[PATCH AUTOSEL 6.1 01/16] crypto: hisilicon/hpre - fix resource leak in remove process

[PATCH AUTOSEL 6.1 01/16] crypto: hisilicon/hpre - fix resource leak in remove process

[Sasha Levin]

From: Zhiqi Song <songzhiqi1@huawei.com>

[ Upstream commit 45e6319bd5f2154d8b8c9f1eaa4ac030ba0d330c ]

In hpre_remove(), when the disable operation of qm sriov failed,
the following logic should continue to be executed to release the
remaining resources that have been allocated, instead of returning
directly, otherwise there will be resource leakage.

Signed-off-by: Zhiqi Song <songzhiqi1@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/crypto/hisilicon/hpre/hpre_main.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
index 471e5ca720f5..baf1faec7046 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_main.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_main.c
@@ -1437,18 +1437,12 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 static void hpre_remove(struct pci_dev *pdev)
 {
 	struct hisi_qm *qm = pci_get_drvdata(pdev);
-	int ret;
 
 	hisi_qm_pm_uninit(qm);
 	hisi_qm_wait_task_finish(qm, &hpre_devices);
 	hisi_qm_alg_unregister(qm, &hpre_devices);
-	if (qm->fun_type == QM_HW_PF && qm->vfs_num) {
-		ret = hisi_qm_sriov_disable(pdev, true);
-		if (ret) {
-			pci_err(pdev, "Disable SRIOV fail!\n");
-			return;
-		}
-	}
+	if (qm->fun_type == QM_HW_PF && qm->vfs_num)
+		hisi_qm_sriov_disable(pdev, true);
 
 	hpre_debugfs_exit(qm);
 	hisi_qm_stop(qm, QM_NORMAL);
-- 
2.35.1

[PATCH AUTOSEL 6.1 02/16] scsi: lpfc: Fix hard lockup when reading the rx_monitor from debugfs

[Sasha Levin]

From: Justin Tee <justin.tee@broadcom.com>

[ Upstream commit c44e50f4a0ec00c2298f31f91bc2c3e9bbd81c7e ]

During I/O and simultaneous cat of /sys/kernel/debug/lpfc/fnX/rx_monitor, a
hard lockup similar to the call trace below may occur.

The spin_lock_bh in lpfc_rx_monitor_report is not protecting from timer
interrupts as expected, so change the strength of the spin lock to _irq.

Kernel panic - not syncing: Hard LOCKUP
CPU: 3 PID: 110402 Comm: cat Kdump: loaded

exception RIP: native_queued_spin_lock_slowpath+91

[IRQ stack]
 native_queued_spin_lock_slowpath at ffffffffb814e30b
 _raw_spin_lock at ffffffffb89a667a
 lpfc_rx_monitor_record at ffffffffc0a73a36 [lpfc]
 lpfc_cmf_timer at ffffffffc0abbc67 [lpfc]
 __hrtimer_run_queues at ffffffffb8184250
 hrtimer_interrupt at ffffffffb8184ab0
 smp_apic_timer_interrupt at ffffffffb8a026ba
 apic_timer_interrupt at ffffffffb8a01c4f
[End of IRQ stack]

 apic_timer_interrupt at ffffffffb8a01c4f
 lpfc_rx_monitor_report at ffffffffc0a73c80 [lpfc]
 lpfc_rx_monitor_read at ffffffffc0addde1 [lpfc]
 full_proxy_read at ffffffffb83e7fc3
 vfs_read at ffffffffb833fe71
 ksys_read at ffffffffb83402af
 do_syscall_64 at ffffffffb800430b
 entry_SYSCALL_64_after_hwframe at ffffffffb8a000ad

Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Link: https://lore.kernel.org/r/20221017164323.14536-2-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_sli.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 99d06dc7ddf6..21c52154626f 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -8150,10 +8150,10 @@ u32 lpfc_rx_monitor_report(struct lpfc_hba *phba,
 					"IO_cnt", "Info", "BWