kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); - kvm_rip_write(vcpu, 0xfff0); - - vmcs_writel(GUEST_GDTR_BASE, 0); - vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); - - vmcs_writel(GUEST_IDTR_BASE, 0); - vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); - - vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); - vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); - if (kvm_mpx_supported()) - vmcs_write64(GUEST_BNDCFGS, 0); - - setup_msrs(vmx); - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - - if (cpu_has_vmx_tpr_shadow() && !init_event) { - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (cpu_need_tpr_shadow(vcpu)) - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - __pa(vcpu->arch.apic->regs)); - vmcs_write32(TPR_THRESHOLD, 0); - } - - kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - - cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx->vcpu.arch.cr0 = cr0; - vmx_set_cr0(vcpu, cr0); /* enter rmode */ - vmx_set_cr4(vcpu, 0); - vmx_set_efer(vcpu, 0); - - update_exception_bitmap(vcpu); - - vpid_sync_context(vmx->vpid); - if (init_event) - vmx_clear_hlt(vcpu); -} - -static void enable_irq_window(struct kvm_vcpu *vcpu) -{ - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); -} - -static void enable_nmi_window(struct kvm_vcpu *vcpu) -{ - if (!enable_vnmi || - vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { - enable_irq_window(vcpu); - return; - } - - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); -} - -static void vmx_inject_irq(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - uint32_t intr; - int irq = vcpu->arch.interrupt.nr; - - trace_kvm_inj_virq(irq); - - ++vcpu->stat.irq_injections; - if (vmx->rmode.vm86_active) { - int inc_eip = 0; - if (vcpu->arch.interrupt.soft) - inc_eip = vcpu->arch.event_exit_inst_len; - kvm_inject_realmode_interrupt(vcpu, irq, inc_eip); - return; - } - intr = irq | INTR_INFO_VALID_MASK; - if (vcpu->arch.interrupt.soft) { - intr |= INTR_TYPE_SOFT_INTR; - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmx->vcpu.arch.event_exit_inst_len); - } else - intr |= INTR_TYPE_EXT_INTR; - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr); - - vmx_clear_hlt(vcpu); -} - -static void vmx_inject_nmi(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!enable_vnmi) { - /* - * Tracking the NMI-blocked state in software is built upon - * finding the next open IRQ window. This, in turn, depends on - * well-behaving guests: They have to keep IRQs disabled at - * least as long as the NMI handler runs. Otherwise we may - * cause NMI nesting, maybe breaking the guest. But as this is - * highly unlikely, we can live with the residual risk. - */ - vmx->loaded_vmcs->soft_vnmi_blocked = 1; - vmx->loaded_vmcs->vnmi_blocked_time = 0; - } - - ++vcpu->stat.nmi_injections; - vmx->loaded_vmcs->nmi_known_unmasked = false; - - if (vmx->rmode.vm86_active) { - kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0); - return; - } - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR); - - vmx_clear_hlt(vcpu); -} - -bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - bool masked; - - if (!enable_vnmi) - return vmx->loaded_vmcs->soft_vnmi_blocked; - if (vmx->loaded_vmcs->nmi_known_unmasked) - return false; - masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; - vmx->loaded_vmcs->nmi_known_unmasked = !masked; - return masked; -} - -void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!enable_vnmi) { - if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) { - vmx->loaded_vmcs->soft_vnmi_blocked = masked; - vmx->loaded_vmcs->vnmi_blocked_time = 0; - } - } else { - vmx->loaded_vmcs->nmi_known_unmasked = !masked; - if (masked) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - else - vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - } -} - -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) -{ - if (to_vmx(vcpu)->nested.nested_run_pending) - return 0; - - if (!enable_vnmi && - to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked) - return 0; - - return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI - | GUEST_INTR_STATE_NMI)); -} - -static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) -{ - return (!to_vmx(vcpu)->nested.nested_run_pending && - vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && - !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); -} - -static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) -{ - int ret; - - if (enable_unrestricted_guest) - return 0; - - ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, - PAGE_SIZE * 3); - if (ret) - return ret; - to_kvm_vmx(kvm)->tss_addr = addr; - return init_rmode_tss(kvm); -} - -static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) -{ - to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr; - return 0; -} - -static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) -{ - switch (vec) { - case BP_VECTOR: - /* - * Update instruction length as we may reinject the exception - * from user space while in guest debugging mode. - */ - to_vmx(vcpu)->vcpu.arch.event_exit_inst_len = - vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) - return false; - /* fall through */ - case DB_VECTOR: - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - return false; - /* fall through */ - case DE_VECTOR: - case OF_VECTOR: - case BR_VECTOR: - case UD_VECTOR: - case DF_VECTOR: - case SS_VECTOR: - case GP_VECTOR: - case MF_VECTOR: - return true; - break; - } - return false; -} - -static int handle_rmode_exception(struct kvm_vcpu *vcpu, - int vec, u32 err_code) -{ - /* - * Instruction with address size override prefix opcode 0x67 - * Cause the #SS fault with 0 error code in VM86 mode. - */ - if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { - if (kvm_emulate_instruction(vcpu, 0)) { - if (vcpu->arch.halt_request) { - vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); - } - return 1; - } - return 0; - } - - /* - * Forward all other exceptions that are valid in real mode. - * FIXME: Breaks guest debugging in real mode, needs to be fixed with - * the required debugging infrastructure rework. - */ - kvm_queue_exception(vcpu, vec); - return 1; -} - -/* - * Trigger machine check on the host. We assume all the MSRs are already set up - * by the CPU and that we still run on the same CPU as the MCE occurred on. - * We pass a fake environment to the machine check handler because we want - * the guest to be always treated like user space, no matter what context - * it used internally. - */ -static void kvm_machine_check(void) -{ -#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64) - struct pt_regs regs = { - .cs = 3, /* Fake ring 3 no matter what the guest ran on */ - .flags = X86_EFLAGS_IF, - }; - - do_machine_check(&regs, 0); -#endif -} - -static int handle_machine_check(struct kvm_vcpu *vcpu) -{ - /* handled by vmx_vcpu_run() */ - return 1; -} - -static int handle_exception_nmi(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_run *kvm_run = vcpu->run; - u32 intr_info, ex_no, error_code; - unsigned long cr2, rip, dr6; - u32 vect_info; - - vect_info = vmx->idt_vectoring_info; - intr_info = vmx->exit_intr_info; - - if (is_machine_check(intr_info) || is_nmi(intr_info)) - return 1; /* handled by handle_exception_nmi_irqoff() */ - - if (is_invalid_opcode(intr_info)) - return handle_ud(vcpu); - - error_code = 0; - if (intr_info & INTR_INFO_DELIVER_CODE_MASK) - error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); - - if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { - WARN_ON_ONCE(!enable_vmware_backdoor); - - /* - * VMware backdoor emulation on #GP interception only handles - * IN{S}, OUT{S}, and RDPMC, none of which generate a non-zero - * error code on #GP. - */ - if (error_code) { - kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); - return 1; - } - return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP); - } - - /* - * The #PF with PFEC.RSVD = 1 indicates the guest is accessing - * MMIO, it is better to report an internal error. - * See the comments in vmx_handle_exit. - */ - if ((vect_info & VECTORING_INFO_VALID_MASK) && - !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; - vcpu->run->internal.ndata = 3; - vcpu->run->internal.data[0] = vect_info; - vcpu->run->internal.data[1] = intr_info; - vcpu->run->internal.data[2] = error_code; - return 0; - } - - if (is_page_fault(intr_info)) { - cr2 = vmcs_readl(EXIT_QUALIFICATION); - /* EPT won't cause page fault directly */ - WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept); - return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0); - } - - ex_no = intr_info & INTR_INFO_VECTOR_MASK; - - if (vmx->rmode.vm86_active && rmode_exception(vcpu, ex_no)) - return handle_rmode_exception(vcpu, ex_no, error_code); - - switch (ex_no) { - case AC_VECTOR: - kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); - return 1; - case DB_VECTOR: - dr6 = vmcs_readl(EXIT_QUALIFICATION); - if (!(vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= dr6 | DR6_RTM; - if (is_icebp(intr_info)) - WARN_ON(!skip_emulated_instruction(vcpu)); - - kvm_queue_exception(vcpu, DB_VECTOR); - return 1; - } - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; - kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); - /* fall through */ - case BP_VECTOR: - /* - * Update instruction length as we may reinject #BP from - * user space while in guest debugging mode. Reading it for - * #DB as well causes no harm, it is not used in that case. - */ - vmx->vcpu.arch.event_exit_inst_len = - vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - kvm_run->exit_reason = KVM_EXIT_DEBUG; - rip = kvm_rip_read(vcpu); - kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; - kvm_run->debug.arch.exception = ex_no; - break; - default: - kvm_run->exit_reason = KVM_EXIT_EXCEPTION; - kvm_run->ex.exception = ex_no; - kvm_run->ex.error_code = error_code; - break; - } - return 0; -} - -static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.irq_exits; - return 1; -} - -static int handle_triple_fault(struct kvm_vcpu *vcpu) -{ - vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; - vcpu->mmio_needed = 0; - return 0; -} - -static int handle_io(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification; - int size, in, string; - unsigned port; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - string = (exit_qualification & 16) != 0; - - ++vcpu->stat.io_exits; - - if (string) - return kvm_emulate_instruction(vcpu, 0); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - in = (exit_qualification & 8) != 0; - - return kvm_fast_pio(vcpu, size, port, in); -} - -static void -vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) -{ - /* - * Patch in the VMCALL instruction: - */ - hypercall[0] = 0x0f; - hypercall[1] = 0x01; - hypercall[2] = 0xc1; -} - -/* called to set cr0 as appropriate for a mov-to-cr0 exit. */ -static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val) -{ - if (is_guest_mode(vcpu)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned long orig_val = val; - - /* - * We get here when L2 changed cr0 in a way that did not change - * any of L1's shadowed bits (see nested_vmx_exit_handled_cr), - * but did change L0 shadowed bits. So we first calculate the - * effective cr0 value that L1 would like to write into the - * hardware. It consists of the L2-owned bits from the new - * value combined with the L1-owned bits from L1's guest_cr0. - */ - val = (val & ~vmcs12->cr0_guest_host_mask) | - (vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask); - - if (!nested_guest_cr0_valid(vcpu, val)) - return 1; - - if (kvm_set_cr0(vcpu, val)) - return 1; - vmcs_writel(CR0_READ_SHADOW, orig_val); - return 0; - } else { - if (to_vmx(vcpu)->nested.vmxon && - !nested_host_cr0_valid(vcpu, val)) - return 1; - - return kvm_set_cr0(vcpu, val); - } -} - -static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) -{ - if (is_guest_mode(vcpu)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - unsigned long orig_val = val; - - /* analogously to handle_set_cr0 */ - val = (val & ~vmcs12->cr4_guest_host_mask) | - (vmcs12->guest_cr4 & vmcs12->cr4_guest_host_mask); - if (kvm_set_cr4(vcpu, val)) - return 1; - vmcs_writel(CR4_READ_SHADOW, orig_val); - return 0; - } else - return kvm_set_cr4(vcpu, val); -} - -static int handle_desc(struct kvm_vcpu *vcpu) -{ - WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); - return kvm_emulate_instruction(vcpu, 0); -} - -static int handle_cr(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification, val; - int cr; - int reg; - int err; - int ret; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - cr = exit_qualification & 15; - reg = (exit_qualification >> 8) & 15; - switch ((exit_qualification >> 4) & 3) { - case 0: /* mov to cr */ - val = kvm_register_readl(vcpu, reg); - trace_kvm_cr_write(cr, val); - switch (cr) { - case 0: - err = handle_set_cr0(vcpu, val); - return kvm_complete_insn_gp(vcpu, err); - case 3: - WARN_ON_ONCE(enable_unrestricted_guest); - err = kvm_set_cr3(vcpu, val); - return kvm_complete_insn_gp(vcpu, err); - case 4: - err = handle_set_cr4(vcpu, val); - return kvm_complete_insn_gp(vcpu, err); - case 8: { - u8 cr8_prev = kvm_get_cr8(vcpu); - u8 cr8 = (u8)val; - err = kvm_set_cr8(vcpu, cr8); - ret = kvm_complete_insn_gp(vcpu, err); - if (lapic_in_kernel(vcpu)) - return ret; - if (cr8_prev <= cr8) - return ret; - /* - * TODO: we might be squashing a - * KVM_GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ - vcpu->run->exit_reason = KVM_EXIT_SET_TPR; - return 0; - } - } - break; - case 2: /* clts */ - WARN_ONCE(1, "Guest should always own CR0.TS"); - vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); - trace_kvm_cr_write(0, kvm_read_cr0(vcpu)); - return kvm_skip_emulated_instruction(vcpu); - case 1: /*mov from cr*/ - switch (cr) { - case 3: - WARN_ON_ONCE(enable_unrestricted_guest); - val = kvm_read_cr3(vcpu); - kvm_register_write(vcpu, reg, val); - trace_kvm_cr_read(cr, val); - return kvm_skip_emulated_instruction(vcpu); - case 8: - val = kvm_get_cr8(vcpu); - kvm_register_write(vcpu, reg, val); - trace_kvm_cr_read(cr, val); - return kvm_skip_emulated_instruction(vcpu); - } - break; - case 3: /* lmsw */ - val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; - trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val); - kvm_lmsw(vcpu, val); - - return kvm_skip_emulated_instruction(vcpu); - default: - break; - } - vcpu->run->exit_reason = 0; - vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n", - (int)(exit_qualification >> 4) & 3, cr); - return 0; -} - -static int handle_dr(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification; - int dr, dr7, reg; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - dr = exit_qualification & DEBUG_REG_ACCESS_NUM; - - /* First, if DR does not exist, trigger UD */ - if (!kvm_require_dr(vcpu, dr)) - return 1; - - /* Do not handle if the CPL > 0, will trigger GP on re-entry */ - if (!kvm_require_cpl(vcpu, 0)) - return 1; - dr7 = vmcs_readl(GUEST_DR7); - if (dr7 & DR7_GD) { - /* - * As the vm-exit takes precedence over the debug trap, we - * need to emulate the latter, either for the host or the - * guest debugging itself. - */ - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - vcpu->run->debug.arch.dr6 = vcpu->arch.dr6; - vcpu->run->debug.arch.dr7 = dr7; - vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu); - vcpu->run->debug.arch.exception = DB_VECTOR; - vcpu->run->exit_reason = KVM_EXIT_DEBUG; - return 0; - } else { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= DR6_BD | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); - return 1; - } - } - - if (vcpu->guest_debug == 0) { - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); - - /* - * No more DR vmexits; force a reload of the debug registers - * and reenter on this instruction. The next vmexit will - * retrieve the full state of the debug registers. - */ - vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; - return 1; - } - - reg = DEBUG_REG_ACCESS_REG(exit_qualification); - if (exit_qualification & TYPE_MOV_FROM_DR) { - unsigned long val; - - if (kvm_get_dr(vcpu, dr, &val)) - return 1; - kvm_register_write(vcpu, reg, val); - } else - if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg))) - return 1; - - return kvm_skip_emulated_instruction(vcpu); -} - -static u64 vmx_get_dr6(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.dr6; -} - -static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ -} - -static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) -{ - get_debugreg(vcpu->arch.db[0], 0); - get_debugreg(vcpu->arch.db[1], 1); - get_debugreg(vcpu->arch.db[2], 2); - get_debugreg(vcpu->arch.db[3], 3); - get_debugreg(vcpu->arch.dr6, 6); - vcpu->arch.dr7 = vmcs_readl(GUEST_DR7); - - vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; - exec_controls_setbit(to_vmx(vcpu), CPU_BASED_MOV_DR_EXITING); -} - -static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) -{ - vmcs_writel(GUEST_DR7, val); -} - -static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) -{ - kvm_apic_update_ppr(vcpu); - return 1; -} - -static int handle_interrupt_window(struct kvm_vcpu *vcpu) -{ - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING); - - kvm_make_request(KVM_REQ_EVENT, vcpu); - - ++vcpu->stat.irq_window_exits; - return 1; -} - -static int handle_vmcall(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_hypercall(vcpu); -} - -static int handle_invd(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_instruction(vcpu, 0); -} - -static int handle_invlpg(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - kvm_mmu_invlpg(vcpu, exit_qualification); - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_rdpmc(struct kvm_vcpu *vcpu) -{ - int err; - - err = kvm_rdpmc(vcpu); - return kvm_complete_insn_gp(vcpu, err); -} - -static int handle_wbinvd(struct kvm_vcpu *vcpu) -{ - return kvm_emulate_wbinvd(vcpu); -} - -static int handle_xsetbv(struct kvm_vcpu *vcpu) -{ - u64 new_bv = kvm_read_edx_eax(vcpu); - u32 index = kvm_rcx_read(vcpu); - - if (kvm_set_xcr(vcpu, index, new_bv) == 0) - return kvm_skip_emulated_instruction(vcpu); - return 1; -} - -static int handle_apic_access(struct kvm_vcpu *vcpu) -{ - if (likely(fasteoi)) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - int access_type, offset; - - access_type = exit_qualification & APIC_ACCESS_TYPE; - offset = exit_qualification & APIC_ACCESS_OFFSET; - /* - * Sane guest uses MOV to write EOI, with written value - * not cared. So make a short-circuit here by avoiding - * heavy instruction emulation. - */ - if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) && - (offset == APIC_EOI)) { - kvm_lapic_set_eoi(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - } - return kvm_emulate_instruction(vcpu, 0); -} - -static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - int vector = exit_qualification & 0xff; - - /* EOI-induced VM exit is trap-like and thus no need to adjust IP */ - kvm_apic_set_eoi_accelerated(vcpu, vector); - return 1; -} - -static int handle_apic_write(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 offset = exit_qualification & 0xfff; - - /* APIC-write VM exit is trap-like and thus no need to adjust IP */ - kvm_apic_write_nodecode(vcpu, offset); - return 1; -} - -static int handle_task_switch(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long exit_qualification; - bool has_error_code = false; - u32 error_code = 0; - u16 tss_selector; - int reason, type, idt_v, idt_index; - - idt_v = (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK); - idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK); - type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - reason = (u32)exit_qualification >> 30; - if (reason == TASK_SWITCH_GATE && idt_v) { - switch (type) { - case INTR_TYPE_NMI_INTR: - vcpu->arch.nmi_injected = false; - vmx_set_nmi_mask(vcpu, true); - break; - case INTR_TYPE_EXT_INTR: - case INTR_TYPE_SOFT_INTR: - kvm_clear_interrupt_queue(vcpu); - break; - case INTR_TYPE_HARD_EXCEPTION: - if (vmx->idt_vectoring_info & - VECTORING_INFO_DELIVER_CODE_MASK) { - has_error_code = true; - error_code = - vmcs_read32(IDT_VECTORING_ERROR_CODE); - } - /* fall through */ - case INTR_TYPE_SOFT_EXCEPTION: - kvm_clear_exception_queue(vcpu); - break; - default: - break; - } - } - tss_selector = exit_qualification; - - if (!idt_v || (type != INTR_TYPE_HARD_EXCEPTION && - type != INTR_TYPE_EXT_INTR && - type != INTR_TYPE_NMI_INTR)) - WARN_ON(!skip_emulated_instruction(vcpu)); - - /* - * TODO: What about debug traps on tss switch? - * Are we supposed to inject them and update dr6? - */ - return kvm_task_switch(vcpu, tss_selector, - type == INTR_TYPE_SOFT_INTR ? idt_index : -1, - reason, has_error_code, error_code); -} - -static int handle_ept_violation(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification; - gpa_t gpa; - u64 error_code; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - /* - * EPT violation happened while executing iret from NMI, - * "blocked by NMI" bit has to be set before next VM entry. - * There are errata that may cause this bit to not be set: - * AAK134, BY25. - */ - if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && - enable_vnmi && - (exit_qualification & INTR_INFO_UNBLOCK_NMI)) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); - - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - trace_kvm_page_fault(gpa, exit_qualification); - - /* Is it a read fault? */ - error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) - ? PFERR_USER_MASK : 0; - /* Is it a write fault? */ - error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE) - ? PFERR_WRITE_MASK : 0; - /* Is it a fetch fault? */ - error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR) - ? PFERR_FETCH_MASK : 0; - /* ept page table entry is present? */ - error_code |= (exit_qualification & - (EPT_VIOLATION_READABLE | EPT_VIOLATION_WRITABLE | - EPT_VIOLATION_EXECUTABLE)) - ? PFERR_PRESENT_MASK : 0; - - error_code |= (exit_qualification & 0x100) != 0 ? - PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; - - vcpu->arch.exit_qualification = exit_qualification; - return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); -} - -static int handle_ept_misconfig(struct kvm_vcpu *vcpu) -{ - gpa_t gpa; - - /* - * A nested guest cannot optimize MMIO vmexits, because we have an - * nGPA here instead of the required GPA. - */ - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - if (!is_guest_mode(vcpu) && - !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { - trace_kvm_fast_mmio(gpa); - return kvm_skip_emulated_instruction(vcpu); - } - - return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); -} - -static int handle_nmi_window(struct kvm_vcpu *vcpu) -{ - WARN_ON_ONCE(!enable_vnmi); - exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); - ++vcpu->stat.nmi_window_exits; - kvm_make_request(KVM_REQ_EVENT, vcpu); - - return 1; -} - -static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - bool intr_window_requested; - unsigned count = 130; - - /* - * We should never reach the point where we are emulating L2 - * due to invalid guest state as that means we incorrectly - * allowed a nested VMEntry with an invalid vmcs12. - */ - WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending); - - intr_window_requested = exec_controls_get(vmx) & - CPU_BASED_INTR_WINDOW_EXITING; - - while (vmx->emulation_required && count-- != 0) { - if (intr_window_requested && vmx_interrupt_allowed(vcpu)) - return handle_interrupt_window(&vmx->vcpu); - - if (kvm_test_request(KVM_REQ_EVENT, vcpu)) - return 1; - - if (!kvm_emulate_instruction(vcpu, 0)) - return 0; - - if (vmx->emulation_required && !vmx->rmode.vm86_active && - vcpu->arch.exception.pending) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; - return 0; - } - - if (vcpu->arch.halt_request) { - vcpu->arch.halt_request = 0; - return kvm_vcpu_halt(vcpu); - } - - /* - * Note, return 1 and not 0, vcpu_run() is responsible for - * morphing the pending signal into the proper return code. - */ - if (signal_pending(current)) - return 1; - - if (need_resched()) - schedule(); - } - - return 1; -} - -static void grow_ple_window(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned int old = vmx->ple_window; - - vmx->ple_window = __grow_ple_window(old, ple_window, - ple_window_grow, - ple_window_max); - - if (vmx->ple_window != old) { - vmx->ple_window_dirty = true; - trace_kvm_ple_window_update(vcpu->vcpu_id, - vmx->ple_window, old); - } -} - -static void shrink_ple_window(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned int old = vmx->ple_window; - - vmx->ple_window = __shrink_ple_window(old, ple_window, - ple_window_shrink, - ple_window); - - if (vmx->ple_window != old) { - vmx->ple_window_dirty = true; - trace_kvm_ple_window_update(vcpu->vcpu_id, - vmx->ple_window, old); - } -} - -/* - * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. - */ -static void wakeup_handler(void) -{ - struct kvm_vcpu *vcpu; - int cpu = smp_processor_id(); - - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu), - blocked_vcpu_list) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - - if (pi_test_on(pi_desc) == 1) - kvm_vcpu_kick(vcpu); - } - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); -} - -static void vmx_enable_tdp(void) -{ - kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, - enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull, - enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK, - cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, - VMX_EPT_RWX_MASK, 0ull); - - ept_set_mmio_spte_mask(); - kvm_enable_tdp(); -} - -/* - * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE - * exiting, so only get here on cpu with PAUSE-Loop-Exiting. - */ -static int handle_pause(struct kvm_vcpu *vcpu) -{ - if (!kvm_pause_in_guest(vcpu->kvm)) - grow_ple_window(vcpu); - - /* - * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting" - * VM-execution control is ignored if CPL > 0. OTOH, KVM - * never set PAUSE_EXITING and just set PLE if supported, - * so the vcpu must be CPL=0 if it gets a PAUSE exit. - */ - kvm_vcpu_on_spin(vcpu, true); - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_nop(struct kvm_vcpu *vcpu) -{ - return kvm_skip_emulated_instruction(vcpu); -} - -static int handle_mwait(struct kvm_vcpu *vcpu) -{ - printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); - return handle_nop(vcpu); -} - -static int handle_invalid_op(struct kvm_vcpu *vcpu) -{ - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; -} - -static int handle_monitor_trap(struct kvm_vcpu *vcpu) -{ - return 1; -} - -static int handle_monitor(struct kvm_vcpu *vcpu) -{ - printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); - return handle_nop(vcpu); -} - -static int handle_invpcid(struct kvm_vcpu *vcpu) -{ - u32 vmx_instruction_info; - unsigned long type; - bool pcid_enabled; - gva_t gva; - struct x86_exception e; - unsigned i; - unsigned long roots_to_free = 0; - struct { - u64 pcid; - u64 gla; - } operand; - - if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; - } - - vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); - - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } - - /* According to the Intel instruction reference, the memory operand - * is read even if it isn't needed (e.g., for type==all) - */ - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, false, - sizeof(operand), &gva)) - return 1; - - if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { - kvm_inject_page_fault(vcpu, &e); - return 1; - } - - if (operand.pcid >> 12 != 0) { - kvm_inject_gp(vcpu, 0); - return 1; - } - - pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); - - switch (type) { - case INVPCID_TYPE_INDIV_ADDR: - if ((!pcid_enabled && (operand.pcid != 0)) || - is_noncanonical_address(operand.gla, vcpu)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid); - return kvm_skip_emulated_instruction(vcpu); - - case INVPCID_TYPE_SINGLE_CTXT: - if (!pcid_enabled && (operand.pcid != 0)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - - if (kvm_get_active_pcid(vcpu) == operand.pcid) { - kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } - - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3) - == operand.pcid) - roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); - - kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free); - /* - * If neither the current cr3 nor any of the prev_roots use the - * given PCID, then nothing needs to be done here because a - * resync will happen anyway before switching to any other CR3. - */ - - return kvm_skip_emulated_instruction(vcpu); - - case INVPCID_TYPE_ALL_NON_GLOBAL: - /* - * Currently, KVM doesn't mark global entries in the shadow - * page tables, so a non-global flush just degenerates to a - * global flush. If needed, we could optimize this later by - * keeping track of global entries in shadow page tables. - */ - - /* fall-through */ - case INVPCID_TYPE_ALL_INCL_GLOBAL: - kvm_mmu_unload(vcpu); - return kvm_skip_emulated_instruction(vcpu); - - default: - BUG(); /* We have already checked above that type <= 3 */ - } -} - -static int handle_pml_full(struct kvm_vcpu *vcpu) -{ - unsigned long exit_qualification; - - trace_kvm_pml_full(vcpu->vcpu_id); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - /* - * PML buffer FULL happened while executing iret from NMI, - * "blocked by NMI" bit has to be set before next VM entry. - */ - if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && - enable_vnmi && - (exit_qualification & INTR_INFO_UNBLOCK_NMI)) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - - /* - * PML buffer already flushed at beginning of VMEXIT. Nothing to do - * here.., and there's no userspace involvement needed for PML. - */ - return 1; -} - -static int handle_preemption_timer(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!vmx->req_immediate_exit && - !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) - kvm_lapic_expired_hv_timer(vcpu); - - return 1; -} - -/* - * When nested=0, all VMX instruction VM Exits filter here. The handlers - * are overwritten by nested_vmx_setup() when nested=1. - */ -static int handle_vmx_instruction(struct kvm_vcpu *vcpu) -{ - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; -} - -static int handle_encls(struct kvm_vcpu *vcpu) -{ - /* - * SGX virtualization is not yet supported. There is no software - * enable bit for SGX, so we have to trap ENCLS and inject a #UD - * to prevent the guest from executing ENCLS. - */ - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; -} - -/* - * The exit handlers return 1 if the exit was handled fully and guest execution - * may resume. Otherwise they set the kvm_run parameter to indicate what needs - * to be done to userspace and return 0. - */ -static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { - [EXIT_REASON_EXCEPTION_NMI] = handle_exception_nmi, - [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, - [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, - [EXIT_REASON_NMI_WINDOW] = handle_nmi_window, - [EXIT_REASON_IO_INSTRUCTION] = handle_io, - [EXIT_REASON_CR_ACCESS] = handle_cr, - [EXIT_REASON_DR_ACCESS] = handle_dr, - [EXIT_REASON_CPUID] = kvm_emulate_cpuid, - [EXIT_REASON_MSR_READ] = kvm_emulate_rdmsr, - [EXIT_REASON_MSR_WRITE] = kvm_emulate_wrmsr, - [EXIT_REASON_INTERRUPT_WINDOW] = handle_interrupt_window, - [EXIT_REASON_HLT] = kvm_emulate_halt, - [EXIT_REASON_INVD] = handle_invd, - [EXIT_REASON_INVLPG] = handle_invlpg, - [EXIT_REASON_RDPMC] = handle_rdpmc, - [EXIT_REASON_VMCALL] = handle_vmcall, - [EXIT_REASON_VMCLEAR] = handle_vmx_instruction, - [EXIT_REASON_VMLAUNCH] = handle_vmx_instruction, - [EXIT_REASON_VMPTRLD] = handle_vmx_instruction, - [EXIT_REASON_VMPTRST] = handle_vmx_instruction, - [EXIT_REASON_VMREAD] = handle_vmx_instruction, - [EXIT_REASON_VMRESUME] = handle_vmx_instruction, - [EXIT_REASON_VMWRITE] = handle_vmx_instruction, - [EXIT_REASON_VMOFF] = handle_vmx_instruction, - [EXIT_REASON_VMON] = handle_vmx_instruction, - [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold, - [EXIT_REASON_APIC_ACCESS] = handle_apic_access, - [EXIT_REASON_APIC_WRITE] = handle_apic_write, - [EXIT_REASON_EOI_INDUCED] = handle_apic_eoi_induced, - [EXIT_REASON_WBINVD] = handle_wbinvd, - [EXIT_REASON_XSETBV] = handle_xsetbv, - [EXIT_REASON_TASK_SWITCH] = handle_task_switch, - [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, - [EXIT_REASON_GDTR_IDTR] = handle_desc, - [EXIT_REASON_LDTR_TR] = handle_desc, - [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, - [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, - [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, - [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, - [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, - [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, - [EXIT_REASON_INVEPT] = handle_vmx_instruction, - [EXIT_REASON_INVVPID] = handle_vmx_instruction, - [EXIT_REASON_RDRAND] = handle_invalid_op, - [EXIT_REASON_RDSEED] = handle_invalid_op, - [EXIT_REASON_PML_FULL] = handle_pml_full, - [EXIT_REASON_INVPCID] = handle_invpcid, - [EXIT_REASON_VMFUNC] = handle_vmx_instruction, - [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, - [EXIT_REASON_ENCLS] = handle_encls, -}; - -static const int kvm_vmx_max_exit_handlers = - ARRAY_SIZE(kvm_vmx_exit_handlers); - -static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) -{ - *info1 = vmcs_readl(EXIT_QUALIFICATION); - *info2 = vmcs_read32(VM_EXIT_INTR_INFO); -} - -static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) -{ - if (vmx->pml_pg) { - __free_page(vmx->pml_pg); - vmx->pml_pg = NULL; - } -} - -static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 *pml_buf; - u16 pml_idx; - - pml_idx = vmcs_read16(GUEST_PML_INDEX); - - /* Do nothing if PML buffer is empty */ - if (pml_idx == (PML_ENTITY_NUM - 1)) - return; - - /* PML index always points to next available PML buffer entity */ - if (pml_idx >= PML_ENTITY_NUM) - pml_idx = 0; - else - pml_idx++; - - pml_buf = page_address(vmx->pml_pg); - for (; pml_idx < PML_ENTITY_NUM; pml_idx++) { - u64 gpa; - - gpa = pml_buf[pml_idx]; - WARN_ON(gpa & (PAGE_SIZE - 1)); - kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); - } - - /* reset PML index */ - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); -} - -/* - * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap. - * Called before reporting dirty_bitmap to userspace. - */ -static void kvm_flush_pml_buffers(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - /* - * We only need to kick vcpu out of guest mode here, as PML buffer - * is flushed at beginning of all VMEXITs, and it's obvious that only - * vcpus running in guest are possible to have unflushed GPAs in PML - * buffer. - */ - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_kick(vcpu); -} - -static void vmx_dump_sel(char *name, uint32_t sel) -{ - pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", - name, vmcs_read16(sel), - vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), - vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), - vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); -} - -static void vmx_dump_dtsel(char *name, uint32_t limit) -{ - pr_err("%s limit=0x%08x, base=0x%016lx\n", - name, vmcs_read32(limit), - vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); -} - -void dump_vmcs(void) -{ - u32 vmentry_ctl, vmexit_ctl; - u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control; - unsigned long cr4; - u64 efer; - int i, n; - - if (!dump_invalid_vmcs) { - pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n"); - return; - } - - vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); - vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); - cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); - cr4 = vmcs_readl(GUEST_CR4); - efer = vmcs_read64(GUEST_IA32_EFER); - secondary_exec_control = 0; - if (cpu_has_secondary_exec_ctrls()) - secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - - pr_err("*** Guest State ***\n"); - pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", - vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), - vmcs_readl(CR0_GUEST_HOST_MASK)); - pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", - cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); - pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); - if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && - (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) - { - pr_err("PDPTR0 = 0x%016llx PDPTR1 = 0x%016llx\n", - vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1)); - pr_err("PDPTR2 = 0x%016llx PDPTR3 = 0x%016llx\n", - vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3)); - } - pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", - vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); - pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n", - vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7)); - pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", - vmcs_readl(GUEST_SYSENTER_ESP), - vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP)); - vmx_dump_sel("CS: ", GUEST_CS_SELECTOR); - vmx_dump_sel("DS: ", GUEST_DS_SELECTOR); - vmx_dump_sel("SS: ", GUEST_SS_SELECTOR); - vmx_dump_sel("ES: ", GUEST_ES_SELECTOR); - vmx_dump_sel("FS: ", GUEST_FS_SELECTOR); - vmx_dump_sel("GS: ", GUEST_GS_SELECTOR); - vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT); - vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); - vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); - vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); - if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || - (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) - pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", - efer, vmcs_read64(GUEST_IA32_PAT)); - pr_err("DebugCtl = 0x%016llx DebugExceptions = 0x%016lx\n", - vmcs_read64(GUEST_IA32_DEBUGCTL), - vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); - if (cpu_has_load_perf_global_ctrl() && - vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) - pr_err("PerfGlobCtl = 0x%016llx\n", - vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL)); - if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) - pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS)); - pr_err("Interruptibility = %08x ActivityState = %08x\n", - vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), - vmcs_read32(GUEST_ACTIVITY_STATE)); - if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) - pr_err("InterruptStatus = %04x\n", - vmcs_read16(GUEST_INTR_STATUS)); - - pr_err("*** Host State ***\n"); - pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", - vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); - pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n", - vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR), - vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR), - vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR), - vmcs_read16(HOST_TR_SELECTOR)); - pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n", - vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE), - vmcs_readl(HOST_TR_BASE)); - pr_err("GDTBase=%016lx IDTBase=%016lx\n", - vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE)); - pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n", - vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3), - vmcs_readl(HOST_CR4)); - pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", - vmcs_readl(HOST_IA32_SYSENTER_ESP), - vmcs_read32(HOST_IA32_SYSENTER_CS), - vmcs_readl(HOST_IA32_SYSENTER_EIP)); - if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) - pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", - vmcs_read64(HOST_IA32_EFER), - vmcs_read64(HOST_IA32_PAT)); - if (cpu_has_load_perf_global_ctrl() && - vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - pr_err("PerfGlobCtl = 0x%016llx\n", - vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); - - pr_err("*** Control State ***\n"); - pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", - pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control); - pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl); - pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", - vmcs_read32(EXCEPTION_BITMAP), - vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), - vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH)); - pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n", - vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), - vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE), - vmcs_read32(VM_ENTRY_INSTRUCTION_LEN)); - pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n", - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_read32(VM_EXIT_INTR_ERROR_CODE), - vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); - pr_err(" reason=%08x qualification=%016lx\n", - vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION)); - pr_err("IDTVectoring: info=%08x errcode=%08x\n", - vmcs_read32(IDT_VECTORING_INFO_FIELD), - vmcs_read32(IDT_VECTORING_ERROR_CODE)); - pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET)); - if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) - pr_err("TSC Multiplier = 0x%016llx\n", - vmcs_read64(TSC_MULTIPLIER)); - if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) { - if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { - u16 status = vmcs_read16(GUEST_INTR_STATUS); - pr_err("SVI|RVI = %02x|%02x ", status >> 8, status & 0xff); - } - pr_cont("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); - if (secondary_exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) - pr_err("APIC-access addr = 0x%016llx ", vmcs_read64(APIC_ACCESS_ADDR)); - pr_cont("virt-APIC addr = 0x%016llx\n", vmcs_read64(VIRTUAL_APIC_PAGE_ADDR)); - } - if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) - pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); - if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) - pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER)); - n = vmcs_read32(CR3_TARGET_COUNT); - for (i = 0; i + 1 < n; i += 4) - pr_err("CR3 target%u=%016lx target%u=%016lx\n", - i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2), - i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2)); - if (i < n) - pr_err("CR3 target%u=%016lx\n", - i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2)); - if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) - pr_err("PLE Gap=%08x Window=%08x\n", - vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); - if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) - pr_err("Virtual processor ID = 0x%04x\n", - vmcs_read16(VIRTUAL_PROCESSOR_ID)); -} - -/* - * The guest has exited. See if we can fix it or if we need userspace - * assistance. - */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion exit_fastpath) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exit_reason = vmx->exit_reason; - u32 vectoring_info = vmx->idt_vectoring_info; - - trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); - - /* - * Flush logged GPAs PML buffer, this will make dirty_bitmap more - * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before - * querying dirty_bitmap, we only need to kick all vcpus out of guest - * mode as if vcpus is in root mode, the PML buffer must has been - * flushed already. - */ - if (enable_pml) - vmx_flush_pml_buffer(vcpu); - - /* If guest state is invalid, start emulating */ - if (vmx->emulation_required) - return handle_invalid_guest_state(vcpu); - - if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason)) - return nested_vmx_reflect_vmexit(vcpu, exit_reason); - - if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { - dump_vmcs(); - vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; - vcpu->run->fail_entry.hardware_entry_failure_reason - = exit_reason; - return 0; - } - - if (unlikely(vmx->fail)) { - dump_vmcs(); - vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; - vcpu->run->fail_entry.hardware_entry_failure_reason - = vmcs_read32(VM_INSTRUCTION_ERROR); - return 0; - } - - /* - * Note: - * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by - * delivery event since it indicates guest is accessing MMIO. - * The vm-exit can be triggered again after return to guest that - * will cause infinite loop. - */ - if ((vectoring_info & VECTORING_INFO_VALID_MASK) && - (exit_reason != EXIT_REASON_EXCEPTION_NMI && - exit_reason != EXIT_REASON_EPT_VIOLATION && - exit_reason != EXIT_REASON_PML_FULL && - exit_reason != EXIT_REASON_TASK_SWITCH)) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.ndata = 3; - vcpu->run->internal.data[0] = vectoring_info; - vcpu->run->internal.data[1] = exit_reason; - vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; - if (exit_reason == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.ndata++; - vcpu->run->internal.data[3] = - vmcs_read64(GUEST_PHYSICAL_ADDRESS); - } - return 0; - } - - if (unlikely(!enable_vnmi && - vmx->loaded_vmcs->soft_vnmi_blocked)) { - if (vmx_interrupt_allowed(vcpu)) { - vmx->loaded_vmcs->soft_vnmi_blocked = 0; - } else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL && - vcpu->arch.nmi_pending) { - /* - * This CPU don't support us in finding the end of an - * NMI-blocked window if the guest runs with IRQs - * disabled. So we pull the trigger after 1 s of - * futile waiting, but inform the user about this. - */ - printk(KERN_WARNING "%s: Breaking out of NMI-blocked " - "state on VCPU %d after 1 s timeout\n", - __func__, vcpu->vcpu_id); - vmx->loaded_vmcs->soft_vnmi_blocked = 0; - } - } - - if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { - kvm_skip_emulated_instruction(vcpu); - return 1; - } else if (exit_reason < kvm_vmx_max_exit_handlers - && kvm_vmx_exit_handlers[exit_reason]) { -#ifdef CONFIG_RETPOLINE - if (exit_reason == EXIT_REASON_MSR_WRITE) - return kvm_emulate_wrmsr(vcpu); - else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER) - return handle_preemption_timer(vcpu); - else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW) - return handle_interrupt_window(vcpu); - else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) - return handle_external_interrupt(vcpu); - else if (exit_reason == EXIT_REASON_HLT) - return kvm_emulate_halt(vcpu); - else if (exit_reason == EXIT_REASON_EPT_MISCONFIG) - return handle_ept_misconfig(vcpu); -#endif - return kvm_vmx_exit_handlers[exit_reason](vcpu); - } else { - vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", - exit_reason); - dump_vmcs(); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 1; - vcpu->run->internal.data[0] = exit_reason; - return 0; - } -} - -/* - * Software based L1D cache flush which is used when microcode providing - * the cache control MSR is not loaded. - * - * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to - * flush it is required to read in 64 KiB because the replacement algorithm - * is not exactly LRU. This could be sized at runtime via topology - * information but as all relevant affected CPUs have 32KiB L1D cache size - * there is no point in doing so. - */ -static void vmx_l1d_flush(struct kvm_vcpu *vcpu) -{ - int size = PAGE_SIZE << L1D_CACHE_ORDER; - - /* - * This code is only executed when the the flush mode is 'cond' or - * 'always' - */ - if (static_branch_likely(&vmx_l1d_flush_cond)) { - bool flush_l1d; - - /* - * Clear the per-vcpu flush bit, it gets set again - * either from vcpu_run() or from one of the unsafe - * VMEXIT handlers. - */ - flush_l1d = vcpu->arch.l1tf_flush_l1d; - vcpu->arch.l1tf_flush_l1d = false; - - /* - * Clear the per-cpu flush bit, it gets set again from - * the interrupt handlers. - */ - flush_l1d |= kvm_get_cpu_l1tf_flush_l1d(); - kvm_clear_cpu_l1tf_flush_l1d(); - - if (!flush_l1d) - return; - } - - vcpu->stat.l1d_flush++; - - if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) { - wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); - return; - } - - asm volatile( - /* First ensure the pages are in the TLB */ - "xorl %%eax, %%eax\n" - ".Lpopulate_tlb:\n\t" - "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" - "addl $4096, %%eax\n\t" - "cmpl %%eax, %[size]\n\t" - "jne .Lpopulate_tlb\n\t" - "xorl %%eax, %%eax\n\t" - "cpuid\n\t" - /* Now fill the cache */ - "xorl %%eax, %%eax\n" - ".Lfill_cache:\n" - "movzbl (%[flush_pages], %%" _ASM_AX "), %%ecx\n\t" - "addl $64, %%eax\n\t" - "cmpl %%eax, %[size]\n\t" - "jne .Lfill_cache\n\t" - "lfence\n" - :: [flush_pages] "r" (vmx_l1d_flush_pages), - [size] "r" (size) - : "eax", "ebx", "ecx", "edx"); -} - -static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - int tpr_threshold; - - if (is_guest_mode(vcpu) && - nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) - return; - - tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr; - if (is_guest_mode(vcpu)) - to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold; - else - vmcs_write32(TPR_THRESHOLD, tpr_threshold); -} - -void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 sec_exec_control; - - if (!lapic_in_kernel(vcpu)) - return; - - if (!flexpriority_enabled && - !cpu_has_vmx_virtualize_x2apic_mode()) - return; - - /* Postpone execution until vmcs01 is the current VMCS. */ - if (is_guest_mode(vcpu)) { - vmx->nested.change_vmcs01_virtual_apic_mode = true; - return; - } - - sec_exec_control = secondary_exec_controls_get(vmx); - sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); - - switch (kvm_get_apic_mode(vcpu)) { - case LAPIC_MODE_INVALID: - WARN_ONCE(true, "Invalid local APIC state"); - case LAPIC_MODE_DISABLED: - break; - case LAPIC_MODE_XAPIC: - if (flexpriority_enabled) { - sec_exec_control |= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - vmx_flush_tlb(vcpu, true); - } - break; - case LAPIC_MODE_X2APIC: - if (cpu_has_vmx_virtualize_x2apic_mode()) - sec_exec_control |= - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; - break; - } - secondary_exec_controls_set(vmx, sec_exec_control); - - vmx_update_msr_bitmap(vcpu); -} - -static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) -{ - if (!is_guest_mode(vcpu)) { - vmcs_write64(APIC_ACCESS_ADDR, hpa); - vmx_flush_tlb(vcpu, true); - } -} - -static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) -{ - u16 status; - u8 old; - - if (max_isr == -1) - max_isr = 0; - - status = vmcs_read16(GUEST_INTR_STATUS); - old = status >> 8; - if (max_isr != old) { - status &= 0xff; - status |= max_isr << 8; - vmcs_write16(GUEST_INTR_STATUS, status); - } -} - -static void vmx_set_rvi(int vector) -{ - u16 status; - u8 old; - - if (vector == -1) - vector = 0; - - status = vmcs_read16(GUEST_INTR_STATUS); - old = (u8)status & 0xff; - if ((u8)vector != old) { - status &= ~0xff; - status |= (u8)vector; - vmcs_write16(GUEST_INTR_STATUS, status); - } -} - -static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) -{ - /* - * When running L2, updating RVI is only relevant when - * vmcs12 virtual-interrupt-delivery enabled. - * However, it can be enabled only when L1 also - * intercepts external-interrupts and in that case - * we should not update vmcs02 RVI but instead intercept - * interrupt. Therefore, do nothing when running L2. - */ - if (!is_guest_mode(vcpu)) - vmx_set_rvi(max_irr); -} - -static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - int max_irr; - bool max_irr_updated; - - WARN_ON(!vcpu->arch.apicv_active); - if (pi_test_on(&vmx->pi_desc)) { - pi_clear_on(&vmx->pi_desc); - /* - * IOMMU can write to PID.ON, so the barrier matters even on UP. - * But on x86 this is just a compiler barrier anyway. - */ - smp_mb__after_atomic(); - max_irr_updated = - kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); - - /* - * If we are running L2 and L1 has a new pending interrupt - * which can be injected, we should re-evaluate - * what should be done with this new L1 interrupt. - * If L1 intercepts external-interrupts, we should - * exit from L2 to L1. Otherwise, interrupt should be - * delivered directly to L2. - */ - if (is_guest_mode(vcpu) && max_irr_updated) { - if (nested_exit_on_intr(vcpu)) - kvm_vcpu_exiting_guest_mode(vcpu); - else - kvm_make_request(KVM_REQ_EVENT, vcpu); - } - } else { - max_irr = kvm_lapic_find_highest_irr(vcpu); - } - vmx_hwapic_irr_update(vcpu, max_irr); - return max_irr; -} - -static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) -{ - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - - return pi_test_on(pi_desc) || - (pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc)); -} - -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) -{ - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); - vmcs_write64(EOI_EXIT_BITMAP1, eoi_exit_bitmap[1]); - vmcs_write64(EOI_EXIT_BITMAP2, eoi_exit_bitmap[2]); - vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); -} - -static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - pi_clear_on(&vmx->pi_desc); - memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); -} - -static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) -{ - vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - - /* if exit due to PF check for async PF */ - if (is_page_fault(vmx->exit_intr_info)) - vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); - - /* Handle machine checks before interrupts are enabled */ - if (is_machine_check(vmx->exit_intr_info)) - kvm_machine_check(); - - /* We need to handle NMIs before interrupts are enabled */ - if (is_nmi(vmx->exit_intr_info)) { - kvm_before_interrupt(&vmx->vcpu); - asm("int $2"); - kvm_after_interrupt(&vmx->vcpu); - } -} - -static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) -{ - unsigned int vector; - unsigned long entry; -#ifdef CONFIG_X86_64 - unsigned long tmp; -#endif - gate_desc *desc; - u32 intr_info; - - intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - if (WARN_ONCE(!is_external_intr(intr_info), - "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) - return; - - vector = intr_info & INTR_INFO_VECTOR_MASK; - desc = (gate_desc *)host_idt_base + vector; - entry = gate_offset(desc); - - kvm_before_interrupt(vcpu); - - asm volatile( -#ifdef CONFIG_X86_64 - "mov %%" _ASM_SP ", %[sp]\n\t" - "and $0xfffffffffffffff0, %%" _ASM_SP "\n\t" - "push $%c[ss]\n\t" - "push %[sp]\n\t" -#endif - "pushf\n\t" - __ASM_SIZE(push) " $%c[cs]\n\t" - CALL_NOSPEC - : -#ifdef CONFIG_X86_64 - [sp]"=&r"(tmp), -#endif - ASM_CALL_CONSTRAINT - : - THUNK_TARGET(entry), - [ss]"i"(__KERNEL_DS), - [cs]"i"(__KERNEL_CS) - ); - - kvm_after_interrupt(vcpu); -} -STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff); - -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion *exit_fastpath) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (vmx->exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) - handle_external_interrupt_irqoff(vcpu); - else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) - handle_exception_nmi_irqoff(vmx); - else if (!is_guest_mode(vcpu) && - vmx->exit_reason == EXIT_REASON_MSR_WRITE) - *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); -} - -static bool vmx_has_emulated_msr(int index) -{ - switch (index) { - case MSR_IA32_SMBASE: - /* - * We cannot do SMM unless we can run the guest in big - * real mode. - */ - return enable_unrestricted_guest || emulate_invalid_guest_state; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: - return nested; - case MSR_AMD64_VIRT_SPEC_CTRL: - /* This is AMD only. */ - return false; - default: - return true; - } -} - -static bool vmx_pt_supported(void) -{ - return pt_mode == PT_MODE_HOST_GUEST; -} - -static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) -{ - u32 exit_intr_info; - bool unblock_nmi; - u8 vector; - bool idtv_info_valid; - - idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK; - - if (enable_vnmi) { - if (vmx->loaded_vmcs->nmi_known_unmasked) - return; - /* - * Can't use vmx->exit_intr_info since we're not sure what - * the exit reason is. - */ - exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; - vector = exit_intr_info & INTR_INFO_VECTOR_MASK; - /* - * SDM 3: 27.7.1.2 (September 2008) - * Re-set bit "block by NMI" before VM entry if vmexit caused by - * a guest IRET fault. - * SDM 3: 23.2.2 (September 2008) - * Bit 12 is undefined in any of the following cases: - * If the VM exit sets the valid bit in the IDT-vectoring - * information field. - * If the VM exit is due to a double fault. - */ - if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi && - vector != DF_VECTOR && !idtv_info_valid) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - else - vmx->loaded_vmcs->nmi_known_unmasked = - !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) - & GUEST_INTR_STATE_NMI); - } else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked)) - vmx->loaded_vmcs->vnmi_blocked_time += - ktime_to_ns(ktime_sub(ktime_get(), - vmx->loaded_vmcs->entry_time)); -} - -static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, - u32 idt_vectoring_info, - int instr_len_field, - int error_code_field) -{ - u8 vector; - int type; - bool idtv_info_valid; - - idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK; - - vcpu->arch.nmi_injected = false; - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); - - if (!idtv_info_valid) - return; - - kvm_make_request(KVM_REQ_EVENT, vcpu); - - vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK; - type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK; - - switch (type) { - case INTR_TYPE_NMI_INTR: - vcpu->arch.nmi_injected = true; - /* - * SDM 3: 27.7.1.2 (September 2008) - * Clear bit "block by NMI" before VM entry if a NMI - * delivery faulted. - */ - vmx_set_nmi_mask(vcpu, false); - break; - case INTR_TYPE_SOFT_EXCEPTION: - vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ - case INTR_TYPE_HARD_EXCEPTION: - if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { - u32 err = vmcs_read32(error_code_field); - kvm_requeue_exception_e(vcpu, vector, err); - } else - kvm_requeue_exception(vcpu, vector); - break; - case INTR_TYPE_SOFT_INTR: - vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ - case INTR_TYPE_EXT_INTR: - kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); - break; - default: - break; - } -} - -static void vmx_complete_interrupts(struct vcpu_vmx *vmx) -{ - __vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info, - VM_EXIT_INSTRUCTION_LEN, - IDT_VECTORING_ERROR_CODE); -} - -static void vmx_cancel_injection(struct kvm_vcpu *vcpu) -{ - __vmx_complete_interrupts(vcpu, - vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), - VM_ENTRY_INSTRUCTION_LEN, - VM_ENTRY_EXCEPTION_ERROR_CODE); - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); -} - -static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) -{ - int i, nr_msrs; - struct perf_guest_switch_msr *msrs; - - msrs = perf_guest_get_msrs(&nr_msrs); - - if (!msrs) - return; - - for (i = 0; i < nr_msrs; i++) - if (msrs[i].host == msrs[i].guest) - clear_atomic_switch_msr(vmx, msrs[i].msr); - else - add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest, - msrs[i].host, false); -} - -static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx) -{ - u32 host_umwait_control; - - if (!vmx_has_waitpkg(vmx)) - return; - - host_umwait_control = get_umwait_control_msr(); - - if (vmx->msr_ia32_umwait_control != host_umwait_control) - add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL, - vmx->msr_ia32_umwait_control, - host_umwait_control, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL); -} - -static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 tscl; - u32 delta_tsc; - - if (vmx->req_immediate_exit) { - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); - vmx->loaded_vmcs->hv_timer_soft_disabled = false; - } else if (vmx->hv_deadline_tsc != -1) { - tscl = rdtsc(); - if (vmx->hv_deadline_tsc > tscl) - /* set_hv_timer ensures the delta fits in 32-bits */ - delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> - cpu_preemption_timer_multi); - else - delta_tsc = 0; - - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); - vmx->loaded_vmcs->hv_timer_soft_disabled = false; - } else if (!vmx->loaded_vmcs->hv_timer_soft_disabled) { - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, -1); - vmx->loaded_vmcs->hv_timer_soft_disabled = true; - } -} - -void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) -{ - if (unlikely(host_rsp != vmx->loaded_vmcs->host_state.rsp)) { - vmx->loaded_vmcs->host_state.rsp = host_rsp; - vmcs_writel(HOST_RSP, host_rsp); - } -} - -bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); - -static void vmx_vcpu_run(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr3, cr4; - - /* Record the guest's net vcpu time for enforced NMI injections. */ - if (unlikely(!enable_vnmi && - vmx->loaded_vmcs->soft_vnmi_blocked)) - vmx->loaded_vmcs->entry_time = ktime_get(); - - /* Don't enter VMX if guest state is invalid, let the exit handler - start emulation until we arrive back to a valid state */ - if (vmx->emulation_required) - return; - - if (vmx->ple_window_dirty) { - vmx->ple_window_dirty = false; - vmcs_write32(PLE_WINDOW, vmx->ple_window); - } - - if (vmx->nested.need_vmcs12_to_shadow_sync) - nested_sync_vmcs12_to_shadow(vcpu); - - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) - vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP)) - vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); - - cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { - vmcs_writel(HOST_CR3, cr3); - vmx->loaded_vmcs->host_state.cr3 = cr3; - } - - cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { - vmcs_writel(HOST_CR4, cr4); - vmx->loaded_vmcs->host_state.cr4 = cr4; - } - - /* When single-stepping over STI and MOV SS, we must clear the - * corresponding interruptibility bits in the guest state. Otherwise - * vmentry fails as it then expects bit 14 (BS) in pending debug - * exceptions being set, but that's not correct for the guest debugging - * case. */ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - vmx_set_interrupt_shadow(vcpu, 0); - - kvm_load_guest_xsave_state(vcpu); - - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && - vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vcpu->arch.pkru); - - pt_guest_enter(vmx); - - atomic_switch_perf_msrs(vmx); - atomic_switch_umwait_control_msr(vmx); - - if (enable_preemption_timer) - vmx_update_hv_timer(vcpu); - - if (lapic_in_kernel(vcpu) && - vcpu->arch.apic->lapic_timer.timer_advance_ns) - kvm_wait_lapic_expire(vcpu); - - /* - * If this vCPU has touched SPEC_CTRL, restore the guest's value if - * it's non-zero. Since vmentry is serialising on affected CPUs, there - * is no need to worry about the conditional branch over the wrmsr - * being speculatively taken. - */ - x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0); - - /* L1D Flush includes CPU buffer clear to mitigate MDS */ - if (static_branch_unlikely(&vmx_l1d_should_flush)) - vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); - - if (vcpu->arch.cr2 != read_cr2()) - write_cr2(vcpu->arch.cr2); - - vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs, - vmx->loaded_vmcs->launched); - - vcpu->arch.cr2 = read_cr2(); - - /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) - vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - - x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); - - /* All fields are clean at this point */ - if (static_branch_unlikely(&enable_evmcs)) - current_evmcs->hv_clean_fields |= - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; - - if (static_branch_unlikely(&enable_evmcs)) - current_evmcs->hv_vp_id = vcpu->arch.hyperv.vp_index; - - /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ - if (vmx->host_debugctlmsr) - update_debugctlmsr(vmx->host_debugctlmsr); - -#ifndef CONFIG_X86_64 - /* - * The sysexit path does not restore ds/es, so we must set them to - * a reasonable value ourselves. - * - * We can't defer this to vmx_prepare_switch_to_host() since that - * function may be executed in interrupt context, which saves and - * restore segments around it, nullifying its effect. - */ - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); -#endif - - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) - | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_PDPTR) - | (1 << VCPU_EXREG_SEGMENTS) - | (1 << VCPU_EXREG_CR3)); - vcpu->arch.regs_dirty = 0; - - pt_guest_exit(vmx); - - /* - * eager fpu is enabled if PKEY is supported and CR4 is switched - * back on host, so it is safe to read guest PKRU from current - * XSAVE. - */ - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { - vcpu->arch.pkru = rdpkru(); - if (vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vmx->host_pkru); - } - - kvm_load_host_xsave_state(vcpu); - - vmx->nested.nested_run_pending = 0; - vmx->idt_vectoring_info = 0; - - vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON); - if ((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY) - kvm_machine_check(); - - if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) - return; - - vmx->loaded_vmcs->launched = 1; - vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - - vmx_recover_nmi_blocking(vmx); - vmx_complete_interrupts(vmx); -} - -static struct kvm *vmx_vm_alloc(void) -{ - struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx), - GFP_KERNEL_ACCOUNT | __GFP_ZERO, - PAGE_KERNEL); - return &kvm_vmx->kvm; -} - -static void vmx_vm_free(struct kvm *kvm) -{ - kfree(kvm->arch.hyperv.hv_pa_pg); - vfree(to_kvm_vmx(kvm)); -} - -static void vmx_free_vcpu(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (enable_pml) - vmx_destroy_pml_buffer(vmx); - free_vpid(vmx->vpid); - nested_vmx_free_vcpu(vcpu); - free_loaded_vmcs(vmx->loaded_vmcs); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); - kmem_cache_free(kvm_vcpu_cache, vmx); -} - -static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) -{ - int err; - struct vcpu_vmx *vmx; - unsigned long *msr_bitmap; - int i, cpu; - - BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0, - "struct kvm_vcpu must be at offset 0 for arch usercopy region"); - - vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); - if (!vmx) - return ERR_PTR(-ENOMEM); - - vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.user_fpu) { - printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); - err = -ENOMEM; - goto free_partial_vcpu; - } - - vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, - GFP_KERNEL_ACCOUNT); - if (!vmx->vcpu.arch.guest_fpu) { - printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); - err = -ENOMEM; - goto free_user_fpu; - } - - vmx->vpid = allocate_vpid(); - - err = kvm_vcpu_init(&vmx->vcpu, kvm, id); - if (err) - goto free_vcpu; - - err = -ENOMEM; - - /* - * If PML is turned on, failure on enabling PML just results in failure - * of creating the vcpu, therefore we can simplify PML logic (by - * avoiding dealing with cases, such as enabling PML partially on vcpus - * for the guest), etc. - */ - if (enable_pml) { - vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); - if (!vmx->pml_pg) - goto uninit_vcpu; - } - - BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS); - - for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { - u32 index = vmx_msr_index[i]; - u32 data_low, data_high; - int j = vmx->nmsrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - - vmx->guest_msrs[j].index = i; - vmx->guest_msrs[j].data = 0; - switch (index) { - case MSR_IA32_TSX_CTRL: - /* - * No need to pass TSX_CTRL_CPUID_CLEAR through, so - * let's avoid changing CPUID bits under the host - * kernel's feet. - */ - vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; - break; - default: - vmx->guest_msrs[j].mask = -1ull; - break; - } - ++vmx->nmsrs; - } - - err = alloc_loaded_vmcs(&vmx->vmcs01); - if (err < 0) - goto free_pml; - - msr_bitmap = vmx->vmcs01.msr_bitmap; - vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW); - if (kvm_cstate_in_guest(kvm)) { - vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R); - vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R); - } - vmx->msr_bitmap_mode = 0; - - vmx->loaded_vmcs = &vmx->vmcs01; - cpu = get_cpu(); - vmx_vcpu_load(&vmx->vcpu, cpu); - vmx->vcpu.cpu = cpu; - init_vmcs(vmx); - vmx_vcpu_put(&vmx->vcpu); - put_cpu(); - if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - err = alloc_apic_access_page(kvm); - if (err) - goto free_vmcs; - } - - if (enable_ept && !enable_unrestricted_guest) { - err = init_rmode_identity_map(kvm); - if (err) - goto free_vmcs; - } - - if (nested) - nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, - vmx_capability.ept, - kvm_vcpu_apicv_active(&vmx->vcpu)); - else - memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); - - vmx->nested.posted_intr_nv = -1; - vmx->nested.current_vmptr = -1ull; - - vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; - - /* - * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR - * or POSTED_INTR_WAKEUP_VECTOR. - */ - vmx->pi_desc.nv = POSTED_INTR_VECTOR; - vmx->pi_desc.sn = 1; - - vmx->ept_pointer = INVALID_PAGE; - - return &vmx->vcpu; - -free_vmcs: - free_loaded_vmcs(vmx->loaded_vmcs); -free_pml: - vmx_destroy_pml_buffer(vmx); -uninit_vcpu: - kvm_vcpu_uninit(&vmx->vcpu); -free_vcpu: - free_vpid(vmx->vpid); - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); -free_user_fpu: - kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); -free_partial_vcpu: - kmem_cache_free(kvm_vcpu_cache, vmx); - return ERR_PTR(err); -} - -#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" -#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n" - -static int vmx_vm_init(struct kvm *kvm) -{ - spin_lock_init(&to_kvm_vmx(kvm)->ept_pointer_lock); - - if (!ple_gap) - kvm->arch.pause_in_guest = true; - - if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) { - switch (l1tf_mitigation) { - case L1TF_MITIGATION_OFF: - case L1TF_MITIGATION_FLUSH_NOWARN: - /* 'I explicitly don't care' is set */ - break; - case L1TF_MITIGATION_FLUSH: - case L1TF_MITIGATION_FLUSH_NOSMT: - case L1TF_MITIGATION_FULL: - /* - * Warn upon starting the first VM in a potentially - * insecure environment. - */ - if (sched_smt_active()) - pr_warn_once(L1TF_MSG_SMT); - if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) - pr_warn_once(L1TF_MSG_L1D); - break; - case L1TF_MITIGATION_FULL_FORCE: - /* Flush is enforced */ - break; - } - } - return 0; -} - -static int __init vmx_check_processor_compat(void) -{ - struct vmcs_config vmcs_conf; - struct vmx_capability vmx_cap; - - if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) - return -EIO; - if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, - enable_apicv); - if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { - printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", - smp_processor_id()); - return -EIO; - } - return 0; -} - -static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) -{ - u8 cache; - u64 ipat = 0; - - /* For VT-d and EPT combination - * 1. MMIO: always map as UC - * 2. EPT with VT-d: - * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. - * b. VT-d with snooping control feature: snooping control feature of - * VT-d engine can guarantee the cache correctness. Just set it - * to WB to keep consistent with host. So the same as item 3. - * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep - * consistent with host MTRR - */ - if (is_mmio) { - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - - if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { - ipat = VMX_EPT_IPAT_BIT; - cache = MTRR_TYPE_WRBACK; - goto exit; - } - - if (kvm_read_cr0(vcpu) & X86_CR0_CD) { - ipat = VMX_EPT_IPAT_BIT; - if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cache = MTRR_TYPE_WRBACK; - else - cache = MTRR_TYPE_UNCACHABLE; - goto exit; - } - - cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); - -exit: - return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; -} - -static int vmx_get_lpage_level(void) -{ - if (enable_ept && !cpu_has_vmx_ept_1g_page()) - return PT_DIRECTORY_LEVEL; - else - /* For shadow and EPT supported 1GB page */ - return PT_PDPE_LEVEL; -} - -static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx) -{ - /* - * These bits in the secondary execution controls field - * are dynamic, the others are mostly based on the hypervisor - * architecture and the guest's CPUID. Do not touch the - * dynamic bits. - */ - u32 mask = - SECONDARY_EXEC_SHADOW_VMCS | - SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_DESC; - - u32 new_ctl = vmx->secondary_exec_control; - u32 cur_ctl = secondary_exec_controls_get(vmx); - - secondary_exec_controls_set(vmx, (new_ctl & ~mask) | (cur_ctl & mask)); -} - -/* - * Generate MSR_IA32_VMX_CR{0,4}_FIXED1 according to CPUID. Only set bits - * (indicating "allowed-1") if they are supported in the guest's CPUID. - */ -static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_cpuid_entry2 *entry; - - vmx->nested.msrs.cr0_fixed1 = 0xffffffff; - vmx->nested.msrs.cr4_fixed1 = X86_CR4_PCE; - -#define cr4_fixed1_update(_cr4_mask, _reg, _cpuid_mask) do { \ - if (entry && (entry->_reg & (_cpuid_mask))) \ - vmx->nested.msrs.cr4_fixed1 |= (_cr4_mask); \ -} while (0) - - entry = kvm_find_cpuid_entry(vcpu, 0x1, 0); - cr4_fixed1_update(X86_CR4_VME, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_PVI, edx, bit(X86_FEATURE_VME)); - cr4_fixed1_update(X86_CR4_TSD, edx, bit(X86_FEATURE_TSC)); - cr4_fixed1_update(X86_CR4_DE, edx, bit(X86_FEATURE_DE)); - cr4_fixed1_update(X86_CR4_PSE, edx, bit(X86_FEATURE_PSE)); - cr4_fixed1_update(X86_CR4_PAE, edx, bit(X86_FEATURE_PAE)); - cr4_fixed1_update(X86_CR4_MCE, edx, bit(X86_FEATURE_MCE)); - cr4_fixed1_update(X86_CR4_PGE, edx, bit(X86_FEATURE_PGE)); - cr4_fixed1_update(X86_CR4_OSFXSR, edx, bit(X86_FEATURE_FXSR)); - cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM)); - cr4_fixed1_update(X86_CR4_VMXE, ecx, bit(X86_FEATURE_VMX)); - cr4_fixed1_update(X86_CR4_SMXE, ecx, bit(X86_FEATURE_SMX)); - cr4_fixed1_update(X86_CR4_PCIDE, ecx, bit(X86_FEATURE_PCID)); - cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, bit(X86_FEATURE_XSAVE)); - - entry = kvm_find_cpuid_entry(vcpu, 0x7, 0); - cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, bit(X86_FEATURE_FSGSBASE)); - cr4_fixed1_update(X86_CR4_SMEP, ebx, bit(X86_FEATURE_SMEP)); - cr4_fixed1_update(X86_CR4_SMAP, ebx, bit(X86_FEATURE_SMAP)); - cr4_fixed1_update(X86_CR4_PKE, ecx, bit(X86_FEATURE_PKU)); - cr4_fixed1_update(X86_CR4_UMIP, ecx, bit(X86_FEATURE_UMIP)); - cr4_fixed1_update(X86_CR4_LA57, ecx, bit(X86_FEATURE_LA57)); - -#undef cr4_fixed1_update -} - -static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (kvm_mpx_supported()) { - bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX); - - if (mpx_enabled) { - vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; - vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; - } else { - vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS; - vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS; - } - } -} - -static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_cpuid_entry2 *best = NULL; - int i; - - for (i = 0; i < PT_CPUID_LEAVES; i++) { - best = kvm_find_cpuid_entry(vcpu, 0x14, i); - if (!best) - return; - vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax; - vmx->pt_desc.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM] = best->ebx; - vmx->pt_desc.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM] = best->ecx; - vmx->pt_desc.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM] = best->edx; - } - - /* Get the number of configurable Address Ranges for filtering */ - vmx->pt_desc.addr_range = intel_pt_validate_cap(vmx->pt_desc.caps, - PT_CAP_num_address_ranges); - - /* Initialize and clear the no dependency bits */ - vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS | - RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC); - - /* - * If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set otherwise - * will inject an #GP - */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_cr3_filtering)) - vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_CR3EN; - - /* - * If CPUID.(EAX=14H,ECX=0):EBX[1]=1 CYCEn, CycThresh and - * PSBFreq can be set - */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_psb_cyc)) - vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_CYCLEACC | - RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ); - - /* - * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn BranchEn and - * MTCFreq can be set - */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc)) - vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN | - RTIT_CTL_BRANCH_EN | RTIT_CTL_MTC_RANGE); - - /* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_ptwrite)) - vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_FUP_ON_PTW | - RTIT_CTL_PTW_EN); - - /* If CPUID.(EAX=14H,ECX=0):EBX[5]=1 PwrEvEn can be set */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_power_event_trace)) - vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_PWR_EVT_EN; - - /* If CPUID.(EAX=14H,ECX=0):ECX[0]=1 ToPA can be set */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output)) - vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA; - - /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */ - if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys)) - vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN; - - /* unmask address range configure area */ - for (i = 0; i < vmx->pt_desc.addr_range; i++) - vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4)); -} - -static void vmx_cpuid_update(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - /* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */ - vcpu->arch.xsaves_enabled = false; - - if (cpu_has_secondary_exec_ctrls()) { - vmx_compute_secondary_exec_control(vmx); - vmcs_set_secondary_exec_control(vmx); - } - - if (nested_vmx_allowed(vcpu)) - to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= - FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX | - FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - else - to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= - ~(FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX | - FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX); - - if (nested_vmx_allowed(vcpu)) { - nested_vmx_cr_fixed1_bits_update(vcpu); - nested_vmx_entry_exit_ctls_update(vcpu); - } - - if (boot_cpu_has(X86_FEATURE_INTEL_PT) && - guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) - update_intel_pt_cfg(vcpu); - - if (boot_cpu_has(X86_FEATURE_RTM)) { - struct shared_msr_entry *msr; - msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL); - if (msr) { - bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); - vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); - } - } -} - -static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) -{ - if (func == 1 && nested) - entry->ecx |= bit(X86_FEATURE_VMX); -} - -static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - to_vmx(vcpu)->req_immediate_exit = true; -} - -static int vmx_check_intercept(struct kvm_vcpu *vcpu, - struct x86_instruction_info *info, - enum x86_intercept_stage stage) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; - - /* - * RDPID causes #UD if disabled through secondary execution controls. - * Because it is marked as EmulateOnUD, we need to intercept it here. - */ - if (info->intercept == x86_intercept_rdtscp && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; - return X86EMUL_PROPAGATE_FAULT; - } - - /* TODO: check more intercepts... */ - return X86EMUL_CONTINUE; -} - -#ifdef CONFIG_X86_64 -/* (a << shift) / divisor, return 1 if overflow otherwise 0 */ -static inline int u64_shl_div_u64(u64 a, unsigned int shift, - u64 divisor, u64 *result) -{ - u64 low = a << shift, high = a >> (64 - shift); - - /* To avoid the overflow on divq */ - if (high >= divisor) - return 1; - - /* Low hold the result, high hold rem which is discarded */ - asm("divq %2\n\t" : "=a" (low), "=d" (high) : - "rm" (divisor), "0" (low), "1" (high)); - *result = low; - - return 0; -} - -static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, - bool *expired) -{ - struct vcpu_vmx *vmx; - u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; - struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; - - if (kvm_mwait_in_guest(vcpu->kvm) || - kvm_can_post_timer_interrupt(vcpu)) - return -EOPNOTSUPP; - - vmx = to_vmx(vcpu); - tscl = rdtsc(); - guest_tscl = kvm_read_l1_tsc(vcpu, tscl); - delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; - lapic_timer_advance_cycles = nsec_to_cycles(vcpu, - ktimer->timer_advance_ns); - - if (delta_tsc > lapic_timer_advance_cycles) - delta_tsc -= lapic_timer_advance_cycles; - else - delta_tsc = 0; - - /* Convert to host delta tsc if tsc scaling is enabled */ - if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && - delta_tsc && u64_shl_div_u64(delta_tsc, - kvm_tsc_scaling_ratio_frac_bits, - vcpu->arch.tsc_scaling_ratio, &delta_tsc)) - return -ERANGE; - - /* - * If the delta tsc can't fit in the 32 bit after the multi shift, - * we can't use the preemption timer. - * It's possible that it fits on later vmentries, but checking - * on every vmentry is costly so we just use an hrtimer. - */ - if (delta_tsc >> (cpu_preemption_timer_multi + 32)) - return -ERANGE; - - vmx->hv_deadline_tsc = tscl + delta_tsc; - *expired = !delta_tsc; - return 0; -} - -static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) -{ - to_vmx(vcpu)->hv_deadline_tsc = -1; -} -#endif - -static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu) -{ - if (!kvm_pause_in_guest(vcpu->kvm)) - shrink_ple_window(vcpu); -} - -static void vmx_slot_enable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - kvm_mmu_slot_leaf_clear_dirty(kvm, slot); - kvm_mmu_slot_largepage_remove_write_access(kvm, slot); -} - -static void vmx_slot_disable_log_dirty(struct kvm *kvm, - struct kvm_memory_slot *slot) -{ - kvm_mmu_slot_set_dirty(kvm, slot); -} - -static void vmx_flush_log_dirty(struct kvm *kvm) -{ - kvm_flush_pml_buffers(kvm); -} - -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) -{ - struct vmcs12 *vmcs12; - struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa, dst; - - if (is_guest_mode(vcpu)) { - WARN_ON_ONCE(vmx->nested.pml_full); - - /* - * Check if PML is enabled for the nested guest. - * Whether eptp bit 6 is set is already checked - * as part of A/D emulation. - */ - vmcs12 = get_vmcs12(vcpu); - if (!nested_cpu_has_pml(vmcs12)) - return 0; - - if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { - vmx->nested.pml_full = true; - return 1; - } - - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; - dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; - - if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, - offset_in_page(dst), sizeof(gpa))) - return 0; - - vmcs12->guest_pml_index--; - } - - return 0; -} - -static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *memslot, - gfn_t offset, unsigned long mask) -{ - kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); -} - -static void __pi_post_block(struct kvm_vcpu *vcpu) -{ - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - - do { - old.control = new.control = pi_desc->control; - WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, - "Wakeup handler not enabled while the VCPU is blocked\n"); - - dest = cpu_physical_id(vcpu->cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - - if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - vcpu->pre_pcpu = -1; - } -} - -/* - * This routine does the following things for vCPU which is going - * to be blocked if VT-d PI is enabled. - * - Store the vCPU to the wakeup list, so when interrupts happen - * we can find the right vCPU to wake up. - * - Change the Posted-interrupt descriptor as below: - * 'NDST' <-- vcpu->pre_pcpu - * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR - * - If 'ON' is set during this process, which means at least one - * interrupt is posted for this vCPU, we cannot block it, in - * this case, return 1, otherwise, return 0. - * - */ -static int pi_pre_block(struct kvm_vcpu *vcpu) -{ - unsigned int dest; - struct pi_desc old, new; - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) - return 0; - - WARN_ON(irqs_disabled()); - local_irq_disable(); - if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { - vcpu->pre_pcpu = vcpu->cpu; - spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); - } - - do { - old.control = new.control = pi_desc->control; - - WARN((pi_desc->sn == 1), - "Warning: SN field of posted-interrupts " - "is set before blocking\n"); - - /* - * Since vCPU can be preempted during this process, - * vcpu->cpu could be different with pre_pcpu, we - * need to set pre_pcpu as the destination of wakeup - * notification event, then we can find the right vCPU - * to wakeup in wakeup handler if interrupts happen - * when the vCPU is in blocked state. - */ - dest = cpu_physical_id(vcpu->pre_pcpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* set 'NV' to 'wakeup vector' */ - new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg64(&pi_desc->control, old.control, - new.control) != old.control); - - /* We should not block the vCPU if an interrupt is posted for it. */ - if (pi_test_on(pi_desc) == 1) - __pi_post_block(vcpu); - - local_irq_enable(); - return (vcpu->pre_pcpu == -1); -} - -static int vmx_pre_block(struct kvm_vcpu *vcpu) -{ - if (pi_pre_block(vcpu)) - return 1; - - if (kvm_lapic_hv_timer_in_use(vcpu)) - kvm_lapic_switch_to_sw_timer(vcpu); - - return 0; -} - -static void pi_post_block(struct kvm_vcpu *vcpu) -{ - if (vcpu->pre_pcpu == -1) - return; - - WARN_ON(irqs_disabled()); - local_irq_disable(); - __pi_post_block(vcpu); - local_irq_enable(); -} - -static void vmx_post_block(struct kvm_vcpu *vcpu) -{ - if (kvm_x86_ops->set_hv_timer) - kvm_lapic_switch_to_hv_timer(vcpu); - - pi_post_block(vcpu); -} - -/* - * vmx_update_pi_irte - set IRTE for Posted-Interrupts - * - * @kvm: kvm - * @host_irq: host irq of the interrupt - * @guest_irq: gsi of the interrupt - * @set: set or unset PI - * returns 0 on success, < 0 on failure - */ -static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) -{ - struct kvm_kernel_irq_routing_entry *e; - struct kvm_irq_routing_table *irq_rt; - struct kvm_lapic_irq irq; - struct kvm_vcpu *vcpu; - struct vcpu_data vcpu_info; - int idx, ret = 0; - - if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(kvm->vcpus[0])) - return 0; - - idx = srcu_read_lock(&kvm->irq_srcu); - irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - if (guest_irq >= irq_rt->nr_rt_entries || - hlist_empty(&irq_rt->map[guest_irq])) { - pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n", - guest_irq, irq_rt->nr_rt_entries); - goto out; - } - - hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { - if (e->type != KVM_IRQ_ROUTING_MSI) - continue; - /* - * VT-d PI cannot support posting multicast/broadcast - * interrupts to a vCPU, we still use interrupt remapping - * for these kind of interrupts. - * - * For lowest-priority interrupts, we only support - * those with single CPU as the destination, e.g. user - * configures the interrupts via /proc/irq or uses - * irqbalance to make the interrupts single-CPU. - * - * We will support full lowest-priority interrupt later. - * - * In addition, we can only inject generic interrupts using - * the PI mechanism, refuse to route others through it. - */ - - kvm_set_msi_irq(kvm, e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || - !kvm_irq_is_postable(&irq)) { - /* - * Make sure the IRTE is in remapped mode if - * we don't handle it in posted mode. - */ - ret = irq_set_vcpu_affinity(host_irq, NULL); - if (ret < 0) { - printk(KERN_INFO - "failed to back to remapped mode, irq: %u\n", - host_irq); - goto out; - } - - continue; - } - - vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); - vcpu_info.vector = irq.vector; - - trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi, - vcpu_info.vector, vcpu_info.pi_desc_addr, set); - - if (set) - ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); - else - ret = irq_set_vcpu_affinity(host_irq, NULL); - - if (ret < 0) { - printk(KERN_INFO "%s: failed to update PI IRTE\n", - __func__); - goto out; - } - } - - ret = 0; -out: - srcu_read_unlock(&kvm->irq_srcu, idx); - return ret; -} - -static void vmx_setup_mce(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.mcg_cap & MCG_LMCE_P) - to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |= - FEATURE_CONTROL_LMCE; - else - to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= - ~FEATURE_CONTROL_LMCE; -} - -static int vmx_smi_allowed(struct kvm_vcpu *vcpu) -{ - /* we need a nested vmexit to enter SMM, postpone if run is pending */ - if (to_vmx(vcpu)->nested.nested_run_pending) - return 0; - return 1; -} - -static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - vmx->nested.smm.guest_mode = is_guest_mode(vcpu); - if (vmx->nested.smm.guest_mode) - nested_vmx_vmexit(vcpu, -1, 0, 0); - - vmx->nested.smm.vmxon = vmx->nested.vmxon; - vmx->nested.vmxon = false; - vmx_clear_hlt(vcpu); - return 0; -} - -static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - int ret; - - if (vmx->nested.smm.vmxon) { - vmx->nested.vmxon = true; - vmx->nested.smm.vmxon = false; - } - - if (vmx->nested.smm.guest_mode) { - ret = nested_vmx_enter_non_root_mode(vcpu, false); - if (ret) - return ret; - - vmx->nested.smm.guest_mode = false; - } - return 0; -} - -static int enable_smi_window(struct kvm_vcpu *vcpu) -{ - return 0; -} - -static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) -{ - return false; -} - -static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) -{ - return to_vmx(vcpu)->nested.vmxon; -} - -static __init int hardware_setup(void) -{ - unsigned long host_bndcfgs; - struct desc_ptr dt; - int r, i; - - rdmsrl_safe(MSR_EFER, &host_efer); - - store_idt(&dt); - host_idt_base = dt.address; - - for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) - kvm_define_shared_msr(i, vmx_msr_index[i]); - - if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) - return -EIO; - - if (boot_cpu_has(X86_FEATURE_NX)) - kvm_enable_efer_bits(EFER_NX); - - if (boot_cpu_has(X86_FEATURE_MPX)) { - rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs); - WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); - } - - if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || - !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) - enable_vpid = 0; - - if (!cpu_has_vmx_ept() || - !cpu_has_vmx_ept_4levels() || - !cpu_has_vmx_ept_mt_wb() || - !cpu_has_vmx_invept_global()) - enable_ept = 0; - - if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) - enable_ept_ad_bits = 0; - - if (!cpu_has_vmx_unrestricted_guest() || !enable_ept) - enable_unrestricted_guest = 0; - - if (!cpu_has_vmx_flexpriority()) - flexpriority_enabled = 0; - - if (!cpu_has_virtual_nmis()) - enable_vnmi = 0; - - /* - * set_apic_access_page_addr() is used to reload apic access - * page upon invalidation. No need to do anything if not - * using the APIC_ACCESS_ADDR VMCS field. - */ - if (!flexpriority_enabled) - kvm_x86_ops->set_apic_access_page_addr = NULL; - - if (!cpu_has_vmx_tpr_shadow()) - kvm_x86_ops->update_cr8_intercept = NULL; - - if (enable_ept && !cpu_has_vmx_ept_2m_page()) - kvm_disable_largepages(); - -#if IS_ENABLED(CONFIG_HYPERV) - if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH - && enable_ept) { - kvm_x86_ops->tlb_remote_flush = hv_remote_flush_tlb; - kvm_x86_ops->tlb_remote_flush_with_range = - hv_remote_flush_tlb_with_range; - } -#endif - - if (!cpu_has_vmx_ple()) { - ple_gap = 0; - ple_window = 0; - ple_window_grow = 0; - ple_window_max = 0; - ple_window_shrink = 0; - } - - if (!cpu_has_vmx_apicv()) { - enable_apicv = 0; - kvm_x86_ops->sync_pir_to_irr = NULL; - } - - if (cpu_has_vmx_tsc_scaling()) { - kvm_has_tsc_control = true; - kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; - kvm_tsc_scaling_ratio_frac_bits = 48; - } - - set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ - - if (enable_ept) - vmx_enable_tdp(); - else - kvm_disable_tdp(); - - /* - * Only enable PML when hardware supports PML feature, and both EPT - * and EPT A/D bit features are enabled -- PML depends on them to work. - */ - if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml()) - enable_pml = 0; - - if (!enable_pml) { - kvm_x86_ops->slot_enable_log_dirty = NULL; - kvm_x86_ops->slot_disable_log_dirty = NULL; - kvm_x86_ops->flush_log_dirty = NULL; - kvm_x86_ops->enable_log_dirty_pt_masked = NULL; - } - - if (!cpu_has_vmx_preemption_timer()) - enable_preemption_timer = false; - - if (enable_preemption_timer) { - u64 use_timer_freq = 5000ULL * 1000 * 1000; - u64 vmx_msr; - - rdmsrl(MSR_IA32_VMX_MISC, vmx_msr); - cpu_preemption_timer_multi = - vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; - - if (tsc_khz) - use_timer_freq = (u64)tsc_khz * 1000; - use_timer_freq >>= cpu_preemption_timer_multi; - - /* - * KVM "disables" the preemption timer by setting it to its max - * value. Don't use the timer if it might cause spurious exits - * at a rate faster than 0.1 Hz (of uninterrupted guest time). - */ - if (use_timer_freq > 0xffffffffu / 10) - enable_preemption_timer = false; - } - - if (!enable_preemption_timer) { - kvm_x86_ops->set_hv_timer = NULL; - kvm_x86_ops->cancel_hv_timer = NULL; - kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; - } - - kvm_set_posted_intr_wakeup_handler(wakeup_handler); - - kvm_mce_cap_supported |= MCG_LMCE_P; - - if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST) - return -EINVAL; - if (!enable_ept || !cpu_has_vmx_intel_pt()) - pt_mode = PT_MODE_SYSTEM; - - if (nested) { - nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept, enable_apicv); - - r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); - if (r) - return r; - } - - r = alloc_kvm_area(); - if (r) - nested_vmx_hardware_unsetup(); - return r; -} - -static __exit void hardware_unsetup(void) -{ - if (nested) - nested_vmx_hardware_unsetup(); - - free_kvm_area(); -} - -static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { - .cpu_has_kvm_support = cpu_has_kvm_support, - .disabled_by_bios = vmx_disabled_by_bios, - .hardware_setup = hardware_setup, - .hardware_unsetup = hardware_unsetup, - .check_processor_compatibility = vmx_check_processor_compat, - .hardware_enable = hardware_enable, - .hardware_disable = hardware_disable, - .cpu_has_accelerated_tpr = report_flexpriority, - .has_emulated_msr = vmx_has_emulated_msr, - - .vm_init = vmx_vm_init, - .vm_alloc = vmx_vm_alloc, - .vm_free = vmx_vm_free, - - .vcpu_create = vmx_create_vcpu, - .vcpu_free = vmx_free_vcpu, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_guest_switch = vmx_prepare_switch_to_guest, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - - .update_bp_intercept = update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cpl = vmx_get_cpl, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, - .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, - .set_cr0 = vmx_set_cr0, - .set_cr3 = vmx_set_cr3, - .set_cr4 = vmx_set_cr4, - .set_efer = vmx_set_efer, - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .get_dr6 = vmx_get_dr6, - .set_dr6 = vmx_set_dr6, - .set_dr7 = vmx_set_dr7, - .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, - .cache_reg = vmx_cache_reg, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - - .tlb_flush = vmx_flush_tlb, - .tlb_flush_gva = vmx_flush_tlb_gva, - - .run = vmx_vcpu_run, - .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, - .set_interrupt_shadow = vmx_set_interrupt_shadow, - .get_interrupt_shadow = vmx_get_interrupt_shadow, - .patch_hypercall = vmx_patch_hypercall, - .set_irq = vmx_inject_irq, - .set_nmi = vmx_inject_nmi, - .queue_exception = vmx_queue_exception, - .cancel_injection = vmx_cancel_injection, - .interrupt_allowed = vmx_interrupt_allowed, - .nmi_allowed = vmx_nmi_allowed, - .get_nmi_mask = vmx_get_nmi_mask, - .set_nmi_mask = vmx_set_nmi_mask, - .enable_nmi_window = enable_nmi_window, - .enable_irq_window = enable_irq_window, - .update_cr8_intercept = update_cr8_intercept, - .set_virtual_apic_mode = vmx_set_virtual_apic_mode, - .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .get_enable_apicv = vmx_get_enable_apicv, - .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, - .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, - .hwapic_irr_update = vmx_hwapic_irr_update, - .hwapic_isr_update = vmx_hwapic_isr_update, - .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, - .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_posted_interrupt = vmx_deliver_posted_interrupt, - .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt, - - .set_tss_addr = vmx_set_tss_addr, - .set_identity_map_addr = vmx_set_identity_map_addr, - .get_tdp_level = get_ept_level, - .get_mt_mask = vmx_get_mt_mask, - - .get_exit_info = vmx_get_exit_info, - - .get_lpage_level = vmx_get_lpage_level, - - .cpuid_update = vmx_cpuid_update, - - .rdtscp_supported = vmx_rdtscp_supported, - .invpcid_supported = vmx_invpcid_supported, - - .set_supported_cpuid = vmx_set_supported_cpuid, - - .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - - .read_l1_tsc_offset = vmx_read_l1_tsc_offset, - .write_l1_tsc_offset = vmx_write_l1_tsc_offset, - - .set_tdp_cr3 = vmx_set_cr3, - - .check_intercept = vmx_check_intercept, - .handle_exit_irqoff = vmx_handle_exit_irqoff, - .mpx_supported = vmx_mpx_supported, - .xsaves_supported = vmx_xsaves_supported, - .umip_emulated = vmx_umip_emulated, - .pt_supported = vmx_pt_supported, - - .request_immediate_exit = vmx_request_immediate_exit, - - .sched_in = vmx_sched_in, - - .slot_enable_log_dirty = vmx_slot_enable_log_dirty, - .slot_disable_log_dirty = vmx_slot_disable_log_dirty, - .flush_log_dirty = vmx_flush_log_dirty, - .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, - .write_log_dirty = vmx_write_pml_buffer, - - .pre_block = vmx_pre_block, - .post_block = vmx_post_block, - - .pmu_ops = &intel_pmu_ops, - - .update_pi_irte = vmx_update_pi_irte, - -#ifdef CONFIG_X86_64 - .set_hv_timer = vmx_set_hv_timer, - .cancel_hv_timer = vmx_cancel_hv_timer, -#endif - - .setup_mce = vmx_setup_mce, - - .smi_allowed = vmx_smi_allowed, - .pre_enter_smm = vmx_pre_enter_smm, - .pre_leave_smm = vmx_pre_leave_smm, - .enable_smi_window = enable_smi_window, - - .check_nested_events = NULL, - .get_nested_state = NULL, - .set_nested_state = NULL, - .get_vmcs12_pages = NULL, - .nested_enable_evmcs = NULL, - .nested_get_evmcs_version = NULL, - .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, - .apic_init_signal_blocked = vmx_apic_init_signal_blocked, -}; - -static void vmx_cleanup_l1d_flush(void) -{ - if (vmx_l1d_flush_pages) { - free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER); - vmx_l1d_flush_pages = NULL; - } - /* Restore state so sysfs ignores VMX */ - l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; -} - -static void vmx_exit(void) -{ -#ifdef CONFIG_KEXEC_CORE - RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); - synchronize_rcu(); -#endif - - kvm_exit(); - -#if IS_ENABLED(CONFIG_HYPERV) - if (static_branch_unlikely(&enable_evmcs)) { - int cpu; - struct hv_vp_assist_page *vp_ap; - /* - * Reset everything to support using non-enlightened VMCS - * access later (e.g. when we reload the module with - * enlightened_vmcs=0) - */ - for_each_online_cpu(cpu) { - vp_ap = hv_get_vp_assist_page(cpu); - - if (!vp_ap) - continue; - - vp_ap->nested_control.features.directhypercall = 0; - vp_ap->current_nested_vmcs = 0; - vp_ap->enlighten_vmentry = 0; - } - - static_branch_disable(&enable_evmcs); - } -#endif - vmx_cleanup_l1d_flush(); -} -module_exit(vmx_exit); - -static int __init vmx_init(void) -{ - int r; - -#if IS_ENABLED(CONFIG_HYPERV) - /* - * Enlightened VMCS usage should be recommended and the host needs - * to support eVMCS v1 or above. We can also disable eVMCS support - * with module parameter. - */ - if (enlightened_vmcs && - ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && - (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= - KVM_EVMCS_VERSION) { - int cpu; - - /* Check that we have assist pages on all online CPUs */ - for_each_online_cpu(cpu) { - if (!hv_get_vp_assist_page(cpu)) { - enlightened_vmcs = false; - break; - } - } - - if (enlightened_vmcs) { - pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n"); - static_branch_enable(&enable_evmcs); - } - - if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_direct_tlbflush - = hv_enable_direct_tlbflush; - - } else { - enlightened_vmcs = false; - } -#endif - - r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); - if (r) - return r; - - /* - * Must be called after kvm_init() so enable_ept is properly set - * up. Hand the parameter mitigation value in which was stored in - * the pre module init parser. If no parameter was given, it will - * contain 'auto' which will be turned into the default 'cond' - * mitigation mode. - */ - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } - -#ifdef CONFIG_KEXEC_CORE - rcu_assign_pointer(crash_vmclear_loaded_vmcss, - crash_vmclear_local_loaded_vmcss); -#endif - vmx_check_vmcs12_offsets(); - - return 0; -} -module_init(vmx_init);

From: Paul Kocialkowski paul.kocialkowski@bootlin.com

[ Upstream commit fd1a5e521c3c083bb43ea731aae0f8b95f12b9bd ]

psbfb_probe performs an evaluation of the required size from the stolen GTT memory, but gets it wrong in two distinct ways: - The resulting size must be page-size-aligned; - The size to allocate is derived from the surface dimensions, not the fb dimensions.

When two connectors are connected with different modes, the smallest will be stored in the fb dimensions, but the size that needs to be allocated must match the largest (surface) dimensions. This is what is used in the actual allocation code.

Fix this by correcting the evaluation to conform to the two points above. It allows correctly switching to 16bpp when one connector is e.g. 1920x1080 and the other is 1024x768.

Signed-off-by: Paul Kocialkowski paul.kocialkowski@bootlin.com Signed-off-by: Patrik Jakobsson patrik.r.jakobsson@gmail.com Link: https://patchwork.freedesktop.org/patch/msgid/20191107153048.843881-1-paul.k... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/gma500/framebuffer.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c index 2570c7f647a63..883fc45870dd9 100644 --- a/drivers/gpu/drm/gma500/framebuffer.c +++ b/drivers/gpu/drm/gma500/framebuffer.c @@ -486,6 +486,7 @@ static int psbfb_probe(struct drm_fb_helper *helper, container_of(helper, struct psb_fbdev, psb_fb_helper); struct drm_device *dev = psb_fbdev->psb_fb_helper.dev; struct drm_psb_private *dev_priv = dev->dev_private; + unsigned int fb_size; int bytespp;

bytespp = sizes->surface_bpp / 8; @@ -495,8 +496,11 @@ static int psbfb_probe(struct drm_fb_helper *helper, /* If the mode will not fit in 32bit then switch to 16bit to get a console on full resolution. The X mode setting server will allocate its own 32bit GEM framebuffer */ - if (ALIGN(sizes->fb_width * bytespp, 64) * sizes->fb_height > - dev_priv->vram_stolen_size) { + fb_size = ALIGN(sizes->surface_width * bytespp, 64) * + sizes->surface_height; + fb_size = ALIGN(fb_size, PAGE_SIZE); + + if (fb_size > dev_priv->vram_stolen_size) { sizes->surface_bpp = 16; sizes->surface_depth = 16; }

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit 216b44000ada87a63891a8214c347e05a4aea8fe ]

The brcmu_pkt_buf_free_skb() function frees "pkt" so it leads to a static checker warning:

drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c:1974 brcmf_sdio_readframes() error: dereferencing freed memory 'pkt'

It looks like there was supposed to be a continue after we free "pkt".

Fixes: 4754fceeb9a6 ("brcmfmac: streamline SDIO read frame routine") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Acked-by: Franky Lin franky.lin@broadcom.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 4c28b04ea6053..d198a8780b966 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -1932,6 +1932,7 @@ static uint brcmf_sdio_readframes(struct brcmf_sdio *bus, uint maxframes) BRCMF_SDIO_FT_NORMAL)) { rd->len = 0; brcmu_pkt_buf_free_skb(pkt); + continue; } bus->sdcnt.rx_readahead_cnt++; if (rd->len != roundup(rd_new.len, 16)) {

From: Ritesh Harjani riteshh@linux.ibm.com

[ Upstream commit f629afe3369e9885fd6e9cc7a4f514b6a65cf9e9 ]

Apparently our current rwsem code doesn't like doing the trylock, then lock for real scheme. So change our dax read/write methods to just do the trylock for the RWF_NOWAIT case. This seems to fix AIM7 regression in some scalable filesystems upto ~25% in some cases. Claimed in commit 942491c9e6d6 ("xfs: fix AIM7 regression")

Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Matthew Bobrowski mbobrowski@mbobrowski.org Tested-by: Joseph Qi joseph.qi@linux.alibaba.com Signed-off-by: Ritesh Harjani riteshh@linux.ibm.com Link: https://lore.kernel.org/r/20191212055557.11151-2-riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/file.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 4ede0af9d6fe3..acec134da57df 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -38,9 +38,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret;

- if (!inode_trylock_shared(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock_shared(inode)) return -EAGAIN; + } else { inode_lock_shared(inode); } /* @@ -188,9 +189,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret;

- if (!inode_trylock(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) return -EAGAIN; + } else { inode_lock(inode); } ret = ext4_write_checks(iocb, from);

From: Vladimir Oltean olteanv@gmail.com

[ Upstream commit c26a2c2ddc0115eb088873f5c309cf46b982f522 ]

The driver wrongly assumes that it is the only entity that can set the SKBTX_IN_PROGRESS bit of the current skb. Therefore, in the gfar_clean_tx_ring function, where the TX timestamp is collected if necessary, the aforementioned bit is used to discriminate whether or not the TX timestamp should be delivered to the socket's error queue.

But a stacked driver such as a DSA switch can also set the SKBTX_IN_PROGRESS bit, which is actually exactly what it should do in order to denote that the hardware timestamping process is undergoing.

Therefore, gianfar would misinterpret the "in progress" bit as being its own, and deliver a second skb clone in the socket's error queue, completely throwing off a PTP process which is not expecting to receive it, _even though_ TX timestamping is not enabled for gianfar.

There have been discussions [0] as to whether non-MAC drivers need or not to set SKBTX_IN_PROGRESS at all (whose purpose is to avoid sending 2 timestamps, a sw and a hw one, to applications which only expect one). But as of this patch, there are at least 2 PTP drivers that would break in conjunction with gianfar: the sja1105 DSA switch and the felix switch, by way of its ocelot core driver.

So regardless of that conclusion, fix the gianfar driver to not do stuff based on flags set by others and not intended for it.

[0]: https://www.spinics.net/lists/netdev/msg619699.html

Fixes: f0ee7acfcdd4 ("gianfar: Add hardware TX timestamping support") Signed-off-by: Vladimir Oltean olteanv@gmail.com Acked-by: Richard Cochran richardcochran@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/gianfar.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 27d0e3b9833cd..e4a2c74a9b47e 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2685,13 +2685,17 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) skb_dirtytx = tx_queue->skb_dirtytx;

while ((skb = tx_queue->tx_skbuff[skb_dirtytx])) { + bool do_tstamp; + + do_tstamp = (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en;

frags = skb_shinfo(skb)->nr_frags;

/* When time stamping, one additional TxBD must be freed. * Also, we need to dma_unmap_single() the TxPAL. */ - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) + if (unlikely(do_tstamp)) nr_txbds = frags + 2; else nr_txbds = frags + 1; @@ -2705,7 +2709,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) (lstatus & BD_LENGTH_MASK)) break;

- if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { + if (unlikely(do_tstamp)) { next = next_txbd(bdp, base, tx_ring_size); buflen = be16_to_cpu(next->length) + GMAC_FCB_LEN + GMAC_TXPAL_LEN; @@ -2715,7 +2719,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) dma_unmap_single(priv->dev, be32_to_cpu(bdp->bufPtr), buflen, DMA_TO_DEVICE);

- if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { + if (unlikely(do_tstamp)) { struct skb_shared_hwtstamps shhwtstamps; u64 *ns = (u64 *)(((uintptr_t)skb->data + 0x10) & ~0x7UL);

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 3c911fe799d1c338d94b78e7182ad452c37af897 ]

In the probe function, some resources are allocated using 'dma_alloc_wc()', they should be released with 'dma_free_wc()', not 'dma_free_coherent()'.

We already use 'dma_free_wc()' in the remove function, but not in the error handling path of the probe function.

Also, remove a useless 'PAGE_ALIGN()'. 'info->fix.smem_len' is already PAGE_ALIGNed.

Fixes: 638772c7553f ("fb: add support of LCD display controller on pxa168/910 (base layer)") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Reviewed-by: Lubomir Rintel lkundrak@v3.sk CC: YueHaibing yuehaibing@huawei.com Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Link: https://patchwork.freedesktop.org/patch/msgid/20190831100024.3248-1-christop... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/pxa168fb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c index d059d04c63acd..20195d3dbf088 100644 --- a/drivers/video/fbdev/pxa168fb.c +++ b/drivers/video/fbdev/pxa168fb.c @@ -769,8 +769,8 @@ failed_free_cmap: failed_free_clk: clk_disable_unprepare(fbi->clk); failed_free_fbmem: - dma_free_coherent(fbi->dev, info->fix.smem_len, - info->screen_base, fbi->fb_start_dma); + dma_free_wc(fbi->dev, info->fix.smem_len, + info->screen_base, fbi->fb_start_dma); failed_free_info: kfree(info);

@@ -804,7 +804,7 @@ static int pxa168fb_remove(struct platform_device *pdev)

irq = platform_get_irq(pdev, 0);

- dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len), + dma_free_wc(fbi->dev, info->fix.smem_len, info->screen_base, info->fix.smem_start);

clk_disable_unprepare(fbi->clk);

From: Oliver O'Halloran oohall@gmail.com

[ Upstream commit 3b5b9997b331e77ce967eba2c4bc80dc3134a7fe ]

On pseries there is a bug with adding hotplugged devices to an IOMMU group. For a number of dumb reasons fixing that bug first requires re-working how VFs are configured on PowerNV. For background, on PowerNV we use the pcibios_sriov_enable() hook to do two things:

1. Create a pci_dn structure for each of the VFs, and 2. Configure the PHB's internal BARs so the MMIO range for each VF maps to a unique PE.

Roughly speaking a PE is the hardware counterpart to a Linux IOMMU group since all the devices in a PE share the same IOMMU table. A PE also defines the set of devices that should be isolated in response to a PCI error (i.e. bad DMA, UR/CA, AER events, etc). When isolated all MMIO and DMA traffic to and from devicein the PE is blocked by the root complex until the PE is recovered by the OS.

The requirement to block MMIO causes a giant headache because the P8 PHB generally uses a fixed mapping between MMIO addresses and PEs. As a result we need to delay configuring the IOMMU groups for device until after MMIO resources are assigned. For physical devices (i.e. non-VFs) the PE assignment is done in pcibios_setup_bridge() which is called immediately after the MMIO resources for downstream devices (and the bridge's windows) are assigned. For VFs the setup is more complicated because:

a) pcibios_setup_bridge() is not called again when VFs are activated, and b) The pci_dev for VFs are created by generic code which runs after pcibios_sriov_enable() is called.

The work around for this is a two step process:

1. A fixup in pcibios_add_device() is used to initialised the cached pe_number in pci_dn, then 2. A bus notifier then adds the device to the IOMMU group for the PE specified in pci_dn->pe_number.

A side effect fixing the pseries bug mentioned in the first paragraph is moving the fixup out of pcibios_add_device() and into pcibios_bus_add_device(), which is called much later. This results in step 2. failing because pci_dn->pe_number won't be initialised when the bus notifier is run.

We can fix this by removing the need for the fixup. The PE for a VF is known before the VF is even scanned so we can initialise pci_dn->pe_number pcibios_sriov_enable() instead. Unfortunately, moving the initialisation causes two problems:

1. We trip the WARN_ON() in the current fixup code, and 2. The EEH core clears pdn->pe_number when recovering a VF and relies on the fixup to correctly re-set it.

The only justification for either of these is a comment in eeh_rmv_device() suggesting that pdn->pe_number *must* be set to IODA_INVALID_PE in order for the VF to be scanned. However, this comment appears to have no basis in reality. Both bugs can be fixed by just deleting the code.

Tested-by: Alexey Kardashevskiy aik@ozlabs.ru Reviewed-by: Alexey Kardashevskiy aik@ozlabs.ru Signed-off-by: Oliver O'Halloran oohall@gmail.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20191028085424.12006-1-oohall@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kernel/eeh_driver.c | 6 ------ arch/powerpc/platforms/powernv/pci-ioda.c | 19 +++++++++++++++---- arch/powerpc/platforms/powernv/pci.c | 4 ---- 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 470284f9e4f66..5a48c93aaa1b3 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -520,12 +520,6 @@ static void *eeh_rmv_device(void *data, void *userdata)

pci_iov_remove_virtfn(edev->physfn, pdn->vf_index, 0); edev->pdev = NULL; - - /* - * We have to set the VF PE number to invalid one, which is - * required to plug the VF successfully. - */ - pdn->pe_number = IODA_INVALID_PE; #endif if (rmv_data) list_add(&edev->rmv_list, &rmv_data->edev_list); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index d3d5796f7df60..36ef504eeab32 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1523,6 +1523,10 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)

/* Reserve PE for each VF */ for (vf_index = 0; vf_index < num_vfs; vf_index++) { + int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index); + int vf_bus = pci_iov_virtfn_bus(pdev, vf_index); + struct pci_dn *vf_pdn; + if (pdn->m64_single_mode) pe_num = pdn->pe_num_map[vf_index]; else @@ -1535,13 +1539,11 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) pe->pbus = NULL; pe->parent_dev = pdev; pe->mve_number = -1; - pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) | - pci_iov_virtfn_devfn(pdev, vf_index); + pe->rid = (vf_bus << 8) | vf_devfn;

pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n", hose->global_number, pdev->bus->number, - PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)), - PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num); + PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num);

if (pnv_ioda_configure_pe(phb, pe)) { /* XXX What do we do here ? */ @@ -1555,6 +1557,15 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) list_add_tail(&pe->list, &phb->ioda.pe_list); mutex_unlock(&phb->ioda.pe_list_mutex);

+ /* associate this pe to it's pdn */ + list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) { + if (vf_pdn->busno == vf_bus && + vf_pdn->devfn == vf_devfn) { + vf_pdn->pe_number = pe_num; + break; + } + } + pnv_pci_ioda2_setup_dma_pe(phb, pe); } } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 961c131a5b7e8..844ca1886063b 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -978,16 +978,12 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev) struct pnv_phb *phb = hose->private_data; #ifdef CONFIG_PCI_IOV struct pnv_ioda_pe *pe; - struct pci_dn *pdn;

/* Fix the VF pdn PE number */ if (pdev->is_virtfn) { - pdn = pci_get_pdn(pdev); - WARN_ON(pdn->pe_number != IODA_INVALID_PE); list_for_each_entry(pe, &phb->ioda.pe_list, list) { if (pe->rid == ((pdev->bus->number << 8) | (pdev->devfn & 0xff))) { - pdn->pe_number = pe->pe_number; pe->pdev = pdev; break; }

From: Sergey Senozhatsky sergey.senozhatsky.work@gmail.com

[ Upstream commit 1b710b1b10eff9d46666064ea25f079f70bc67a8 ]

Sergey didn't like the locking order,

uart_port->lock -> tty_port->lock

uart_write (uart_port->lock) __uart_start pl011_start_tx pl011_tx_chars uart_write_wakeup tty_port_tty_wakeup tty_port_default tty_port_tty_get (tty_port->lock)

but those code is so old, and I have no clue how to de-couple it after checking other locks in the splat. There is an onging effort to make all printk() as deferred, so until that happens, workaround it for now as a short-term fix.

LTP: starting iogen01 (export LTPROOT; rwtest -N iogen01 -i 120s -s read,write -Da -Dv -n 2 500b:$TMPDIR/doio.f1.$$ 1000b:$TMPDIR/doio.f2.$$) WARNING: possible circular locking dependency detected ------------------------------------------------------ doio/49441 is trying to acquire lock: ffff008b7cff7290 (&(&zone->lock)->rlock){..-.}, at: rmqueue+0x138/0x2050

but task is already holding lock: 60ff000822352818 (&pool->lock/1){-.-.}, at: start_flush_work+0xd8/0x3f0

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #4 (&pool->lock/1){-.-.}: lock_acquire+0x320/0x360 _raw_spin_lock+0x64/0x80 __queue_work+0x4b4/0xa10 queue_work_on+0xac/0x11c tty_schedule_flip+0x84/0xbc tty_flip_buffer_push+0x1c/0x28 pty_write+0x98/0xd0 n_tty_write+0x450/0x60c tty_write+0x338/0x474 __vfs_write+0x88/0x214 vfs_write+0x12c/0x1a4 redirected_tty_write+0x90/0xdc do_loop_readv_writev+0x140/0x180 do_iter_write+0xe0/0x10c vfs_writev+0x134/0x1cc do_writev+0xbc/0x130 __arm64_sys_writev+0x58/0x8c el0_svc_handler+0x170/0x240 el0_sync_handler+0x150/0x250 el0_sync+0x164/0x180

-> #3 (&(&port->lock)->rlock){-.-.}: lock_acquire+0x320/0x360 _raw_spin_lock_irqsave+0x7c/0x9c tty_port_tty_get+0x24/0x60 tty_port_default_wakeup+0x1c/0x3c tty_port_tty_wakeup+0x34/0x40 uart_write_wakeup+0x28/0x44 pl011_tx_chars+0x1b8/0x270 pl011_start_tx+0x24/0x70 __uart_start+0x5c/0x68 uart_write+0x164/0x1c8 do_output_char+0x33c/0x348 n_tty_write+0x4bc/0x60c tty_write+0x338/0x474 redirected_tty_write+0xc0/0xdc do_loop_readv_writev+0x140/0x180 do_iter_write+0xe0/0x10c vfs_writev+0x134/0x1cc do_writev+0xbc/0x130 __arm64_sys_writev+0x58/0x8c el0_svc_handler+0x170/0x240 el0_sync_handler+0x150/0x250 el0_sync+0x164/0x180

-> #2 (&port_lock_key){-.-.}: lock_acquire+0x320/0x360 _raw_spin_lock+0x64/0x80 pl011_console_write+0xec/0x2cc console_unlock+0x794/0x96c vprintk_emit+0x260/0x31c vprintk_default+0x54/0x7c vprintk_func+0x218/0x254 printk+0x7c/0xa4 register_console+0x734/0x7b0 uart_add_one_port+0x734/0x834 pl011_register_port+0x6c/0xac sbsa_uart_probe+0x234/0x2ec platform_drv_probe+0xd4/0x124 really_probe+0x250/0x71c driver_probe_device+0xb4/0x200 __device_attach_driver+0xd8/0x188 bus_for_each_drv+0xbc/0x110 __device_attach+0x120/0x220 device_initial_probe+0x20/0x2c bus_probe_device+0x54/0x100 device_add+0xae8/0xc2c platform_device_add+0x278/0x3b8 platform_device_register_full+0x238/0x2ac acpi_create_platform_device+0x2dc/0x3a8 acpi_bus_attach+0x390/0x3cc acpi_bus_attach+0x108/0x3cc acpi_bus_attach+0x108/0x3cc acpi_bus_attach+0x108/0x3cc acpi_bus_scan+0x7c/0xb0 acpi_scan_init+0xe4/0x304 acpi_init+0x100/0x114 do_one_initcall+0x348/0x6a0 do_initcall_level+0x190/0x1fc do_basic_setup+0x34/0x4c kernel_init_freeable+0x19c/0x260 kernel_init+0x18/0x338 ret_from_fork+0x10/0x18

-> #1 (console_owner){-...}: lock_acquire+0x320/0x360 console_lock_spinning_enable+0x6c/0x7c console_unlock+0x4f8/0x96c vprintk_emit+0x260/0x31c vprintk_default+0x54/0x7c vprintk_func+0x218/0x254 printk+0x7c/0xa4 get_random_u64+0x1c4/0x1dc shuffle_pick_tail+0x40/0xac __free_one_page+0x424/0x710 free_one_page+0x70/0x120 __free_pages_ok+0x61c/0xa94 __free_pages_core+0x1bc/0x294 memblock_free_pages+0x38/0x48 __free_pages_memory+0xcc/0xfc __free_memory_core+0x70/0x78 free_low_memory_core_early+0x148/0x18c memblock_free_all+0x18/0x54 mem_init+0xb4/0x17c mm_init+0x14/0x38 start_kernel+0x19c/0x530

-> #0 (&(&zone->lock)->rlock){..-.}: validate_chain+0xf6c/0x2e2c __lock_acquire+0x868/0xc2c lock_acquire+0x320/0x360 _raw_spin_lock+0x64/0x80 rmqueue+0x138/0x2050 get_page_from_freelist+0x474/0x688 __alloc_pages_nodemask+0x3b4/0x18dc alloc_pages_current+0xd0/0xe0 alloc_slab_page+0x2b4/0x5e0 new_slab+0xc8/0x6bc ___slab_alloc+0x3b8/0x640 kmem_cache_alloc+0x4b4/0x588 __debug_object_init+0x778/0x8b4 debug_object_init_on_stack+0x40/0x50 start_flush_work+0x16c/0x3f0 __flush_work+0xb8/0x124 flush_work+0x20/0x30 xlog_cil_force_lsn+0x88/0x204 [xfs] xfs_log_force_lsn+0x128/0x1b8 [xfs] xfs_file_fsync+0x3c4/0x488 [xfs] vfs_fsync_range+0xb0/0xd0 generic_write_sync+0x80/0xa0 [xfs] xfs_file_buffered_aio_write+0x66c/0x6e4 [xfs] xfs_file_write_iter+0x1a0/0x218 [xfs] __vfs_write+0x1cc/0x214 vfs_write+0x12c/0x1a4 ksys_write+0xb0/0x120 __arm64_sys_write+0x54/0x88 el0_svc_handler+0x170/0x240 el0_sync_handler+0x150/0x250 el0_sync+0x164/0x180

other info that might help us debug this:

Chain exists of: &(&zone->lock)->rlock --> &(&port->lock)->rlock --> &pool->lock/1

Possible unsafe locking scenario:

CPU0 CPU1 ---- ---- lock(&pool->lock/1); lock(&(&port->lock)->rlock); lock(&pool->lock/1); lock(&(&zone->lock)->rlock);

*** DEADLOCK ***

4 locks held by doio/49441: #0: a0ff00886fc27408 (sb_writers#8){.+.+}, at: vfs_write+0x118/0x1a4 #1: 8fff00080810dfe0 (&xfs_nondir_ilock_class){++++}, at: xfs_ilock+0x2a8/0x300 [xfs] #2: ffff9000129f2390 (rcu_read_lock){....}, at: rcu_lock_acquire+0x8/0x38 #3: 60ff000822352818 (&pool->lock/1){-.-.}, at: start_flush_work+0xd8/0x3f0

stack backtrace: CPU: 48 PID: 49441 Comm: doio Tainted: G W Hardware name: HPE Apollo 70 /C01_APACHE_MB , BIOS L50_5.13_1.11 06/18/2019 Call trace: dump_backtrace+0x0/0x248 show_stack+0x20/0x2c dump_stack+0xe8/0x150 print_circular_bug+0x368/0x380 check_noncircular+0x28c/0x294 validate_chain+0xf6c/0x2e2c __lock_acquire+0x868/0xc2c lock_acquire+0x320/0x360 _raw_spin_lock+0x64/0x80 rmqueue+0x138/0x2050 get_page_from_freelist+0x474/0x688 __alloc_pages_nodemask+0x3b4/0x18dc alloc_pages_current+0xd0/0xe0 alloc_slab_page+0x2b4/0x5e0 new_slab+0xc8/0x6bc ___slab_alloc+0x3b8/0x640 kmem_cache_alloc+0x4b4/0x588 __debug_object_init+0x778/0x8b4 debug_object_init_on_stack+0x40/0x50 start_flush_work+0x16c/0x3f0 __flush_work+0xb8/0x124 flush_work+0x20/0x30 xlog_cil_force_lsn+0x88/0x204 [xfs] xfs_log_force_lsn+0x128/0x1b8 [xfs] xfs_file_fsync+0x3c4/0x488 [xfs] vfs_fsync_range+0xb0/0xd0 generic_write_sync+0x80/0xa0 [xfs] xfs_file_buffered_aio_write+0x66c/0x6e4 [xfs] xfs_file_write_iter+0x1a0/0x218 [xfs] __vfs_write+0x1cc/0x214 vfs_write+0x12c/0x1a4 ksys_write+0xb0/0x120 __arm64_sys_write+0x54/0x88 el0_svc_handler+0x170/0x240 el0_sync_handler+0x150/0x250 el0_sync+0x164/0x180

Reviewed-by: Sergey Senozhatsky sergey.senozhatsky.work@gmail.com Signed-off-by: Qian Cai cai@lca.pw Link: https://lore.kernel.org/r/1573679785-21068-1-git-send-email-cai@lca.pw Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/char/random.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c index e6efa07e9f9ea..50d5846acf48a 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1598,8 +1598,9 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, print_once = true; #endif if (__ratelimit(&unseeded_warning)) - pr_notice("random: %s called from %pS with crng_init=%d\n", - func_name, caller, crng_init); + printk_deferred(KERN_NOTICE "random: %s called from %pS " + "with crng_init=%d\n", func_name, caller, + crng_init); }

/*

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit a23680594da7a9e2696dbcf4f023e9273e2fa40b ]

Suspending Goodix touchscreens requires changing the interrupt pin to output before sending them a power-down command. Followed by wiggling the interrupt pin to wake the device up, after which it is put back in input mode.

On Bay Trail devices with a Goodix touchscreen direct-irq mode is used in combination with listing the pin as a normal GpioIo resource.

This works fine, until the goodix driver gets rmmod-ed and then insmod-ed again. In this case byt_gpio_disable_free() calls byt_gpio_clear_triggering() which clears the IRQ flags and after that the (direct) IRQ no longer triggers.

This commit fixes this by adding a check for the BYT_DIRECT_IRQ_EN flag to byt_gpio_clear_triggering().

Note that byt_gpio_clear_triggering() only gets called from byt_gpio_disable_free() for direct-irq enabled pins, as these are excluded from the irq_valid mask by byt_init_irq_valid_mask().

Signed-off-by: Hans de Goede hdegoede@redhat.com Acked-by: Mika Westerberg mika.westerberg@linux.intel.com Reviewed-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pinctrl/intel/pinctrl-baytrail.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 9df5d29d708da..4fb3e44f91331 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -958,7 +958,13 @@ static void byt_gpio_clear_triggering(struct byt_gpio *vg, unsigned int offset)

raw_spin_lock_irqsave(&byt_lock, flags); value = readl(reg); - value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL); + + /* Do not clear direct-irq enabled IRQs (from gpio_disable_free) */ + if (value & BYT_DIRECT_IRQ_EN) + /* nothing to do */ ; + else + value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL); + writel(value, reg); raw_spin_unlock_irqrestore(&byt_lock, flags); }

From: Tiezhu Yang yangtiezhu@loongson.cn

[ Upstream commit 72d052e28d1d2363f9107be63ef3a3afdea6143c ]

If kzalloc fails, it should return -ENOMEM, otherwise may trigger a NULL pointer dereference.

Fixes: 3adeb2566b9b ("MIPS: Loongson: Improve LEFI firmware interface") Signed-off-by: Tiezhu Yang yangtiezhu@loongson.cn Signed-off-by: Paul Burton paulburton@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Huacai Chen chenhc@lemote.com Cc: Jiaxun Yang jiaxun.yang@flygoat.com Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/loongson64/loongson-3/platform.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/arch/mips/loongson64/loongson-3/platform.c b/arch/mips/loongson64/loongson-3/platform.c index 25a97cc0ee336..0db4cc3196ebd 100644 --- a/arch/mips/loongson64/loongson-3/platform.c +++ b/arch/mips/loongson64/loongson-3/platform.c @@ -31,6 +31,9 @@ static int __init loongson3_platform_init(void) continue;

pdev = kzalloc(sizeof(struct platform_device), GFP_KERNEL); + if (!pdev) + return -ENOMEM; + pdev->name = loongson_sysconf.sensors[i].name; pdev->id = loongson_sysconf.sensors[i].id; pdev->dev.platform_data = &loongson_sysconf.sensors[i];

From: Jia-Ju Bai baijiaju1990@gmail.com

[ Upstream commit b74351287d4bd90636c3f48bc188c2f53824c2d4 ]

The driver may sleep while holding a spinlock. The function call path (from bottom to top) in Linux 4.19 is:

kernel/irq/manage.c, 523: synchronize_irq in disable_irq drivers/uio/uio_dmem_genirq.c, 140: disable_irq in uio_dmem_genirq_irqcontrol drivers/uio/uio_dmem_genirq.c, 134: _raw_spin_lock_irqsave in uio_dmem_genirq_irqcontrol

synchronize_irq() can sleep at runtime.

To fix this bug, disable_irq() is called without holding the spinlock.

This bug is found by a static analysis tool STCheck written by myself.

Signed-off-by: Jia-Ju Bai baijiaju1990@gmail.com Link: https://lore.kernel.org/r/20191218094405.6009-1-baijiaju1990@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/uio/uio_dmem_genirq.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c index e1134a4d97f3f..a00b4aee6c799 100644 --- a/drivers/uio/uio_dmem_genirq.c +++ b/drivers/uio/uio_dmem_genirq.c @@ -135,11 +135,13 @@ static int uio_dmem_genirq_irqcontrol(struct uio_info *dev_info, s32 irq_on) if (irq_on) { if (test_and_clear_bit(0, &priv->flags)) enable_irq(dev_info->irq); + spin_unlock_irqrestore(&priv->lock, flags); } else { - if (!test_and_set_bit(0, &priv->flags)) + if (!test_and_set_bit(0, &priv->flags)) { + spin_unlock_irqrestore(&priv->lock, flags); disable_irq(dev_info->irq); + } } - spin_unlock_irqrestore(&priv->lock, flags);

return 0; }

From: John Keeping john@metanate.com

[ Upstream commit 644139f8b64d818f6345351455f14471510879a5 ]

On chips with fewer FIFOs than endpoints (for example RK3288 which has 9 endpoints, but only 6 which are cabable of input), the DPTXFSIZN registers above the FIFO count may return invalid values.

With logging added on startup, I see:

dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=1 sz=256 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=2 sz=128 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=3 sz=128 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=4 sz=64 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=5 sz=64 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=6 sz=32 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=7 sz=0 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=8 sz=0 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=9 sz=0 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=10 sz=0 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=11 sz=0 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=12 sz=0 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=13 sz=0 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=14 sz=0 dwc2 ff580000.usb: dwc2_hsotg_init_fifo: ep=15 sz=0

but:

# cat /sys/kernel/debug/ff580000.usb/fifo Non-periodic FIFOs: RXFIFO: Size 275 NPTXFIFO: Size 16, Start 0x00000113

Periodic TXFIFOs: DPTXFIFO 1: Size 256, Start 0x00000123 DPTXFIFO 2: Size 128, Start 0x00000223 DPTXFIFO 3: Size 128, Start 0x000002a3 DPTXFIFO 4: Size 64, Start 0x00000323 DPTXFIFO 5: Size 64, Start 0x00000363 DPTXFIFO 6: Size 32, Start 0x000003a3 DPTXFIFO 7: Size 0, Start 0x000003e3 DPTXFIFO 8: Size 0, Start 0x000003a3 DPTXFIFO 9: Size 256, Start 0x00000123

so it seems that FIFO 9 is mirroring FIFO 1.

Fix the allocation by using the FIFO count instead of the endpoint count when selecting a FIFO for an endpoint.

Acked-by: Minas Harutyunyan hminas@synopsys.com Signed-off-by: John Keeping john@metanate.com Signed-off-by: Felipe Balbi balbi@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/dwc2/gadget.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 4af9a1c652edb..aeb6f7c84ea0a 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -3933,11 +3933,12 @@ static int dwc2_hsotg_ep_enable(struct usb_ep *ep, * a unique tx-fifo even if it is non-periodic. */ if (dir_in && hsotg->dedicated_fifos) { + unsigned fifo_count = dwc2_hsotg_tx_fifo_count(hsotg); u32 fifo_index = 0; u32 fifo_size = UINT_MAX;

size = hs_ep->ep.maxpacket * hs_ep->mc; - for (i = 1; i < hsotg->num_of_eps; ++i) { + for (i = 1; i <= fifo_count; ++i) { if (hsotg->fifo_map & (1 << i)) continue; val = dwc2_readl(hsotg->regs + DPTXFSIZN(i));

From: Siddhesh Poyarekar siddhesh@gotplt.org

[ Upstream commit 6b64a650f0b2ae3940698f401732988699eecf7a ]

It was observed[1] on arm64 that __builtin_strlen led to an infinite loop in the get_size selftest. This is because __builtin_strlen (and other builtins) may sometimes result in a call to the C library function. The C library implementation of strlen uses an IFUNC resolver to load the most efficient strlen implementation for the underlying machine and hence has a PLT indirection even for static binaries. Because this binary avoids the C library startup routines, the PLT initialization never happens and hence the program gets stuck in an infinite loop.

On x86_64 the __builtin_strlen just happens to expand inline and avoid the call but that is not always guaranteed.

Further, while testing on x86_64 (Fedora 31), it was observed that the test also failed with a segfault inside write() because the generated code for the write function in glibc seems to access TLS before the syscall (probably due to the cancellation point check) and fails because TLS is not initialised.

To mitigate these problems, this patch reduces the interface with the C library to just the syscall function. The syscall function still sets errno on failure, which is undesirable but for now it only affects cases where syscalls fail.

[1] https://bugs.linaro.org/show_bug.cgi?id=5479

Signed-off-by: Siddhesh Poyarekar siddhesh@gotplt.org Reported-by: Masami Hiramatsu masami.hiramatsu@linaro.org Tested-by: Masami Hiramatsu masami.hiramatsu@linaro.org Reviewed-by: Tim Bird tim.bird@sony.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/size/get_size.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/size/get_size.c b/tools/testing/selftests/size/get_size.c index d4b59ab979a09..f55943b6d1e2a 100644 --- a/tools/testing/selftests/size/get_size.c +++ b/tools/testing/selftests/size/get_size.c @@ -12,23 +12,35 @@ * own execution. It also attempts to have as few dependencies * on kernel features as possible. * - * It should be statically linked, with startup libs avoided. - * It uses no library calls, and only the following 3 syscalls: + * It should be statically linked, with startup libs avoided. It uses + * no library calls except the syscall() function for the following 3 + * syscalls: * sysinfo(), write(), and _exit() * * For output, it avoids printf (which in some C libraries * has large external dependencies) by implementing it's own * number output and print routines, and using __builtin_strlen() + * + * The test may crash if any of the above syscalls fails because in some + * libc implementations (e.g. the GNU C Library) errno is saved in + * thread-local storage, which does not get initialized due to avoiding + * startup libs. */

#include <sys/sysinfo.h> #include <unistd.h> +#include <sys/syscall.h>

#define STDOUT_FILENO 1

static int print(const char *s) { - return write(STDOUT_FILENO, s, __builtin_strlen(s)); + size_t len = 0; + + while (s[len] != '\0') + len++; + + return syscall(SYS_write, STDOUT_FILENO, s, len); }

static inline char *num_to_str(unsigned long num, char *buf, int len) @@ -80,12 +92,12 @@ void _start(void) print("TAP version 13\n"); print("# Testing system size.\n");

- ccode = sysinfo(&info); + ccode = syscall(SYS_sysinfo, &info); if (ccode < 0) { print("not ok 1"); print(test_name); print(" ---\n reason: "could not get sysinfo"\n ...\n"); - _exit(ccode); + syscall(SYS_exit, ccode); } print("ok 1"); print(test_name); @@ -101,5 +113,5 @@ void _start(void) print(" ...\n"); print("1..1\n");

- _exit(0); + syscall(SYS_exit, 0); }

From: Arvind Sankar nivedita@alum.mit.edu

[ Upstream commit dacc9092336be20b01642afe1a51720b31f60369 ]

When checking whether the reported lfb_size makes sense, the height * stride result is page-aligned before seeing whether it exceeds the reported size.

This doesn't work if height * stride is not an exact number of pages. For example, as reported in the kernel bugzilla below, an 800x600x32 EFI framebuffer gets skipped because of this.

Move the PAGE_ALIGN to after the check vs size.

Reported-by: Christopher Head chead@chead.ca Tested-by: Christopher Head chead@chead.ca Signed-off-by: Arvind Sankar nivedita@alum.mit.edu Signed-off-by: Borislav Petkov bp@suse.de Link: https://bugzilla.kernel.org/show_bug.cgi?id=206051 Link: https://lkml.kernel.org/r/20200107230410.2291947-1-nivedita@alum.mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/sysfb_simplefb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 85195d447a922..f3215346e47fd 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -94,11 +94,11 @@ __init int create_simplefb(const struct screen_info *si, if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) size <<= 16; length = mode->height * mode->stride; - length = PAGE_ALIGN(length); if (length > size) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } + length = PAGE_ALIGN(length);

/* setup IORESOURCE_MEM as framebuffer memory */ memset(&res, 0, sizeof(res));

From: Steven Rostedt (VMware) rostedt@goodmis.org

[ Upstream commit dfb6cd1e654315168e36d947471bd2a0ccd834ae ]

Looking through old emails in my INBOX, I came across a patch from Luis Henriques that attempted to fix a race of two stat tracers registering the same stat trace (extremely unlikely, as this is done in the kernel, and probably doesn't even exist). The submitted patch wasn't quite right as it needed to deal with clean up a bit better (if two stat tracers were the same, it would have the same files).

But to make the code cleaner, all we needed to do is to keep the all_stat_sessions_mutex held for most of the registering function.

Link: http://lkml.kernel.org/r/1410299375-20068-1-git-send-email-luis.henriques@ca...

Fixes: 002bb86d8d42f ("tracing/ftrace: separate events tracing and stats tracing engine") Reported-by: Luis Henriques luis.henriques@canonical.com Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/trace/trace_stat.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index bf68af63538b4..92b76f9e25edd 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -306,7 +306,7 @@ static int init_stat_file(struct stat_session *session) int register_stat_tracer(struct tracer_stat *trace) { struct stat_session *session, *node; - int ret; + int ret = -EINVAL;

if (!trace) return -EINVAL; @@ -317,17 +317,15 @@ int register_stat_tracer(struct tracer_stat *trace) /* Already registered? */ mutex_lock(&all_stat_sessions_mutex); list_for_each_entry(node, &all_stat_sessions, session_list) { - if (node->ts == trace) { - mutex_unlock(&all_stat_sessions_mutex); - return -EINVAL; - } + if (node->ts == trace) + goto out; } - mutex_unlock(&all_stat_sessions_mutex);

+ ret = -ENOMEM; /* Init the session */ session = kzalloc(sizeof(*session), GFP_KERNEL); if (!session) - return -ENOMEM; + goto out;

session->ts = trace; INIT_LIST_HEAD(&session->session_list); @@ -336,15 +334,16 @@ int register_stat_tracer(struct tracer_stat *trace) ret = init_stat_file(session); if (ret) { destroy_session(session); - return ret; + goto out; }

+ ret = 0; /* Register */ - mutex_lock(&all_stat_sessions_mutex); list_add_tail(&session->session_list, &all_stat_sessions); + out: mutex_unlock(&all_stat_sessions_mutex);

- return 0; + return ret; }

void unregister_stat_tracer(struct tracer_stat *trace)

From: Sun Ke sunke32@huawei.com

[ Upstream commit 5c0dd228b5fc30a3b732c7ae2657e0161ec7ed80 ]

When kzalloc fail, may cause trying to destroy the workqueue from inside the workqueue.

If num_connections is m (2 < m), and NO.1 ~ NO.n (1 < n < m) kzalloc are successful. The NO.(n + 1) failed. Then, nbd_start_device will return ENOMEM to nbd_start_device_ioctl, and nbd_start_device_ioctl will return immediately without running flush_workqueue. However, we still have n recv threads. If nbd_release run first, recv threads may have to drop the last config_refs and try to destroy the workqueue from inside the workqueue.

To fix it, add a flush_workqueue in nbd_start_device.

Fixes: e9e006f5fcf2 ("nbd: fix max number of supported devs") Signed-off-by: Sun Ke sunke32@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/block/nbd.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 4c661ad91e7d3..8f56e6b2f114f 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1203,6 +1203,16 @@ static int nbd_start_device(struct nbd_device *nbd) args = kzalloc(sizeof(*args), GFP_KERNEL); if (!args) { sock_shutdown(nbd); + /* + * If num_connections is m (2 < m), + * and NO.1 ~ NO.n(1 < n < m) kzallocs are successful. + * But NO.(n + 1) failed. We still have n recv threads. + * So, add flush_workqueue here to prevent recv threads + * dropping the last config_refs and trying to destroy + * the workqueue from inside the workqueue. + */ + if (i) + flush_workqueue(nbd->recv_workq); return -ENOMEM; } sk_set_memalloc(config->socks[i]->sock->sk);

From: Masahiro Yamada masahiroy@kernel.org

[ Upstream commit c8fb7d7e48d11520ad24808cfce7afb7b9c9f798 ]

Running randconfig on arm64 using KCONFIG_SEED=0x40C5E904 (e.g. on v5.5) produces the .config with CONFIG_EFI=y and CONFIG_CPU_BIG_ENDIAN=y, which does not meet the !CONFIG_CPU_BIG_ENDIAN dependency.

This is because the user choice for CONFIG_CPU_LITTLE_ENDIAN vs CONFIG_CPU_BIG_ENDIAN is set by randomize_choice_values() after the value of CONFIG_EFI is calculated.

When this happens, the has_changed flag should be set.

Currently, it takes the result from the last iteration. It should accumulate all the results of the loop.

Fixes: 3b9a19e08960 ("kconfig: loop as long as we changed some symbols in randconfig") Reported-by: Vincenzo Frascino vincenzo.frascino@arm.com Signed-off-by: Masahiro Yamada masahiroy@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/kconfig/confdata.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 27aac273205ba..fa423fcd1a928 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -1238,7 +1238,7 @@ bool conf_set_all_new_symbols(enum conf_def_mode mode)

sym_calc_value(csym); if (mode == def_random) - has_changed = randomize_choice_values(csym); + has_changed |= randomize_choice_values(csym); else { set_all_choice_values(csym); has_changed = true;

From: yu kuai yukuai3@huawei.com

[ Upstream commit bae028e3e521e8cb8caf2cc16a455ce4c55f2332 ]

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c: In function 'amdgpu_atombios_get_connector_info_from_object_table': drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c:376:26: warning: variable 'grph_obj_num' set but not used [-Wunused-but-set-variable] drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c:376:13: warning: variable 'grph_obj_id' set but not used [-Wunused-but-set-variable] drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c:341:37: warning: variable 'con_obj_type' set but not used [-Wunused-but-set-variable] drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c:341:24: warning: variable 'con_obj_num' set but not used [-Wunused-but-set-variable]

They are never used, so can be removed.

Fixes: d38ceaf99ed0 ("drm/amdgpu: add core driver (v4)") Signed-off-by: yu kuai yukuai3@huawei.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index cc4e18dcd8b6f..4779740421a88 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -336,17 +336,9 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * path_size += le16_to_cpu(path->usSize);

if (device_support & le16_to_cpu(path->usDeviceTag)) { - uint8_t con_obj_id, con_obj_num, con_obj_type; - - con_obj_id = + uint8_t con_obj_id = (le16_to_cpu(path->usConnObjectId) & OBJECT_ID_MASK) >> OBJECT_ID_SHIFT; - con_obj_num = - (le16_to_cpu(path->usConnObjectId) & ENUM_ID_MASK) - >> ENUM_ID_SHIFT; - con_obj_type = - (le16_to_cpu(path->usConnObjectId) & - OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;

/* Skip TV/CV support */ if ((le16_to_cpu(path->usDeviceTag) == @@ -371,14 +363,7 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * router.ddc_valid = false; router.cd_valid = false; for (j = 0; j < ((le16_to_cpu(path->usSize) - 8) / 2); j++) { - uint8_t grph_obj_id, grph_obj_num, grph_obj_type; - - grph_obj_id = - (le16_to_cpu(path->usGraphicObjIds[j]) & - OBJECT_ID_MASK) >> OBJECT_ID_SHIFT; - grph_obj_num = - (le16_to_cpu(path->usGraphicObjIds[j]) & - ENUM_ID_MASK) >> ENUM_ID_SHIFT; + uint8_t grph_obj_type= grph_obj_type = (le16_to_cpu(path->usGraphicObjIds[j]) & OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;

From: Rasmus Villemoes linux@rasmusvillemoes.dk

[ Upstream commit 148587a59f6b85831695e0497d9dd1af5f0495af ]

Qiang Zhao points out that these offsets get written to 16-bit registers, and there are some QE platforms with more than 64K muram. So it is possible that qe_muram_alloc() gives us an allocation that can't actually be used by the hardware, so detect and reject that.

Reported-by: Qiang Zhao qiang.zhao@nxp.com Reviewed-by: Timur Tabi timur@kernel.org Signed-off-by: Rasmus Villemoes linux@rasmusvillemoes.dk Acked-by: David S. Miller davem@davemloft.net Signed-off-by: Li Yang leoyang.li@nxp.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wan/fsl_ucc_hdlc.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 571a1ff8f81f2..6a26cef621935 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -240,6 +240,11 @@ static int uhdlc_init(struct ucc_hdlc_private *priv) ret = -ENOMEM; goto free_riptr; } + if (riptr != (u16)riptr || tiptr != (u16)tiptr) { + dev_err(priv->dev, "MURAM allocation out of addressable range\n"); + ret = -ENOMEM; + goto free_tiptr; + }

/* Set RIPTR, TIPTR */ iowrite16be(riptr, &priv->ucc_pram->riptr);

From: Mao Wenan maowenan@huawei.com

[ Upstream commit 718eae277e62a26e5862eb72a830b5e0fe37b04a ]

Convert cpu_to_le16(le16_to_cpu(frame->datalen) + len) to use le16_add_cpu(), which is more concise and does the same thing.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Mao Wenan maowenan@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/port100.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 60ae382f50da9..06bb226c62ef4 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -574,7 +574,7 @@ static void port100_tx_update_payload_len(void *_frame, int len) { struct port100_frame *frame = _frame;

- frame->datalen = cpu_to_le16(le16_to_cpu(frame->datalen) + len); + le16_add_cpu(&frame->datalen, len); }

static bool port100_rx_frame_is_valid(void *_frame)

From: Andrey Smirnov andrew.smirnov@gmail.com

[ Upstream commit cd58a174e58649426fb43d7456e5f7d7eab58af1 ]

RDU2 production units come with resistor connecting WP pin to correpsonding GPIO DNPed for both SD card slots. Drop any WP related configuration and mark both slots with "disable-wp".

Reported-by: Chris Healy cphealy@gmail.com Reviewed-by: Chris Healy cphealy@gmail.com Reviewed-by: Lucas Stach l.stach@pengutronix.de Signed-off-by: Andrey Smirnov andrew.smirnov@gmail.com Cc: Shawn Guo shawnguo@kernel.org Cc: Fabio Estevam festevam@gmail.com Cc: Lucas Stach l.stach@pengutronix.de Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi index 849eb3443cde2..719e63092c2ea 100644 --- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi @@ -587,7 +587,7 @@ pinctrl-0 = <&pinctrl_usdhc2>; bus-width = <4>; cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>; - wp-gpios = <&gpio2 3 GPIO_ACTIVE_HIGH>; + disable-wp; vmmc-supply = <&reg_3p3v_sd>; vqmmc-supply = <&reg_3p3v>; status = "okay"; @@ -598,7 +598,7 @@ pinctrl-0 = <&pinctrl_usdhc3>; bus-width = <4>; cd-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>; - wp-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>; + disable-wp; vmmc-supply = <&reg_3p3v_sd>; vqmmc-supply = <&reg_3p3v>; status = "okay"; @@ -1001,7 +1001,6 @@ MX6QDL_PAD_SD2_DAT1__SD2_DATA1 0x17059 MX6QDL_PAD_SD2_DAT2__SD2_DATA2 0x17059 MX6QDL_PAD_SD2_DAT3__SD2_DATA3 0x17059 - MX6QDL_PAD_NANDF_D3__GPIO2_IO03 0x40010040 MX6QDL_PAD_NANDF_D2__GPIO2_IO02 0x40010040 >; }; @@ -1014,7 +1013,6 @@ MX6QDL_PAD_SD3_DAT1__SD3_DATA1 0x17059 MX6QDL_PAD_SD3_DAT2__SD3_DATA2 0x17059 MX6QDL_PAD_SD3_DAT3__SD3_DATA3 0x17059 - MX6QDL_PAD_NANDF_D1__GPIO2_IO01 0x40010040 MX6QDL_PAD_NANDF_D0__GPIO2_IO00 0x40010040

>;

From: Jan Kara jack@suse.cz

[ Upstream commit 4d5c1adaf893b8aa52525d2b81995e949bcb3239 ]

When we fail to allocate string for journal device name we jump to 'error' label which tries to unlock reiserfs write lock which is not held. Jump to 'error_unlocked' instead.

Fixes: f32485be8397 ("reiserfs: delay reiserfs lock until journal initialization") Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- fs/reiserfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 5208d85dd30c5..9caf3948417c0 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1954,7 +1954,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (!sbi->s_jdev) { SWARN(silent, s, "", "Cannot allocate memory for " "journal device name"); - goto error; + goto error_unlocked; } } #ifdef CONFIG_QUOTA

From: Nathan Chancellor natechancellor@gmail.com

[ Upstream commit df4654bd6e42125d9b85ce3a26eaca2935290b98 ]

Clang warns:

../sound/usb/usx2y/usX2Yhwdep.c:122:3: warning: misleading indentation; statement is not part of the previous 'if' [-Wmisleading-indentation] info->version = USX2Y_DRIVER_VERSION; ^ ../sound/usb/usx2y/usX2Yhwdep.c:120:2: note: previous statement is here if (us428->chip_status & USX2Y_STAT_CHIP_INIT) ^ 1 warning generated.

This warning occurs because there is a space before the tab on this line. Remove it so that the indentation is consistent with the Linux kernel coding style and clang no longer warns.

This was introduced before the beginning of git history so no fixes tag.

Link: https://github.com/ClangBuiltLinux/linux/issues/831 Signed-off-by: Nathan Chancellor natechancellor@gmail.com Link: https://lore.kernel.org/r/20191218034257.54535-1-natechancellor@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/usb/usx2y/usX2Yhwdep.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c index f4b3cda412fcc..e75271e731b2d 100644 --- a/sound/usb/usx2y/usX2Yhwdep.c +++ b/sound/usb/usx2y/usX2Yhwdep.c @@ -131,7 +131,7 @@ static int snd_usX2Y_hwdep_dsp_status(struct snd_hwdep *hw, info->num_dsps = 2; // 0: Prepad Data, 1: FPGA Code if (us428->chip_status & USX2Y_STAT_CHIP_INIT) info->chip_ready = 1; - info->version = USX2Y_DRIVER_VERSION; + info->version = USX2Y_DRIVER_VERSION; return 0; }

From: Phong Tran tranmanphong@gmail.com

[ Upstream commit ebd77feb27e91bb5fe35a7818b7c13ea7435fb98 ]

correct usage prototype of callback in tasklet_init(). Report by https://github.com/KSPP/linux/issues/20

Signed-off-by: Phong Tran tranmanphong@gmail.com Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/ipw2x00/ipw2100.c | 7 ++++--- drivers/net/wireless/intel/ipw2x00/ipw2200.c | 5 +++-- 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c index 19c442cb93e4a..8fbdd7d4fd0c2 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c @@ -3220,8 +3220,9 @@ static void ipw2100_tx_send_data(struct ipw2100_priv *priv) } }

-static void ipw2100_irq_tasklet(struct ipw2100_priv *priv) +static void ipw2100_irq_tasklet(unsigned long data) { + struct ipw2100_priv *priv = (struct ipw2100_priv *)data; struct net_device *dev = priv->net_dev; unsigned long flags; u32 inta, tmp; @@ -6027,7 +6028,7 @@ static void ipw2100_rf_kill(struct work_struct *work) spin_unlock_irqrestore(&priv->low_lock, flags); }

-static void ipw2100_irq_tasklet(struct ipw2100_priv *priv); +static void ipw2100_irq_tasklet(unsigned long data);

static const struct net_device_ops ipw2100_netdev_ops = { .ndo_open = ipw2100_open, @@ -6157,7 +6158,7 @@ static struct net_device *ipw2100_alloc_device(struct pci_dev *pci_dev, INIT_DELAYED_WORK(&priv->rf_kill, ipw2100_rf_kill); INIT_DELAYED_WORK(&priv->scan_event, ipw2100_scan_event);

- tasklet_init(&priv->irq_tasklet, (void (*)(unsigned long)) + tasklet_init(&priv->irq_tasklet, ipw2100_irq_tasklet, (unsigned long)priv);

/* NOTE: We do not start the deferred work for status checks yet */ diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c index 8da87496cb587..2d0734ab3f747 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c @@ -1966,8 +1966,9 @@ static void notify_wx_assoc_event(struct ipw_priv *priv) wireless_send_event(priv->net_dev, SIOCGIWAP, &wrqu, NULL); }

-static void ipw_irq_tasklet(struct ipw_priv *priv) +static void ipw_irq_tasklet(unsigned long data) { + struct ipw_priv *priv = (struct ipw_priv *)data; u32 inta, inta_mask, handled = 0; unsigned long flags; int rc = 0; @@ -10702,7 +10703,7 @@ static int ipw_setup_deferred_work(struct ipw_priv *priv) INIT_WORK(&priv->qos_activate, ipw_bg_qos_activate); #endif /* CONFIG_IPW2200_QOS */

- tasklet_init(&priv->irq_tasklet, (void (*)(unsigned long)) + tasklet_init(&priv->irq_tasklet, ipw_irq_tasklet, (unsigned long)priv);

return ret;

From: Phong Tran tranmanphong@gmail.com

[ Upstream commit cb775c88da5d48a85d99d95219f637b6fad2e0e9 ]

correct usage prototype of callback in tasklet_init(). Report by https://github.com/KSPP/linux/issues/20

Signed-off-by: Phong Tran tranmanphong@gmail.com Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/realtek/rtlwifi/pci.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index 457a0f725c8aa..ab74f31558540 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -1091,13 +1091,15 @@ done: return ret; }

-static void _rtl_pci_irq_tasklet(struct ieee80211_hw *hw) +static void _rtl_pci_irq_tasklet(unsigned long data) { + struct ieee80211_hw *hw = (struct ieee80211_hw *)data; _rtl_pci_tx_chk_waitq(hw); }

-static void _rtl_pci_prepare_bcn_tasklet(struct ieee80211_hw *hw) +static void _rtl_pci_prepare_bcn_tasklet(unsigned long data) { + struct ieee80211_hw *hw = (struct ieee80211_hw *)data; struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); struct rtl_mac *mac = rtl_mac(rtl_priv(hw)); @@ -1223,10 +1225,10 @@ static void _rtl_pci_init_struct(struct ieee80211_hw *hw,

/*task */ tasklet_init(&rtlpriv->works.irq_tasklet, - (void (*)(unsigned long))_rtl_pci_irq_tasklet, + _rtl_pci_irq_tasklet, (unsigned long)hw); tasklet_init(&rtlpriv->works.irq_prepare_bcn_tasklet, - (void (*)(unsigned long))_rtl_pci_prepare_bcn_tasklet, + _rtl_pci_prepare_bcn_tasklet, (unsigned long)hw); INIT_WORK(&rtlpriv->works.lps_change_work, rtl_lps_change_work_callback);

From: Erik Kaneda erik.kaneda@intel.com

[ Upstream commit 5ddbd77181dfca61b16d2e2222382ea65637f1b9 ]

ACPICA commit 29cc8dbc5463a93625bed87d7550a8bed8913bf4

create_buffer_field is a deferred op that is typically processed in load pass 2. However, disassembly of control method contents walk the parse tree with ACPI_PARSE_LOAD_PASS1 and AML_CREATE operators are processed in a later walk. This is a problem when there is a control method that has the same name as the AML_CREATE object. In this case, any use of the name segment will be detected as a method call rather than a reference to a buffer field. If this is detected as a method call, it can result in a mal-formed parse tree if the control methods have parameters.

This change in processing AML_CREATE ops earlier solves this issue by inserting the named object in the ACPI namespace so that references to this name would be detected as a name string rather than a method call.

Link: https://github.com/acpica/acpica/commit/29cc8dbc Reported-by: Elia Geretto elia.f.geretto@gmail.com Tested-by: Elia Geretto elia.f.geretto@gmail.com Signed-off-by: Bob Moore robert.moore@intel.com Signed-off-by: Erik Kaneda erik.kaneda@intel.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/acpica/dsfield.c | 2 +- drivers/acpi/acpica/dswload.c | 21 +++++++++++++++++++++ 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index 7bcf5f5ea0297..8df4a49a99a6b 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -273,7 +273,7 @@ cleanup: * FUNCTION: acpi_ds_get_field_names * * PARAMETERS: info - create_field info structure - * ` walk_state - Current method state + * walk_state - Current method state * arg - First parser arg for the field name list * * RETURN: Status diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c index eaa859a89702a..1d82e1419397e 100644 --- a/drivers/acpi/acpica/dswload.c +++ b/drivers/acpi/acpica/dswload.c @@ -444,6 +444,27 @@ acpi_status acpi_ds_load1_end_op(struct acpi_walk_state *walk_state) ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "Op=%p State=%p\n", op, walk_state));

+ /* + * Disassembler: handle create field operators here. + * + * create_buffer_field is a deferred op that is typically processed in load + * pass 2. However, disassembly of control method contents walk the parse + * tree with ACPI_PARSE_LOAD_PASS1 and AML_CREATE operators are processed + * in a later walk. This is a problem when there is a control method that + * has the same name as the AML_CREATE object. In this case, any use of the + * name segment will be detected as a method call rather than a reference + * to a buffer field. + * + * This earlier creation during disassembly solves this issue by inserting + * the named object in the ACPI namespace so that references to this name + * would be a name string rather than a method call. + */ + if ((walk_state->parse_flags & ACPI_PARSE_DISASSEMBLE) && + (walk_state->op_info->flags & AML_CREATE)) { + status = acpi_ds_create_buffer_field(op, walk_state); + return_ACPI_STATUS(status); + } + /* We are only interested in opcodes that have an associated name */

if (!(walk_state->op_info->flags & (AML_NAMED | AML_FIELD))) {

From: Nathan Chancellor natechancellor@gmail.com

[ Upstream commit 4dbc96ad65c45cdd4e895ed7ae4c151b780790c5 ]

Clang warns:

../drivers/scsi/aic7xxx/aic7xxx_core.c:2317:5: warning: misleading indentation; statement is not part of the previous 'if' [-Wmisleading-indentation] if ((syncrate->sxfr_u2 & ST_SXFR) != 0) ^ ../drivers/scsi/aic7xxx/aic7xxx_core.c:2310:4: note: previous statement is here if (syncrate == &ahc_syncrates[maxsync]) ^ 1 warning generated.

This warning occurs because there is a space amongst the tabs on this line. Remove it so that the indentation is consistent with the Linux kernel coding style and clang no longer warns.

This has been a problem since the beginning of git history hence no fixes tag.

Link: https://github.com/ClangBuiltLinux/linux/issues/817 Link: https://lore.kernel.org/r/20191218014220.52746-1-natechancellor@gmail.com Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/aic7xxx/aic7xxx_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c index 3818461640031..fdbb0a3dc9b4f 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_core.c +++ b/drivers/scsi/aic7xxx/aic7xxx_core.c @@ -2321,7 +2321,7 @@ ahc_find_syncrate(struct ahc_softc *ahc, u_int *period, * At some speeds, we only support * ST transfers. */ - if ((syncrate->sxfr_u2 & ST_SXFR) != 0) + if ((syncrate->sxfr_u2 & ST_SXFR) != 0) *ppr_options &= ~MSG_EXT_PPR_DT_REQ; break; }

From: Geert Uytterhoeven geert+renesas@glider.be

[ Upstream commit 8443ffd1bbd5be74e9b12db234746d12e8ea93e2 ]

Add a device node for the global timer, which is part of the Cortex-A9 MPCore.

The global timer can serve as an accurate (4 ns) clock source for scheduling and delay loops.

Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Link: https://lore.kernel.org/r/20191211135222.26770-4-geert+renesas@glider.be Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/r8a7779.dtsi | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/arch/arm/boot/dts/r8a7779.dtsi b/arch/arm/boot/dts/r8a7779.dtsi index 8ee0b2ca5d39a..2face089d65b9 100644 --- a/arch/arm/boot/dts/r8a7779.dtsi +++ b/arch/arm/boot/dts/r8a7779.dtsi @@ -67,6 +67,14 @@ <0xf0000100 0x100>; };

+ timer@f0000200 { + compatible = "arm,cortex-a9-global-timer"; + reg = <0xf0000200 0x100>; + interrupts = <GIC_PPI 11 + (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>; + clocks = <&cpg_clocks R8A7779_CLK_ZS>; + }; + timer@f0000600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0xf0000600 0x20>;

From: Valdis Klētnieks valdis.kletnieks@vt.edu

[ Upstream commit bff47c2302cc249bcd550b17067f8dddbd4b6f77 ]

When building with C=1, sparse issues a warning:

CHECK arch/x86/entry/vdso/vdso32-setup.c arch/x86/entry/vdso/vdso32-setup.c:28:28: warning: symbol 'vdso32_enabled' was not declared. Should it be static?

Provide the missing header file.

Signed-off-by: Valdis Kletnieks valdis.kletnieks@vt.edu Signed-off-by: Borislav Petkov bp@suse.de Cc: "H. Peter Anvin" hpa@zytor.com Cc: Andy Lutomirski luto@kernel.org Cc: Ingo Molnar mingo@redhat.com Cc: Thomas Gleixner tglx@linutronix.de Cc: x86-ml x86@kernel.org Link: https://lkml.kernel.org/r/36224.1575599767@turing-police Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/entry/vdso/vdso32-setup.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 42d4c89f990ed..ddff0ca6f5098 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -11,6 +11,7 @@ #include <linux/smp.h> #include <linux/kernel.h> #include <linux/mm_types.h> +#include <linux/elf.h>

#include <asm/processor.h> #include <asm/vdso.h>

From: Geert Uytterhoeven geert+renesas@glider.be

[ Upstream commit 02aeb2f21530c98fc3ca51028eda742a3fafbd9f ]

pinmux_func_gpios[] contains a hole due to the missing function GPIO definition for the "CTX0&CTX1" signal, which is the logical "AND" of the first two CAN outputs.

A closer look reveals other issues: - Some functionality is available on alternative pins, but the PINMUX_DATA() entries is using the wrong marks, - Several configurations are missing.

Fix this by: - Renaming CTX0CTX1CTX2_MARK, CRX0CRX1_PJ22_MARK, and CRX0CRX1CRX2_PJ20_MARK to CTX0_CTX1_CTX2_MARK, CRX0_CRX1_PJ22_MARK, resp. CRX0_CRX1_CRX2_PJ20_MARK for consistency with the corresponding enum IDs, - Adding all missing enum IDs and marks, - Use the right (*_PJ2x) variants for alternative pins, - Adding all missing configurations to pinmux_data[], - Adding all missing function GPIO definitions to pinmux_func_gpios[].

See SH7268 Group, SH7269 Group User’s Manual: Hardware, Rev. 2.00: [1] Table 1.4 List of Pins [2] Figure 23.29 Connection Example when Using Channels 0 and 1 as One Channel (64 Mailboxes × 1 Channel) and Channel 2 as One Channel (32 Mailboxes × 1 Channel), [3] Figure 23.30 Connection Example when Using Channels 0, 1, and 2 as One Channel (96 Mailboxes × 1 Channel), [4] Table 48.3 Multiplexed Pins (Port B), [5] Table 48.4 Multiplexed Pins (Port C), [6] Table 48.10 Multiplexed Pins (Port J), [7] Section 48.2.4 Port B Control Registers 0 to 5 (PBCR0 to PBCR5).

Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Link: https://lore.kernel.org/r/20191218194812.12741-5-geert+renesas@glider.be Signed-off-by: Sasha Levin sashal@kernel.org --- arch/sh/include/cpu-sh2a/cpu/sh7269.h | 11 ++++++-- drivers/pinctrl/sh-pfc/pfc-sh7269.c | 39 ++++++++++++++++++--------- 2 files changed, 36 insertions(+), 14 deletions(-)

diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7269.h b/arch/sh/include/cpu-sh2a/cpu/sh7269.h index d516e5d488180..b887cc402b712 100644 --- a/arch/sh/include/cpu-sh2a/cpu/sh7269.h +++ b/arch/sh/include/cpu-sh2a/cpu/sh7269.h @@ -78,8 +78,15 @@ enum { GPIO_FN_WDTOVF,

/* CAN */ - GPIO_FN_CTX1, GPIO_FN_CRX1, GPIO_FN_CTX0, GPIO_FN_CTX0_CTX1, - GPIO_FN_CRX0, GPIO_FN_CRX0_CRX1, GPIO_FN_CRX0_CRX1_CRX2, + GPIO_FN_CTX2, GPIO_FN_CRX2, + GPIO_FN_CTX1, GPIO_FN_CRX1, + GPIO_FN_CTX0, GPIO_FN_CRX0, + GPIO_FN_CTX0_CTX1, GPIO_FN_CRX0_CRX1, + GPIO_FN_CTX0_CTX1_CTX2, GPIO_FN_CRX0_CRX1_CRX2, + GPIO_FN_CTX2_PJ21, GPIO_FN_CRX2_PJ20, + GPIO_FN_CTX1_PJ23, GPIO_FN_CRX1_PJ22, + GPIO_FN_CTX0_CTX1_PJ23, GPIO_FN_CRX0_CRX1_PJ22, + GPIO_FN_CTX0_CTX1_CTX2_PJ21, GPIO_FN_CRX0_CRX1_CRX2_PJ20,

/* DMAC */ GPIO_FN_TEND0, GPIO_FN_DACK0, GPIO_FN_DREQ0, diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7269.c b/drivers/pinctrl/sh-pfc/pfc-sh7269.c index cfdb4fc177c3e..3df0c0d139d08 100644 --- a/drivers/pinctrl/sh-pfc/pfc-sh7269.c +++ b/drivers/pinctrl/sh-pfc/pfc-sh7269.c @@ -740,13 +740,12 @@ enum { CRX0_MARK, CTX0_MARK, CRX1_MARK, CTX1_MARK, CRX2_MARK, CTX2_MARK, - CRX0_CRX1_MARK, - CRX0_CRX1_CRX2_MARK, - CTX0CTX1CTX2_MARK, + CRX0_CRX1_MARK, CTX0_CTX1_MARK, + CRX0_CRX1_CRX2_MARK, CTX0_CTX1_CTX2_MARK, CRX1_PJ22_MARK, CTX1_PJ23_MARK, CRX2_PJ20_MARK, CTX2_PJ21_MARK, - CRX0CRX1_PJ22_MARK, - CRX0CRX1CRX2_PJ20_MARK, + CRX0_CRX1_PJ22_MARK, CTX0_CTX1_PJ23_MARK, + CRX0_CRX1_CRX2_PJ20_MARK, CTX0_CTX1_CTX2_PJ21_MARK,

/* VDC */ DV_CLK_MARK, @@ -824,6 +823,7 @@ static const u16 pinmux_data[] = { PINMUX_DATA(CS3_MARK, PC8MD_001), PINMUX_DATA(TXD7_MARK, PC8MD_010), PINMUX_DATA(CTX1_MARK, PC8MD_011), + PINMUX_DATA(CTX0_CTX1_MARK, PC8MD_100),

PINMUX_DATA(PC7_DATA, PC7MD_000), PINMUX_DATA(CKE_MARK, PC7MD_001), @@ -836,11 +836,12 @@ static const u16 pinmux_data[] = { PINMUX_DATA(CAS_MARK, PC6MD_001), PINMUX_DATA(SCK7_MARK, PC6MD_010), PINMUX_DATA(CTX0_MARK, PC6MD_011), + PINMUX_DATA(CTX0_CTX1_CTX2_MARK, PC6MD_100),

PINMUX_DATA(PC5_DATA, PC5MD_000), PINMUX_DATA(RAS_MARK, PC5MD_001), PINMUX_DATA(CRX0_MARK, PC5MD_011), - PINMUX_DATA(CTX0CTX1CTX2_MARK, PC5MD_100), + PINMUX_DATA(CTX0_CTX1_CTX2_MARK, PC5MD_100), PINMUX_DATA(IRQ0_PC_MARK, PC5MD_101),

PINMUX_DATA(PC4_DATA, PC4MD_00), @@ -1292,30 +1293,32 @@ static const u16 pinmux_data[] = { PINMUX_DATA(LCD_DATA23_PJ23_MARK, PJ23MD_010), PINMUX_DATA(LCD_TCON6_MARK, PJ23MD_011), PINMUX_DATA(IRQ3_PJ_MARK, PJ23MD_100), - PINMUX_DATA(CTX1_MARK, PJ23MD_101), + PINMUX_DATA(CTX1_PJ23_MARK, PJ23MD_101), + PINMUX_DATA(CTX0_CTX1_PJ23_MARK, PJ23MD_110),

PINMUX_DATA(PJ22_DATA, PJ22MD_000), PINMUX_DATA(DV_DATA22_MARK, PJ22MD_001), PINMUX_DATA(LCD_DATA22_PJ22_MARK, PJ22MD_010), PINMUX_DATA(LCD_TCON5_MARK, PJ22MD_011), PINMUX_DATA(IRQ2_PJ_MARK, PJ22MD_100), - PINMUX_DATA(CRX1_MARK, PJ22MD_101), - PINMUX_DATA(CRX0_CRX1_MARK, PJ22MD_110), + PINMUX_DATA(CRX1_PJ22_MARK, PJ22MD_101), + PINMUX_DATA(CRX0_CRX1_PJ22_MARK, PJ22MD_110),

PINMUX_DATA(PJ21_DATA, PJ21MD_000), PINMUX_DATA(DV_DATA21_MARK, PJ21MD_001), PINMUX_DATA(LCD_DATA21_PJ21_MARK, PJ21MD_010), PINMUX_DATA(LCD_TCON4_MARK, PJ21MD_011), PINMUX_DATA(IRQ1_PJ_MARK, PJ21MD_100), - PINMUX_DATA(CTX2_MARK, PJ21MD_101), + PINMUX_DATA(CTX2_PJ21_MARK, PJ21MD_101), + PINMUX_DATA(CTX0_CTX1_CTX2_PJ21_MARK, PJ21MD_110),

PINMUX_DATA(PJ20_DATA, PJ20MD_000), PINMUX_DATA(DV_DATA20_MARK, PJ20MD_001), PINMUX_DATA(LCD_DATA20_PJ20_MARK, PJ20MD_010), PINMUX_DATA(LCD_TCON3_MARK, PJ20MD_011), PINMUX_DATA(IRQ0_PJ_MARK, PJ20MD_100), - PINMUX_DATA(CRX2_MARK, PJ20MD_101), - PINMUX_DATA(CRX0CRX1CRX2_PJ20_MARK, PJ20MD_110), + PINMUX_DATA(CRX2_PJ20_MARK, PJ20MD_101), + PINMUX_DATA(CRX0_CRX1_CRX2_PJ20_MARK, PJ20MD_110),

PINMUX_DATA(PJ19_DATA, PJ19MD_000), PINMUX_DATA(DV_DATA19_MARK, PJ19MD_001), @@ -1666,12 +1669,24 @@ static const struct pinmux_func pinmux_func_gpios[] = { GPIO_FN(WDTOVF),

/* CAN */ + GPIO_FN(CTX2), + GPIO_FN(CRX2), GPIO_FN(CTX1), GPIO_FN(CRX1), GPIO_FN(CTX0), GPIO_FN(CRX0), + GPIO_FN(CTX0_CTX1), GPIO_FN(CRX0_CRX1), + GPIO_FN(CTX0_CTX1_CTX2), GPIO_FN(CRX0_CRX1_CRX2), + GPIO_FN(CTX2_PJ21), + GPIO_FN(CRX2_PJ20), + GPIO_FN(CTX1_PJ23), + GPIO_FN(CRX1_PJ22), + GPIO_FN(CTX0_CTX1_PJ23), + GPIO_FN(CRX0_CRX1_PJ22), + GPIO_FN(CTX0_CTX1_CTX2_PJ21), + GPIO_FN(CRX0_CRX1_CRX2_PJ20),

/* DMAC */ GPIO_FN(TEND0),

From: Icenowy Zheng icenowy@aosc.io

[ Upstream commit ec97faff743b398e21f74a54c81333f3390093aa ]

The A64 PLL_CPU clock has the same instability if some factor changed without the PLL gated like other SoCs with sun6i-style CCU, e.g. A33, H3.

Add the mux and pll notifiers for A64 CPU clock to workaround the problem.

Fixes: c6a0637460c2 ("clk: sunxi-ng: Add A64 clocks") Signed-off-by: Icenowy Zheng icenowy@aosc.io Signed-off-by: Vasily Khoruzhick anarsoul@gmail.com Signed-off-by: Maxime Ripard maxime@cerno.tech Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/sunxi-ng/ccu-sun50i-a64.c | 28 ++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c index eaafc038368f5..183985c8c9bab 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c @@ -884,11 +884,26 @@ static const struct sunxi_ccu_desc sun50i_a64_ccu_desc = { .num_resets = ARRAY_SIZE(sun50i_a64_ccu_resets), };

+static struct ccu_pll_nb sun50i_a64_pll_cpu_nb = { + .common = &pll_cpux_clk.common, + /* copy from pll_cpux_clk */ + .enable = BIT(31), + .lock = BIT(28), +}; + +static struct ccu_mux_nb sun50i_a64_cpu_nb = { + .common = &cpux_clk.common, + .cm = &cpux_clk.mux, + .delay_us = 1, /* > 8 clock cycles at 24 MHz */ + .bypass_index = 1, /* index of 24 MHz oscillator */ +}; + static int sun50i_a64_ccu_probe(struct platform_device *pdev) { struct resource *res; void __iomem *reg; u32 val; + int ret;

res = platform_get_resource(pdev, IORESOURCE_MEM, 0); reg = devm_ioremap_resource(&pdev->dev, res); @@ -902,7 +917,18 @@ static int sun50i_a64_ccu_probe(struct platform_device *pdev)

writel(0x515, reg + SUN50I_A64_PLL_MIPI_REG);

- return sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_a64_ccu_desc); + ret = sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_a64_ccu_desc); + if (ret) + return ret; + + /* Gate then ungate PLL CPU after any rate changes */ + ccu_pll_notifier_register(&sun50i_a64_pll_cpu_nb); + + /* Reparent CPU during PLL CPU rate changes */ + ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk, + &sun50i_a64_cpu_nb); + + return 0; }

static const struct of_device_id sun50i_a64_ccu_ids[] = {

From: Takashi Iwai tiwai@suse.de

[ Upstream commit f1dd4795b1523fbca7ab4344dd5a8bb439cc770d ]

A long-standing compile warning was seen during build test: sound/sh/aica.c: In function 'load_aica_firmware': sound/sh/aica.c:521:25: warning: passing argument 2 of 'spu_memload' discards 'const' qualifier from pointer target type [-Wdiscarded-qualifiers]

Fixes: 198de43d758c ("[ALSA] Add ALSA support for the SEGA Dreamcast PCM device") Link: https://lore.kernel.org/r/20200105144823.29547-69-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/sh/aica.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/sh/aica.c b/sound/sh/aica.c index fdc680ae8aa09..d9acf551a8985 100644 --- a/sound/sh/aica.c +++ b/sound/sh/aica.c @@ -117,10 +117,10 @@ static void spu_memset(u32 toi, u32 what, int length) }

/* spu_memload - write to SPU address space */ -static void spu_memload(u32 toi, void *from, int length) +static void spu_memload(u32 toi, const void *from, int length) { unsigned long flags; - u32 *froml = from; + const u32 *froml = from; u32 __iomem *to = (u32 __iomem *) (SPU_MEMORY_BASE + toi); int i; u32 val;

From: Dingchen Zhang dingchen.zhang@amd.com

[ Upstream commit 72a848f5c46bab4c921edc9cbffd1ab273b2be17 ]

userspace may transfer a newline, and this terminating newline is replaced by a '\0' to avoid followup issues.

'len-1' is the index to replace the newline of CRC source name.

v3: typo fix (Sam)

v2: update patch subject, body and format. (Sam)

Cc: Leo Li sunpeng.li@amd.com Cc: Harry Wentland Harry.Wentland@amd.com Cc: Sam Ravnborg sam@ravnborg.org Signed-off-by: Dingchen Zhang dingchen.zhang@amd.com Reviewed-by: Sam Ravnborg sam@ravnborg.org Signed-off-by: Alex Deucher alexander.deucher@amd.com Link: https://patchwork.freedesktop.org/patch/msgid/20190610134751.14356-1-dingche... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/drm_debugfs_crc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c index 2901b7944068d..6858c80d2eb50 100644 --- a/drivers/gpu/drm/drm_debugfs_crc.c +++ b/drivers/gpu/drm/drm_debugfs_crc.c @@ -101,8 +101,8 @@ static ssize_t crc_control_write(struct file *file, const char __user *ubuf, if (IS_ERR(source)) return PTR_ERR(source);

- if (source[len] == '\n') - source[len] = '\0'; + if (source[len - 1] == '\n') + source[len - 1] = '\0';

spin_lock_irq(&crc->lock);

From: Jan Kara jack@suse.cz

[ Upstream commit a4a8b99ec819ca60b49dc582a4287ef03411f117 ]

Free space on filesystems with metadata or virtual partition maps currently gets misreported. This is because these partitions are just remapped onto underlying real partitions from which keep track of free blocks. Take this remapping into account when counting free blocks as well.

Reviewed-by: Pali Rohár pali.rohar@gmail.com Reported-by: Pali Rohár pali.rohar@gmail.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- fs/udf/super.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/fs/udf/super.c b/fs/udf/super.c index 242d960df9a17..51de27685e185 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -2467,17 +2467,29 @@ static unsigned int udf_count_free_table(struct super_block *sb, static unsigned int udf_count_free(struct super_block *sb) { unsigned int accum = 0; - struct udf_sb_info *sbi; + struct udf_sb_info *sbi = UDF_SB(sb); struct udf_part_map *map; + unsigned int part = sbi->s_partition; + int ptype = sbi->s_partmaps[part].s_partition_type; + + if (ptype == UDF_METADATA_MAP25) { + part = sbi->s_partmaps[part].s_type_specific.s_metadata. + s_phys_partition_ref; + } else if (ptype == UDF_VIRTUAL_MAP15 || ptype == UDF_VIRTUAL_MAP20) { + /* + * Filesystems with VAT are append-only and we cannot write to + * them. Let's just report 0 here. + */ + return 0; + }

- sbi = UDF_SB(sb); if (sbi->s_lvid_bh) { struct logicalVolIntegrityDesc *lvid = (struct logicalVolIntegrityDesc *) sbi->s_lvid_bh->b_data; - if (le32_to_cpu(lvid->numOfPartitions) > sbi->s_partition) { + if (le32_to_cpu(lvid->numOfPartitions) > part) { accum = le32_to_cpu( - lvid->freeSpaceTable[sbi->s_partition]); + lvid->freeSpaceTable[part]); if (accum == 0xFFFFFFFF) accum = 0; } @@ -2486,7 +2498,7 @@ static unsigned int udf_count_free(struct super_block *sb) if (accum) return accum;

- map = &sbi->s_partmaps[sbi->s_partition]; + map = &sbi->s_partmaps[part]; if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) { accum += udf_count_free_bitmap(sb, map->s_uspace.s_bitmap);

From: Dmitry Osipenko digetx@gmail.com

[ Upstream commit 2d9ea1934f8ef0dfb862d103389562cc28b4fc03 ]

Trying to read out Chip ID before APBMISC registers are mapped won't succeed, in a result Tegra124 gets a wrong address for the HW straps register if machine uses an old outdated device tree.

Fixes: 297c4f3dcbff ("soc/tegra: fuse: Restrict legacy code to 32-bit ARM") Signed-off-by: Dmitry Osipenko digetx@gmail.com Signed-off-by: Thierry Reding treding@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/tegra/fuse/tegra-apbmisc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/soc/tegra/fuse/tegra-apbmisc.c b/drivers/soc/tegra/fuse/tegra-apbmisc.c index 5b18f6ffa45c7..cd61c883c19f5 100644 --- a/drivers/soc/tegra/fuse/tegra-apbmisc.c +++ b/drivers/soc/tegra/fuse/tegra-apbmisc.c @@ -134,7 +134,7 @@ void __init tegra_init_apbmisc(void) apbmisc.flags = IORESOURCE_MEM;

/* strapping options */ - if (tegra_get_chip_id() == TEGRA124) { + if (of_machine_is_compatible("nvidia,tegra124")) { straps.start = 0x7000e864; straps.end = 0x7000e867; } else {

From: Paul E. McKenney paulmck@kernel.org

[ Upstream commit 860c8802ace14c646864795e057349c9fb2d60ad ]

Eric Dumazet supplied a KCSAN report of a bug that forces use of hlist_unhashed_lockless() from sk_unhashed():

------------------------------------------------------------------------

BUG: KCSAN: data-race in inet_unhash / inet_unhash

write to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 1: __hlist_nulls_del include/linux/list_nulls.h:88 [inline] hlist_nulls_del_init_rcu include/linux/rculist_nulls.h:36 [inline] __sk_nulls_del_node_init_rcu include/net/sock.h:676 [inline] inet_unhash+0x38f/0x4a0 net/ipv4/inet_hashtables.c:612 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241

read to 0xffff8880a69a0170 of 8 bytes by interrupt on cpu 0: sk_unhashed include/net/sock.h:607 [inline] inet_unhash+0x3d/0x4a0 net/ipv4/inet_hashtables.c:592 tcp_set_state+0xfa/0x3e0 net/ipv4/tcp.c:2249 tcp_done+0x93/0x1e0 net/ipv4/tcp.c:3854 tcp_write_err+0x7e/0xc0 net/ipv4/tcp_timer.c:56 tcp_retransmit_timer+0x9b8/0x16d0 net/ipv4/tcp_timer.c:479 tcp_write_timer_handler+0x42d/0x510 net/ipv4/tcp_timer.c:599 tcp_write_timer+0xd1/0xf0 net/ipv4/tcp_timer.c:619 call_timer_fn+0x5f/0x2f0 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0xc0c/0xcd0 kernel/time/timer.c:1786 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 rest_init+0xec/0xf6 init/main.c:452 arch_call_rest_init+0x17/0x37 start_kernel+0x838/0x85e init/main.c:786 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490 x86_64_start_kernel+0x72/0x76 arch/x86/kernel/head64.c:471 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.0-rc6+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

------------------------------------------------------------------------

This commit therefore replaces C-language assignments with WRITE_ONCE() in include/linux/list_nulls.h and include/linux/rculist_nulls.h.

Reported-by: Eric Dumazet edumazet@google.com # For KCSAN Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/list_nulls.h | 8 ++++---- include/linux/rculist_nulls.h | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 3ef96743db8da..1ecd35664e0d3 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -72,10 +72,10 @@ static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, struct hlist_nulls_node *first = h->first;

n->next = first; - n->pprev = &h->first; + WRITE_ONCE(n->pprev, &h->first); h->first = n; if (!is_a_nulls(first)) - first->pprev = &n->next; + WRITE_ONCE(first->pprev, &n->next); }

static inline void __hlist_nulls_del(struct hlist_nulls_node *n) @@ -85,13 +85,13 @@ static inline void __hlist_nulls_del(struct hlist_nulls_node *n)

WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) - next->pprev = pprev; + WRITE_ONCE(next->pprev, pprev); }

static inline void hlist_nulls_del(struct hlist_nulls_node *n) { __hlist_nulls_del(n); - n->pprev = LIST_POISON2; + WRITE_ONCE(n->pprev, LIST_POISON2); }

/** diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index a10da545b3f67..cf64a94922566 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -34,7 +34,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) { if (!hlist_nulls_unhashed(n)) { __hlist_nulls_del(n); - n->pprev = NULL; + WRITE_ONCE(n->pprev, NULL); } }

@@ -66,7 +66,7 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n) { __hlist_nulls_del(n); - n->pprev = LIST_POISON2; + WRITE_ONCE(n->pprev, LIST_POISON2); }

/** @@ -94,10 +94,10 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, struct hlist_nulls_node *first = h->first;

n->next = first; - n->pprev = &h->first; + WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_nulls_first_rcu(h), n); if (!is_a_nulls(first)) - first->pprev = &n->next; + WRITE_ONCE(first->pprev, &n->next); }

/**

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit 504c28c853ec5c626900b914b5833daf0581a344 ]

Change the driver to use portable integer types to avoid warnings during compile testing:

drivers/net/wan/ixp4xx_hss.c:863:21: error: cast to 'u32 *' (aka 'unsigned int *') from smaller integer type 'int' [-Werror,-Wint-to-pointer-cast] memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4); ^ drivers/net/wan/ixp4xx_hss.c:979:12: error: incompatible pointer types passing 'u32 *' (aka 'unsigned int *') to parameter of type 'dma_addr_t *' (aka 'unsigned long long *') [-Werror,-Wincompatible-pointer-types] &port->desc_tab_phys))) ^~~~~~~~~~~~~~~~~~~~ include/linux/dmapool.h:27:20: note: passing argument to parameter 'handle' here dma_addr_t *handle); ^

Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wan/ixp4xx_hss.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c index 6a505c26a3e74..a269ed63d90f7 100644 --- a/drivers/net/wan/ixp4xx_hss.c +++ b/drivers/net/wan/ixp4xx_hss.c @@ -261,7 +261,7 @@ struct port { struct hss_plat_info *plat; buffer_t *rx_buff_tab[RX_DESCS], *tx_buff_tab[TX_DESCS]; struct desc *desc_tab; /* coherent */ - u32 desc_tab_phys; + dma_addr_t desc_tab_phys; unsigned int id; unsigned int clock_type, clock_rate, loopback; unsigned int initialized, carrier; @@ -861,7 +861,7 @@ static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_dropped++; return NETDEV_TX_OK; } - memcpy_swab32(mem, (u32 *)((int)skb->data & ~3), bytes / 4); + memcpy_swab32(mem, (u32 *)((uintptr_t)skb->data & ~3), bytes / 4); dev_kfree_skb(skb); #endif

From: Nathan Chancellor natechancellor@gmail.com

[ Upstream commit 1feedf61e7265128244f6993f23421f33dd93dbc ]

Clang warns:

../drivers/tty/synclinkmp.c:1456:3: warning: misleading indentation; statement is not part of the previous 'if' [-Wmisleading-indentation] if (C_CRTSCTS(tty)) { ^ ../drivers/tty/synclinkmp.c:1453:2: note: previous statement is here if (I_IXOFF(tty)) ^ ../drivers/tty/synclinkmp.c:2473:8: warning: misleading indentation; statement is not part of the previous 'if' [-Wmisleading-indentation] info->port.tty->hw_stopped = 0; ^ ../drivers/tty/synclinkmp.c:2471:7: note: previous statement is here if ( debug_level >= DEBUG_LEVEL_ISR ) ^ ../drivers/tty/synclinkmp.c:2482:8: warning: misleading indentation; statement is not part of the previous 'if' [-Wmisleading-indentation] info->port.tty->hw_stopped = 1; ^ ../drivers/tty/synclinkmp.c:2480:7: note: previous statement is here if ( debug_level >= DEBUG_LEVEL_ISR ) ^ ../drivers/tty/synclinkmp.c:2809:3: warning: misleading indentation; statement is not part of the previous 'if' [-Wmisleading-indentation] if (I_BRKINT(info->port.tty) || I_PARMRK(info->port.tty)) ^ ../drivers/tty/synclinkmp.c:2807:2: note: previous statement is here if (I_INPCK(info->port.tty)) ^ ../drivers/tty/synclinkmp.c:3246:3: warning: misleading indentation; statement is not part of the previous 'else' [-Wmisleading-indentation] set_signals(info); ^ ../drivers/tty/synclinkmp.c:3244:2: note: previous statement is here else ^ 5 warnings generated.

The indentation on these lines is not at all consistent, tabs and spaces are mixed together. Convert to just using tabs to be consistent with the Linux kernel coding style and eliminate these warnings from clang.

Link: https://github.com/ClangBuiltLinux/linux/issues/823 Signed-off-by: Nathan Chancellor natechancellor@gmail.com Link: https://lore.kernel.org/r/20191218024720.3528-1-natechancellor@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/tty/synclinkmp.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/tty/synclinkmp.c b/drivers/tty/synclinkmp.c index 4fed9e7b281f0..3c9e314406b4e 100644 --- a/drivers/tty/synclinkmp.c +++ b/drivers/tty/synclinkmp.c @@ -1467,10 +1467,10 @@ static void throttle(struct tty_struct * tty) if (I_IXOFF(tty)) send_xchar(tty, STOP_CHAR(tty));

- if (C_CRTSCTS(tty)) { + if (C_CRTSCTS(tty)) { spin_lock_irqsave(&info->lock,flags); info->serial_signals &= ~SerialSignal_RTS; - set_signals(info); + set_signals(info); spin_unlock_irqrestore(&info->lock,flags); } } @@ -1496,10 +1496,10 @@ static void unthrottle(struct tty_struct * tty) send_xchar(tty, START_CHAR(tty)); }

- if (C_CRTSCTS(tty)) { + if (C_CRTSCTS(tty)) { spin_lock_irqsave(&info->lock,flags); info->serial_signals |= SerialSignal_RTS; - set_signals(info); + set_signals(info); spin_unlock_irqrestore(&info->lock,flags); } } @@ -2484,7 +2484,7 @@ static void isr_io_pin( SLMP_INFO *info, u16 status ) if (status & SerialSignal_CTS) { if ( debug_level >= DEBUG_LEVEL_ISR ) printk("CTS tx start..."); - info->port.tty->hw_stopped = 0; + info->port.tty->hw_stopped = 0; tx_start(info); info->pending_bh |= BH_TRANSMIT; return; @@ -2493,7 +2493,7 @@ static void isr_io_pin( SLMP_INFO *info, u16 status ) if (!(status & SerialSignal_CTS)) { if ( debug_level >= DEBUG_LEVEL_ISR ) printk("CTS tx stop..."); - info->port.tty->hw_stopped = 1; + info->port.tty->hw_stopped = 1; tx_stop(info); } } @@ -2820,8 +2820,8 @@ static void change_params(SLMP_INFO *info) info->read_status_mask2 = OVRN; if (I_INPCK(info->port.tty)) info->read_status_mask2 |= PE | FRME; - if (I_BRKINT(info->port.tty) || I_PARMRK(info->port.tty)) - info->read_status_mask1 |= BRKD; + if (I_BRKINT(info->port.tty) || I_PARMRK(info->port.tty)) + info->read_status_mask1 |= BRKD; if (I_IGNPAR(info->port.tty)) info->ignore_status_mask2 |= PE | FRME; if (I_IGNBRK(info->port.tty)) { @@ -3191,7 +3191,7 @@ static int tiocmget(struct tty_struct *tty) unsigned long flags;

spin_lock_irqsave(&info->lock,flags); - get_signals(info); + get_signals(info); spin_unlock_irqrestore(&info->lock,flags);

result = ((info->serial_signals & SerialSignal_RTS) ? TIOCM_RTS : 0) | @@ -3229,7 +3229,7 @@ static int tiocmset(struct tty_struct *tty, info->serial_signals &= ~SerialSignal_DTR;

spin_lock_irqsave(&info->lock,flags); - set_signals(info); + set_signals(info); spin_unlock_irqrestore(&info->lock,flags);

return 0; @@ -3241,7 +3241,7 @@ static int carrier_raised(struct tty_port *port) unsigned long flags;

spin_lock_irqsave(&info->lock,flags); - get_signals(info); + get_signals(info); spin_unlock_irqrestore(&info->lock,flags);

return (info->serial_signals & SerialSignal_DCD) ? 1 : 0; @@ -3257,7 +3257,7 @@ static void dtr_rts(struct tty_port *port, int on) info->serial_signals |= SerialSignal_RTS | SerialSignal_DTR; else info->serial_signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_signals(info); + set_signals(info); spin_unlock_irqrestore(&info->lock,flags); }

From: Simon Schwartz kern.simon@theschwartz.xyz

[ Upstream commit 39cc539f90d035a293240c9443af50be55ee81b8 ]

num_resources in the platform_device struct is declared as a u32. The for loops that iterate over num_resources use an int as the counter, which can cause infinite loops on architectures with smaller ints. Change the loop counters to u32.

Signed-off-by: Simon Schwartz kern.simon@theschwartz.xyz Link: https://lore.kernel.org/r/2201ce63a2a171ffd2ed14e867875316efcf71db.camel@the... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/platform.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/base/platform.c b/drivers/base/platform.c index f1105de0d9fed..e3d40c41c33b0 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -28,6 +28,7 @@ #include <linux/limits.h> #include <linux/property.h> #include <linux/kmemleak.h> +#include <linux/types.h>

#include "base.h" #include "power/power.h" @@ -68,7 +69,7 @@ void __weak arch_setup_pdev_archdata(struct platform_device *pdev) struct resource *platform_get_resource(struct platform_device *dev, unsigned int type, unsigned int num) { - int i; + u32 i;

for (i = 0; i < dev->num_resources; i++) { struct resource *r = &dev->resource[i]; @@ -163,7 +164,7 @@ struct resource *platform_get_resource_byname(struct platform_device *dev, unsigned int type, const char *name) { - int i; + u32 i;

for (i = 0; i < dev->num_resources; i++) { struct resource *r = &dev->resource[i]; @@ -360,7 +361,8 @@ EXPORT_SYMBOL_GPL(platform_device_add_properties); */ int platform_device_add(struct platform_device *pdev) { - int i, ret; + u32 i; + int ret;

if (!pdev) return -EINVAL; @@ -447,7 +449,7 @@ EXPORT_SYMBOL_GPL(platform_device_add); */ void platform_device_del(struct platform_device *pdev) { - int i; + u32 i;

if (pdev) { device_remove_properties(&pdev->dev);

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit 7483e7a939c074d887450ef1c4d9ccc5909405f8 ]

With CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE_O3, the stack usage in vme_fake grows above the warning limit:

drivers/vme/bridges/vme_fake.c: In function 'fake_master_read': drivers/vme/bridges/vme_fake.c:610:1: error: the frame size of 1160 bytes is larger than 1024 bytes [-Werror=frame-larger-than=] drivers/vme/bridges/vme_fake.c: In function 'fake_master_write': drivers/vme/bridges/vme_fake.c:797:1: error: the frame size of 1160 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]

The problem is that in some configurations, each call to fake_vmereadX() puts another variable on the stack.

Reduce the amount of inlining to get back to the previous state, with no function using more than 200 bytes each.

Signed-off-by: Arnd Bergmann arnd@arndb.de Link: https://lore.kernel.org/r/20200107200610.3482901-1-arnd@arndb.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/vme/bridges/vme_fake.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/vme/bridges/vme_fake.c b/drivers/vme/bridges/vme_fake.c index 30b3acc938330..e81ec763b5555 100644 --- a/drivers/vme/bridges/vme_fake.c +++ b/drivers/vme/bridges/vme_fake.c @@ -418,8 +418,9 @@ static void fake_lm_check(struct fake_driver *bridge, unsigned long long addr, } }

-static u8 fake_vmeread8(struct fake_driver *bridge, unsigned long long addr, - u32 aspace, u32 cycle) +static noinline_for_stack u8 fake_vmeread8(struct fake_driver *bridge, + unsigned long long addr, + u32 aspace, u32 cycle) { u8 retval = 0xff; int i; @@ -450,8 +451,9 @@ static u8 fake_vmeread8(struct fake_driver *bridge, unsigned long long addr, return retval; }

-static u16 fake_vmeread16(struct fake_driver *bridge, unsigned long long addr, - u32 aspace, u32 cycle) +static noinline_for_stack u16 fake_vmeread16(struct fake_driver *bridge, + unsigned long long addr, + u32 aspace, u32 cycle) { u16 retval = 0xffff; int i; @@ -482,8 +484,9 @@ static u16 fake_vmeread16(struct fake_driver *bridge, unsigned long long addr, return retval; }

-static u32 fake_vmeread32(struct fake_driver *bridge, unsigned long long addr, - u32 aspace, u32 cycle) +static noinline_for_stack u32 fake_vmeread32(struct fake_driver *bridge, + unsigned long long addr, + u32 aspace, u32 cycle) { u32 retval = 0xffffffff; int i; @@ -613,8 +616,9 @@ out: return retval; }

-static void fake_vmewrite8(struct fake_driver *bridge, u8 *buf, - unsigned long long addr, u32 aspace, u32 cycle) +static noinline_for_stack void fake_vmewrite8(struct fake_driver *bridge, + u8 *buf, unsigned long long addr, + u32 aspace, u32 cycle) { int i; unsigned long long start, end, offset; @@ -643,8 +647,9 @@ static void fake_vmewrite8(struct fake_driver *bridge, u8 *buf,

}

-static void fake_vmewrite16(struct fake_driver *bridge, u16 *buf, - unsigned long long addr, u32 aspace, u32 cycle) +static noinline_for_stack void fake_vmewrite16(struct fake_driver *bridge, + u16 *buf, unsigned long long addr, + u32 aspace, u32 cycle) { int i; unsigned long long start, end, offset; @@ -673,8 +678,9 @@ static void fake_vmewrite16(struct fake_driver *bridge, u16 *buf,

}

-static void fake_vmewrite32(struct fake_driver *bridge, u32 *buf, - unsigned long long addr, u32 aspace, u32 cycle) +static noinline_for_stack void fake_vmewrite32(struct fake_driver *bridge, + u32 *buf, unsigned long long addr, + u32 aspace, u32 cycle) { int i; unsigned long long start, end, offset;

From: Ben Skeggs bskeggs@redhat.com

[ Upstream commit 7adc77aa0e11f25b0e762859219c70852cd8d56f ]

Method init is typically ordered by class in the FW image as ThreeD, TwoD, Compute.

Due to a bug in parsing the FW into our internal format, we've been accidentally sending Twod + Compute methods to the ThreeD class, as well as Compute methods to the TwoD class - oops.

Signed-off-by: Ben Skeggs bskeggs@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../gpu/drm/nouveau/nvkm/engine/gr/gk20a.c | 21 ++++++++++--------- 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c index de8b806b88fd9..7618b2eb4fdfd 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c @@ -143,23 +143,24 @@ gk20a_gr_av_to_method(struct gf100_gr *gr, const char *fw_name,

nent = (fuc.size / sizeof(struct gk20a_fw_av));

- pack = vzalloc((sizeof(*pack) * max_classes) + - (sizeof(*init) * (nent + 1))); + pack = vzalloc((sizeof(*pack) * (max_classes + 1)) + + (sizeof(*init) * (nent + max_classes + 1))); if (!pack) { ret = -ENOMEM; goto end; }

- init = (void *)(pack + max_classes); + init = (void *)(pack + max_classes + 1);

- for (i = 0; i < nent; i++) { - struct gf100_gr_init *ent = &init[i]; + for (i = 0; i < nent; i++, init++) { struct gk20a_fw_av *av = &((struct gk20a_fw_av *)fuc.data)[i]; u32 class = av->addr & 0xffff; u32 addr = (av->addr & 0xffff0000) >> 14;

if (prevclass != class) { - pack[classidx].init = ent; + if (prevclass) /* Add terminator to the method list. */ + init++; + pack[classidx].init = init; pack[classidx].type = class; prevclass = class; if (++classidx >= max_classes) { @@ -169,10 +170,10 @@ gk20a_gr_av_to_method(struct gf100_gr *gr, const char *fw_name, } }

- ent->addr = addr; - ent->data = av->data; - ent->count = 1; - ent->pitch = 1; + init->addr = addr; + init->data = av->data; + init->count = 1; + init->pitch = 1; }

*ppack = pack;

From: Navid Emamdoost navid.emamdoost@gmail.com

[ Upstream commit 40efb09a7f53125719e49864da008495e39aaa1e ]

In vmw_cmdbuf_res_add if drm_ht_insert_item fails the allocated memory for cres should be released.

Fixes: 18e4a4669c50 ("drm/vmwgfx: Fix compat shader namespace") Signed-off-by: Navid Emamdoost navid.emamdoost@gmail.com Reviewed-by: Thomas Hellstrom thellstrom@vmware.com Signed-off-by: Thomas Hellstrom thellstrom@vmware.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c index 36c7b6c839c0d..738ad2fc79a25 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c @@ -210,8 +210,10 @@ int vmw_cmdbuf_res_add(struct vmw_cmdbuf_res_manager *man,

cres->hash.key = user_key | (res_type << 24); ret = drm_ht_insert_item(&man->resources, &cres->hash); - if (unlikely(ret != 0)) + if (unlikely(ret != 0)) { + kfree(cres); goto out_invalid_key; + }

cres->state = VMW_CMDBUF_RES_ADD; cres->res = vmw_resource_reference(res);

From: Will Deacon will@kernel.org

[ Upstream commit d71e01716b3606a6648df7e5646ae12c75babde4 ]

If, for some bizarre reason, the compiler decided to split up the write of STE DWORD 0, we could end up making a partial structure valid.

Although this probably won't happen, follow the example of the context-descriptor code and use WRITE_ONCE() to ensure atomicity of the write.

Reported-by: Jean-Philippe Brucker jean-philippe@linaro.org Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/arm-smmu-v3.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 09eb258a9a7de..29feafa8007fb 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1145,7 +1145,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, }

arm_smmu_sync_ste_for_sid(smmu, sid); - dst[0] = cpu_to_le64(val); + /* See comment in arm_smmu_write_ctx_desc() */ + WRITE_ONCE(dst[0], cpu_to_le64(val)); arm_smmu_sync_ste_for_sid(smmu, sid);

/* It's likely that we'll want to use the new STE soon */

From: Nick Black nlb@google.com

[ Upstream commit 54155ed4199c7aa3fd20866648024ab63c96d579 ]

A faulty userspace that calls destroy_session() before destroying the connections can trigger the failure. This patch prevents the issue by refusing to destroy the session if there are outstanding connections.

------------[ cut here ]------------ kernel BUG at mm/slub.c:306! invalid opcode: 0000 [#1] SMP PTI CPU: 1 PID: 1224 Comm: iscsid Not tainted 5.4.0-rc2.iscsi+ #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 RIP: 0010:__slab_free+0x181/0x350 [...] [ 1209.686056] RSP: 0018:ffffa93d4074fae0 EFLAGS: 00010246 [ 1209.686694] RAX: ffff934efa5ad800 RBX: 000000008010000a RCX: ffff934efa5ad800 [ 1209.687651] RDX: ffff934efa5ad800 RSI: ffffeb4041e96b00 RDI: ffff934efd402c40 [ 1209.688582] RBP: ffffa93d4074fb80 R08: 0000000000000001 R09: ffffffffbb5dfa26 [ 1209.689425] R10: ffff934efa5ad800 R11: 0000000000000001 R12: ffffeb4041e96b00 [ 1209.690285] R13: ffff934efa5ad800 R14: ffff934efd402c40 R15: 0000000000000000 [ 1209.691213] FS: 00007f7945dfb540(0000) GS:ffff934efda80000(0000) knlGS:0000000000000000 [ 1209.692316] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1209.693013] CR2: 000055877fd3da80 CR3: 0000000077384000 CR4: 00000000000006e0 [ 1209.693897] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1209.694773] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1209.695631] Call Trace: [ 1209.695957] ? __wake_up_common_lock+0x8a/0xc0 [ 1209.696712] iscsi_pool_free+0x26/0x40 [ 1209.697263] iscsi_session_teardown+0x2f/0xf0 [ 1209.698117] iscsi_sw_tcp_session_destroy+0x45/0x60 [ 1209.698831] iscsi_if_rx+0xd88/0x14e0 [ 1209.699370] netlink_unicast+0x16f/0x200 [ 1209.699932] netlink_sendmsg+0x21a/0x3e0 [ 1209.700446] sock_sendmsg+0x4f/0x60 [ 1209.700902] ___sys_sendmsg+0x2ae/0x320 [ 1209.701451] ? cp_new_stat+0x150/0x180 [ 1209.701922] __sys_sendmsg+0x59/0xa0 [ 1209.702357] do_syscall_64+0x52/0x160 [ 1209.702812] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1209.703419] RIP: 0033:0x7f7946433914 [...] [ 1209.706084] RSP: 002b:00007fffb99f2378 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 1209.706994] RAX: ffffffffffffffda RBX: 000055bc869eac20 RCX: 00007f7946433914 [ 1209.708082] RDX: 0000000000000000 RSI: 00007fffb99f2390 RDI: 0000000000000005 [ 1209.709120] RBP: 00007fffb99f2390 R08: 000055bc84fe9320 R09: 00007fffb99f1f07 [ 1209.710110] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000038 [ 1209.711085] R13: 000055bc8502306e R14: 0000000000000000 R15: 0000000000000000 Modules linked in: ---[ end trace a2d933ede7f730d8 ]---

Link: https://lore.kernel.org/r/20191226203148.2172200-1-krisman@collabora.com Signed-off-by: Nick Black nlb@google.com Co-developed-by: Salman Qazi sqazi@google.com Signed-off-by: Salman Qazi sqazi@google.com Co-developed-by: Junho Ryu jayr@google.com Signed-off-by: Junho Ryu jayr@google.com Co-developed-by: Khazhismel Kumykov khazhy@google.com Signed-off-by: Khazhismel Kumykov khazhy@google.com Co-developed-by: Gabriel Krisman Bertazi krisman@collabora.com Signed-off-by: Gabriel Krisman Bertazi krisman@collabora.com Reviewed-by: Lee Duncan lduncan@suse.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/iscsi_tcp.c | 4 ++++ drivers/scsi/scsi_transport_iscsi.c | 26 +++++++++++++++++++++++--- 2 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 7e3a77d3c6f01..e3ca16043f9af 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -890,6 +890,10 @@ free_host: static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session) { struct Scsi_Host *shost = iscsi_session_to_shost(cls_session); + struct iscsi_session *session = cls_session->dd_data; + + if (WARN_ON_ONCE(session->leadconn)) + return;

iscsi_tcp_r2tpool_free(cls_session->dd_data); iscsi_session_teardown(cls_session); diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 95d71e301a534..aecb563a2b4e3 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2945,6 +2945,24 @@ iscsi_set_path(struct iscsi_transport *transport, struct iscsi_uevent *ev) return err; }

+static int iscsi_session_has_conns(int sid) +{ + struct iscsi_cls_conn *conn; + unsigned long flags; + int found = 0; + + spin_lock_irqsave(&connlock, flags); + list_for_each_entry(conn, &connlist, conn_list) { + if (iscsi_conn_get_sid(conn) == sid) { + found = 1; + break; + } + } + spin_unlock_irqrestore(&connlock, flags); + + return found; +} + static int iscsi_set_iface_params(struct iscsi_transport *transport, struct iscsi_uevent *ev, uint32_t len) @@ -3522,10 +3540,12 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) break; case ISCSI_UEVENT_DESTROY_SESSION: session = iscsi_session_lookup(ev->u.d_session.sid); - if (session) - transport->destroy_session(session); - else + if (!session) err = -EINVAL; + else if (iscsi_session_has_conns(ev->u.d_session.sid)) + err = -EBUSY; + else + transport->destroy_session(session); break; case ISCSI_UEVENT_UNBIND_SESSION: session = iscsi_session_lookup(ev->u.d_session.sid);

From: Thomas Gleixner tglx@linutronix.de

[ Upstream commit 11e31f608b499f044f24b20be73f1dcab3e43f8a ]

Robert reported that during boot the watchdog timestamp is set to 0 for one second which is the indicator for a watchdog reset.

The reason for this is that the timestamp is in seconds and the time is taken from sched clock and divided by ~1e9. sched clock starts at 0 which means that for the first second during boot the watchdog timestamp is 0, i.e. reset.

Use ULONG_MAX as the reset indicator value so the watchdog works correctly right from the start. ULONG_MAX would only conflict with a real timestamp if the system reaches an uptime of 136 years on 32bit and almost eternity on 64bit.

Reported-by: Robert Richter rrichter@marvell.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://lore.kernel.org/r/87o8v3uuzl.fsf@nanos.tec.linutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/watchdog.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 087994b23f8b9..e4db5d54c07c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -164,6 +164,8 @@ static void lockup_detector_update_enable(void)

#ifdef CONFIG_SOFTLOCKUP_DETECTOR

+#define SOFTLOCKUP_RESET ULONG_MAX + /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; @@ -271,7 +273,7 @@ notrace void touch_softlockup_watchdog_sched(void) * Preemption can be enabled. It doesn't matter which CPU's timestamp * gets zeroed here, so use the raw_ operation. */ - raw_cpu_write(watchdog_touch_ts, 0); + raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); }

notrace void touch_softlockup_watchdog(void) @@ -295,14 +297,14 @@ void touch_all_softlockup_watchdogs(void) * the softlockup check. */ for_each_cpu(cpu, &watchdog_allowed_mask) - per_cpu(watchdog_touch_ts, cpu) = 0; + per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET; wq_watchdog_touch(-1); }

void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); - __this_cpu_write(watchdog_touch_ts, 0); + __this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); }

static int is_softlockup(unsigned long touch_ts) @@ -354,7 +356,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));

- if (touch_ts == 0) { + if (touch_ts == SOFTLOCKUP_RESET) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically

From: Ard Biesheuvel ardb@kernel.org

[ Upstream commit 75fbef0a8b6b4bb19b9a91b5214f846c2dc5139e ]

The following commit:

15f003d20782 ("x86/mm/pat: Don't implicitly allow _PAGE_RW in kernel_map_pages_in_pgd()")

modified kernel_map_pages_in_pgd() to manage writable permissions of memory mappings in the EFI page table in a different way, but in the process, it removed the ability to clear NX attributes from read-only mappings, by clobbering the clear mask if _PAGE_RW is not being requested.

Failure to remove the NX attribute from read-only mappings is unlikely to be a security issue, but it does prevent us from tightening the permissions in the EFI page tables going forward, so let's fix it now.

Fixes: 15f003d20782 ("x86/mm/pat: Don't implicitly allow _PAGE_RW in kernel_map_pages_in_pgd() Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/20200113172245.27925-5-ardb@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/mm/pageattr.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 835620ab435fd..eaee1a7ed0b50 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -2077,19 +2077,13 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(0), + .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)), .flags = 0, };

if (!(__supported_pte_mask & _PAGE_NX)) goto out;

- if (!(page_flags & _PAGE_NX)) - cpa.mask_clr = __pgprot(_PAGE_NX); - - if (!(page_flags & _PAGE_RW)) - cpa.mask_clr = __pgprot(_PAGE_RW); - if (!(page_flags & _PAGE_ENC)) cpa.mask_clr = pgprot_encrypted(cpa.mask_clr);

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit 117fcc3053606d8db5cef8821dca15022ae578bb ]

The "drive->dn" value is a u8 and it is controlled by root only, but it could be out of bounds here so let's check.

Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ide/cmd64x.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/ide/cmd64x.c b/drivers/ide/cmd64x.c index b127ed60c7336..9dde8390da09b 100644 --- a/drivers/ide/cmd64x.c +++ b/drivers/ide/cmd64x.c @@ -65,6 +65,9 @@ static void cmd64x_program_timings(ide_drive_t *drive, u8 mode) struct ide_timing t; u8 arttim = 0;

+ if (drive->dn >= ARRAY_SIZE(drwtim_regs)) + return; + ide_timing_compute(drive, mode, &t, T, 0);

/*

From: yu kuai yukuai3@huawei.com

[ Upstream commit 9871abffc81048e20f02e15d6aa4558a44ad53ea ]

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/pwm/pwm-pca9685.c: In function ‘pca9685_pwm_gpio_free’: drivers/pwm/pwm-pca9685.c:162:21: warning: variable ‘pwm’ set but not used [-Wunused-but-set-variable]

It is never used, and so can be removed. In that case, hold and release the lock 'pca->lock' can be removed since nothing will be done between them.

Fixes: e926b12c611c ("pwm: Clear chip_data in pwm_put()") Signed-off-by: yu kuai yukuai3@huawei.com Acked-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Thierry Reding thierry.reding@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pwm/pwm-pca9685.c | 4 ---- 1 file changed, 4 deletions(-)

diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c index 567f5e2771c47..e1e5dfcb16f36 100644 --- a/drivers/pwm/pwm-pca9685.c +++ b/drivers/pwm/pwm-pca9685.c @@ -170,13 +170,9 @@ static void pca9685_pwm_gpio_set(struct gpio_chip *gpio, unsigned int offset, static void pca9685_pwm_gpio_free(struct gpio_chip *gpio, unsigned int offset) { struct pca9685 *pca = gpiochip_get_data(gpio); - struct pwm_device *pwm;

pca9685_pwm_gpio_set(gpio, offset, 0); pm_runtime_put(pca->chip.dev); - mutex_lock(&pca->lock); - pwm = &pca->chip.pwms[offset]; - mutex_unlock(&pca->lock); }

static int pca9685_pwm_gpio_get_direction(struct gpio_chip *chip,

From: David Sterba dsterba@suse.com

[ Upstream commit 4babad10198fa73fe73239d02c2e99e3333f5f5c ]

Dan's smatch tool reports

fs/btrfs/file-item.c:295 btrfs_lookup_bio_sums() warn: should this be 'count == -1'

which points to the while (count--) loop. With count == 0 the check itself could decrement it to -1. There's a WARN_ON a few lines below that has never been seen in practice though.

It turns out that the value of page_bytes_left matches the count (by sectorsize multiples). The loop never reaches the state where count would go to -1, because page_bytes_left == 0 is found first and this breaks out.

For clarity, use only plain check on count (and only for positive value), decrement safely inside the loop. Any other discrepancy after the whole bio list processing should be reported by the exising WARN_ON_ONCE as well.

Reported-by: Dan Carpenter dan.carpenter@oracle.com Reviewed-by: Josef Bacik josef@toxicpanda.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/file-item.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 702b3606ad0ec..717d82d51bb13 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -288,7 +288,8 @@ found: csum += count * csum_size; nblocks -= count; next: - while (count--) { + while (count > 0) { + count--; disk_bytenr += fs_info->sectorsize; offset += fs_info->sectorsize; page_bytes_left -= fs_info->sectorsize;

From: Brandon Maier brandon.maier@rockwellcollins.com

[ Upstream commit a8f40111d184098cd2b3dc0c7170c42250a5fa09 ]

The remoteproc_core and remoteproc drivers all initialize with module_init(). However remoteproc drivers need the rproc_class during their probe. If one of the remoteproc drivers runs init and gets through probe before remoteproc_init() runs, a NULL pointer access of rproc_class's `glue_dirs` spinlock occurs.

Unable to handle kernel NULL pointer dereference at virtual address 000000dc pgd = c0004000 [000000dc] *pgd=00000000 Internal error: Oops: 5 [#1] PREEMPT ARM Modules linked in: CPU: 0 PID: 1 Comm: swapper Tainted: G W 4.14.106-rt56 #1 Hardware name: Generic OMAP36xx (Flattened Device Tree) task: c6050000 task.stack: c604a000 PC is at rt_spin_lock+0x40/0x6c LR is at rt_spin_lock+0x28/0x6c pc : [<c0523c90>] lr : [<c0523c78>] psr: 60000013 sp : c604bdc0 ip : 00000000 fp : 00000000 r10: 00000000 r9 : c61c7c10 r8 : c6269c20 r7 : c0905888 r6 : c6269c20 r5 : 00000000 r4 : 000000d4 r3 : 000000dc r2 : c6050000 r1 : 00000002 r0 : 000000d4 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none

...

[<c0523c90>] (rt_spin_lock) from [<c03b65a4>] (get_device_parent+0x54/0x17c) [<c03b65a4>] (get_device_parent) from [<c03b6bec>] (device_add+0xe0/0x5b4) [<c03b6bec>] (device_add) from [<c042adf4>] (rproc_add+0x18/0xd8) [<c042adf4>] (rproc_add) from [<c01110e4>] (my_rproc_probe+0x158/0x204) [<c01110e4>] (my_rproc_probe) from [<c03bb6b8>] (platform_drv_probe+0x34/0x70) [<c03bb6b8>] (platform_drv_probe) from [<c03b9dd4>] (driver_probe_device+0x2c8/0x420) [<c03b9dd4>] (driver_probe_device) from [<c03ba02c>] (__driver_attach+0x100/0x11c) [<c03ba02c>] (__driver_attach) from [<c03b7d08>] (bus_for_each_dev+0x7c/0xc0) [<c03b7d08>] (bus_for_each_dev) from [<c03b910c>] (bus_add_driver+0x1cc/0x264) [<c03b910c>] (bus_add_driver) from [<c03ba714>] (driver_register+0x78/0xf8) [<c03ba714>] (driver_register) from [<c010181c>] (do_one_initcall+0x100/0x190) [<c010181c>] (do_one_initcall) from [<c0800de8>] (kernel_init_freeable+0x130/0x1d0) [<c0800de8>] (kernel_init_freeable) from [<c051eee8>] (kernel_init+0x8/0x114) [<c051eee8>] (kernel_init) from [<c01175b0>] (ret_from_fork+0x14/0x24) Code: e2843008 e3c2203f f5d3f000 e5922010 (e193cf9f) ---[ end trace 0000000000000002 ]---

Signed-off-by: Brandon Maier brandon.maier@rockwellcollins.com Link: https://lore.kernel.org/r/20190530225223.136420-1-brandon.maier@rockwellcoll... Signed-off-by: Bjorn Andersson bjorn.andersson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/remoteproc/remoteproc_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index eab14b414bf0d..cc733b89560a1 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1620,7 +1620,7 @@ static int __init remoteproc_init(void)

return 0; } -module_init(remoteproc_init); +subsys_initcall(remoteproc_init);

static void __exit remoteproc_exit(void) {

From: Kai Vehmanen kai.vehmanen@linux.intel.com

[ Upstream commit 2928fa0a97ebb9549cb877fdc99aed9b95438c3a ]

The initial snd_hda_get_sub_node() can fail on certain devices (e.g. some Chromebook models using Intel GLK). The failure rate is very low, but as this is is part of the probe process, end-user impact is high.

In observed cases, related hardware status registers have expected values, but the node query still fails. Retrying the node query does seem to help, so fix the problem by adding retry logic to the query. This does not impact non-Intel platforms.

BugLink: https://github.com/thesofproject/linux/issues/1642 Signed-off-by: Kai Vehmanen kai.vehmanen@linux.intel.com Reviewed-by: Takashi Iwai tiwai@suse.de Link: https://lore.kernel.org/r/20200120160117.29130-4-kai.vehmanen@linux.intel.co... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/patch_hdmi.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index f214055972150..12913368c2314 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2574,9 +2574,12 @@ static int alloc_intel_hdmi(struct hda_codec *codec) /* parse and post-process for Intel codecs */ static int parse_intel_hdmi(struct hda_codec *codec) { - int err; + int err, retries = 3; + + do { + err = hdmi_parse_codec(codec); + } while (err < 0 && retries--);

- err = hdmi_parse_codec(codec); if (err < 0) { generic_spec_free(codec); return err;

From: Vasily Gorbik gor@linux.ibm.com

[ Upstream commit 45f7a0da600d3c409b5ad8d5ddddacd98ddc8840 ]

Currently backtrace from ftraced function does not contain ftraced function itself. e.g. for "path_openat":

arch_stack_walk+0x15c/0x2d8 stack_trace_save+0x50/0x68 stack_trace_call+0x15e/0x3d8 ftrace_graph_caller+0x0/0x1c <-- ftrace code do_filp_open+0x7c/0xe8 <-- ftraced function caller do_open_execat+0x76/0x1b8 open_exec+0x52/0x78 load_elf_binary+0x180/0x1160 search_binary_handler+0x8e/0x288 load_script+0x2a8/0x2b8 search_binary_handler+0x8e/0x288 __do_execve_file.isra.39+0x6fa/0xb40 __s390x_sys_execve+0x56/0x68 system_call+0xdc/0x2d8

Ftraced function is expected in the backtrace by ftrace kselftests, which are now failing. It would also be nice to have it for clarity reasons.

"ftrace_caller" itself is called without stack frame allocated for it and does not store its caller (ftraced function). Instead it simply allocates a stack frame for "ftrace_trace_function" and sets backchain to point to ftraced function stack frame (which contains ftraced function caller in saved r14).

To fix this issue make "ftrace_caller" allocate a stack frame for itself just to store ftraced function for the stack unwinder. As a result backtrace looks like the following:

arch_stack_walk+0x15c/0x2d8 stack_trace_save+0x50/0x68 stack_trace_call+0x15e/0x3d8 ftrace_graph_caller+0x0/0x1c <-- ftrace code path_openat+0x6/0xd60 <-- ftraced function do_filp_open+0x7c/0xe8 <-- ftraced function caller do_open_execat+0x76/0x1b8 open_exec+0x52/0x78 load_elf_binary+0x180/0x1160 search_binary_handler+0x8e/0x288 load_script+0x2a8/0x2b8 search_binary_handler+0x8e/0x288 __do_execve_file.isra.39+0x6fa/0xb40 __s390x_sys_execve+0x56/0x68 system_call+0xdc/0x2d8

Reported-by: Sven Schnelle sven.schnelle@ibm.com Tested-by: Sven Schnelle sven.schnelle@ibm.com Reviewed-by: Heiko Carstens heiko.carstens@de.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kernel/mcount.S | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 27110f3294edc..0cfd5a83a1daa 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -25,6 +25,12 @@ ENTRY(ftrace_stub) #define STACK_PTREGS (STACK_FRAME_OVERHEAD) #define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) #define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) +#ifdef __PACK_STACK +/* allocate just enough for r14, r15 and backchain */ +#define TRACED_FUNC_FRAME_SIZE 24 +#else +#define TRACED_FUNC_FRAME_SIZE STACK_FRAME_OVERHEAD +#endif

ENTRY(_mcount) BR_EX %r14 @@ -38,9 +44,16 @@ ENTRY(ftrace_caller) #ifndef CC_USING_HOTPATCH aghi %r0,MCOUNT_RETURN_FIXUP #endif - aghi %r15,-STACK_FRAME_SIZE + # allocate stack frame for ftrace_caller to contain traced function + aghi %r15,-TRACED_FUNC_FRAME_SIZE stg %r1,__SF_BACKCHAIN(%r15) + stg %r0,(__SF_GPRS+8*8)(%r15) + stg %r15,(__SF_GPRS+9*8)(%r15) + # allocate pt_regs and stack frame for ftrace_trace_function + aghi %r15,-STACK_FRAME_SIZE stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15) + aghi %r1,-TRACED_FUNC_FRAME_SIZE + stg %r1,__SF_BACKCHAIN(%r15) stg %r0,(STACK_PTREGS_PSW+8)(%r15) stmg %r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15) #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES

From: Peter Große pegro@friiks.de

[ Upstream commit ef7d84caa5928b40b1c93a26dbe5a3f12737c6ab ]

Lenovo Thinkpad T420s uses the same codec as T420, so apply the same quirk to enable audio output on a docking station.

Signed-off-by: Peter Große pegro@friiks.de Link: https://lore.kernel.org/r/20200122180106.9351-1-pegro@friiks.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/patch_conexant.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 382b6d2ed8036..9cc9304ff21a7 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -969,6 +969,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x17aa, 0x215f, "Lenovo T510", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21ce, "Lenovo T420", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21cf, "Lenovo T520", CXT_PINCFG_LENOVO_TP410), + SND_PCI_QUIRK(0x17aa, 0x21d2, "Lenovo T420s", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21da, "Lenovo X220", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21db, "Lenovo X220-tablet", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo IdeaPad Z560", CXT_FIXUP_MUTE_LED_EAPD),

From: zhangyi (F) yi.zhang@huawei.com

[ Upstream commit d0a186e0d3e7ac05cc77da7c157dae5aa59f95d9 ]

We invoke jbd2_journal_abort() to abort the journal and record errno in the jbd2 superblock when committing journal transaction besides the failure on submitting the commit record. But there is no need for the case and we can also invoke jbd2_journal_abort() instead of __jbd2_journal_abort_hard().

Fixes: 818d276ceb83a ("ext4: Add the journal checksum feature") Signed-off-by: zhangyi (F) yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20191204124614.45424-2-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jbd2/commit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index cb0da3d4adc04..1a4bd8d9636e8 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -783,7 +783,7 @@ start_journal_io: err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); }

blk_finish_plug(&plug); @@ -876,7 +876,7 @@ start_journal_io: err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); } if (cbh) err = journal_wait_on_commit_record(journal, cbh);

From: Vincenzo Frascino vincenzo.frascino@arm.com

[ Upstream commit 76950f7162cad51d2200ebd22c620c14af38f718 ]

To perform the reserve_crashkernel() operation kexec uses SECTION_SIZE to find a memblock in a range. SECTION_SIZE is not defined for nommu systems. Trying to compile kexec in these conditions results in a build error:

linux/arch/arm/kernel/setup.c: In function ‘reserve_crashkernel’: linux/arch/arm/kernel/setup.c:1016:25: error: ‘SECTION_SIZE’ undeclared (first use in this function); did you mean ‘SECTIONS_WIDTH’? crash_size, SECTION_SIZE); ^~~~~~~~~~~~ SECTIONS_WIDTH linux/arch/arm/kernel/setup.c:1016:25: note: each undeclared identifier is reported only once for each function it appears in linux/scripts/Makefile.build:265: recipe for target 'arch/arm/kernel/setup.o' failed

Make KEXEC depend on MMU to fix the compilation issue.

Signed-off-by: Vincenzo Frascino vincenzo.frascino@arm.com Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index ba9325fc75b85..7a8fbe9a077bb 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2005,7 +2005,7 @@ config XIP_PHYS_ADDR config KEXEC bool "Kexec system call (EXPERIMENTAL)" depends on (!SMP || PM_SLEEP_SMP) - depends on !CPU_V7M + depends on MMU select KEXEC_CORE help kexec is a system call that implements the ability to shutdown your

From: Colin Ian King colin.king@canonical.com

[ Upstream commit c2f9a4e4a5abfc84c01b738496b3fd2d471e0b18 ]

The loop counter addr is a u16 where as the upper limit of the loop is an int. In the unlikely event that the il->cfg->eeprom_size is greater than 64K then we end up with an infinite loop since addr will wrap around an never reach upper loop limit. Fix this by making addr an int.

Addresses-Coverity: ("Infinite loop") Fixes: be663ab67077 ("iwlwifi: split the drivers for agn and legacy devices 3945/4965") Signed-off-by: Colin Ian King colin.king@canonical.com Acked-by: Stanislaw Gruszka stf_xl@wp.pl Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlegacy/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c index 8d5acda92a9b8..6e6b124f0d5e3 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.c +++ b/drivers/net/wireless/intel/iwlegacy/common.c @@ -717,7 +717,7 @@ il_eeprom_init(struct il_priv *il) u32 gp = _il_rd(il, CSR_EEPROM_GP); int sz; int ret; - u16 addr; + int addr;

/* allocate eeprom */ sz = il->cfg->eeprom_size;

From: Xiubo Li xiubli@redhat.com

[ Upstream commit 97820058fb2831a4b203981fa2566ceaaa396103 ]

If all the MDS daemons are down for some reason, then the first mount attempt will fail with EIO after the mount request times out. A mount attempt will also fail with EIO if all of the MDS's are laggy.

This patch changes the code to return -EHOSTUNREACH in these situations and adds a pr_info error message to help the admin determine the cause.

URL: https://tracker.ceph.com/issues/4386 Signed-off-by: Xiubo Li xiubli@redhat.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ceph/mds_client.c | 3 +-- fs/ceph/super.c | 5 +++++ 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index b968334f841e8..f36ddfea4997e 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2261,8 +2261,7 @@ static int __do_request(struct ceph_mds_client *mdsc, if (!(mdsc->fsc->mount_options->flags & CEPH_MOUNT_OPT_MOUNTWAIT) && !ceph_mdsmap_is_cluster_available(mdsc->mdsmap)) { - err = -ENOENT; - pr_info("probably no mds server is up\n"); + err = -EHOSTUNREACH; goto finish; } } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 088c4488b4492..6b10b20bfe32b 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1055,6 +1055,11 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, return res;

out_splat: + if (!ceph_mdsmap_is_cluster_available(fsc->mdsc->mdsmap)) { + pr_info("No mds server is up or the cluster is laggy\n"); + err = -EHOSTUNREACH; + } + ceph_mdsc_close_sessions(fsc->mdsc); deactivate_locked_super(sb); goto out_final;

From: Ben Skeggs bskeggs@redhat.com

[ Upstream commit 0e6176c6d286316e9431b4f695940cfac4ffe6c2 ]

The implementations for most channel types contains a map of methods to priv registers in order to provide debugging info when a disp exception has been raised.

This info is missing from the implementation of PIO channels as they're rather simplistic already, however, if an exception is raised by one of them, we'd end up triggering a NULL-pointer deref. Not ideal...

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=206299 Signed-off-by: Ben Skeggs bskeggs@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c index 0c0310498afdb..cd9666583d4bd 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c @@ -73,6 +73,8 @@ nv50_disp_chan_mthd(struct nv50_disp_chan *chan, int debug)

if (debug > subdev->debug) return; + if (!mthd) + return;

for (i = 0; (list = mthd->data[i].mthd) != NULL; i++) { u32 base = chan->head * mthd->addr;

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit 6722b23e7a2ace078344064a9735fb73e554e9ef ]

if seq_file .next fuction does not change position index, read after some lseek can generate unexpected output.

Without patch: # dd bs=30 skip=1 if=/sys/kernel/tracing/events/sched/sched_switch/trigger dd: /sys/kernel/tracing/events/sched/sched_switch/trigger: cannot skip to specified offset n traceoff snapshot stacktrace enable_event disable_event enable_hist disable_hist hist # Available triggers: # traceon traceoff snapshot stacktrace enable_event disable_event enable_hist disable_hist hist 6+1 records in 6+1 records out 206 bytes copied, 0.00027916 s, 738 kB/s

Notice the printing of "# Available triggers:..." after the line.

With the patch: # dd bs=30 skip=1 if=/sys/kernel/tracing/events/sched/sched_switch/trigger dd: /sys/kernel/tracing/events/sched/sched_switch/trigger: cannot skip to specified offset n traceoff snapshot stacktrace enable_event disable_event enable_hist disable_hist hist 2+1 records in 2+1 records out 88 bytes copied, 0.000526867 s, 167 kB/s

It only prints the end of the file, and does not restart.

Link: http://lkml.kernel.org/r/3c35ee24-dd3a-8119-9c19-552ed253388a@virtuozzo.com

https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin vvs@virtuozzo.com Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/trace/trace_events_trigger.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index e2da180ca172a..31e91efe243e5 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -127,9 +127,10 @@ static void *trigger_next(struct seq_file *m, void *t, loff_t *pos) { struct trace_event_file *event_file = event_file_data(m->private);

- if (t == SHOW_AVAILABLE_TRIGGERS) + if (t == SHOW_AVAILABLE_TRIGGERS) { + (*pos)++; return NULL; - + } return seq_list_next(t, &event_file->triggers, pos); }

From: wangyan wangyan122@huawei.com

[ Upstream commit 9f16ca48fc818a17de8be1f75d08e7f4addc4497 ]

I found a NULL pointer dereference in ocfs2_update_inode_fsync_trans(), handle->h_transaction may be NULL in this situation:

ocfs2_file_write_iter ->__generic_file_write_iter ->generic_perform_write ->ocfs2_write_begin ->ocfs2_write_begin_nolock ->ocfs2_write_cluster_by_desc ->ocfs2_write_cluster ->ocfs2_mark_extent_written ->ocfs2_change_extent_flag ->ocfs2_split_extent ->ocfs2_try_to_merge_extent ->ocfs2_extend_rotate_transaction ->ocfs2_extend_trans ->jbd2_journal_restart ->jbd2__journal_restart // handle->h_transaction is NULL here ->handle->h_transaction = NULL; ->start_this_handle /* journal aborted due to storage network disconnection, return error */ ->return -EROFS; /* line 3806 in ocfs2_try_to_merge_extent (), it will ignore ret error. */ ->ret = 0; ->... ->ocfs2_write_end ->ocfs2_write_end_nolock ->ocfs2_update_inode_fsync_trans // NULL pointer dereference ->oi->i_sync_tid = handle->h_transaction->t_tid;

The information of NULL pointer dereference as follows: JBD2: Detected IO errors while flushing file data on dm-11-45 Aborting journal on device dm-11-45. JBD2: Error -5 detected when updating journal superblock for dm-11-45. (dd,22081,3):ocfs2_extend_trans:474 ERROR: status = -30 (dd,22081,3):ocfs2_try_to_merge_extent:3877 ERROR: status = -30 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008 Mem abort info: ESR = 0x96000004 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000e74e1338 [0000000000000008] pgd=0000000000000000 Internal error: Oops: 96000004 [#1] SMP Process dd (pid: 22081, stack limit = 0x00000000584f35a9) CPU: 3 PID: 22081 Comm: dd Kdump: loaded Hardware name: Huawei TaiShan 2280 V2/BC82AMDD, BIOS 0.98 08/25/2019 pstate: 60400009 (nZCv daif +PAN -UAO) pc : ocfs2_write_end_nolock+0x2b8/0x550 [ocfs2] lr : ocfs2_write_end_nolock+0x2a0/0x550 [ocfs2] sp : ffff0000459fba70 x29: ffff0000459fba70 x28: 0000000000000000 x27: ffff807ccf7f1000 x26: 0000000000000001 x25: ffff807bdff57970 x24: ffff807caf1d4000 x23: ffff807cc79e9000 x22: 0000000000001000 x21: 000000006c6cd000 x20: ffff0000091d9000 x19: ffff807ccb239db0 x18: ffffffffffffffff x17: 000000000000000e x16: 0000000000000007 x15: ffff807c5e15bd78 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000001 x9 : 0000000000000228 x8 : 000000000000000c x7 : 0000000000000fff x6 : ffff807a308ed6b0 x5 : ffff7e01f10967c0 x4 : 0000000000000018 x3 : d0bc661572445600 x2 : 0000000000000000 x1 : 000000001b2e0200 x0 : 0000000000000000 Call trace: ocfs2_write_end_nolock+0x2b8/0x550 [ocfs2] ocfs2_write_end+0x4c/0x80 [ocfs2] generic_perform_write+0x108/0x1a8 __generic_file_write_iter+0x158/0x1c8 ocfs2_file_write_iter+0x668/0x950 [ocfs2] __vfs_write+0x11c/0x190 vfs_write+0xac/0x1c0 ksys_write+0x6c/0xd8 __arm64_sys_write+0x24/0x30 el0_svc_common+0x78/0x130 el0_svc_handler+0x38/0x78 el0_svc+0x8/0xc

To prevent NULL pointer dereference in this situation, we use is_handle_aborted() before using handle->h_transaction->t_tid.

Link: http://lkml.kernel.org/r/03e750ab-9ade-83aa-b000-b9e81e34e539@huawei.com Signed-off-by: Yan Wang wangyan122@huawei.com Reviewed-by: Jun Piao piaojun@huawei.com Cc: Mark Fasheh mark@fasheh.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Cc: Joseph Qi jiangqi903@gmail.com Cc: Changwei Ge gechangwei@live.cn Cc: Gang He ghe@suse.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ocfs2/journal.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 497a4171ef61f..bfb50fc51528f 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -637,9 +637,11 @@ static inline void ocfs2_update_inode_fsync_trans(handle_t *handle, { struct ocfs2_inode_info *oi = OCFS2_I(inode);

- oi->i_sync_tid = handle->h_transaction->t_tid; - if (datasync) - oi->i_datasync_tid = handle->h_transaction->t_tid; + if (!is_handle_aborted(handle)) { + oi->i_sync_tid = handle->h_transaction->t_tid; + if (datasync) + oi->i_datasync_tid = handle->h_transaction->t_tid; + } }

#endif /* OCFS2_JOURNAL_H */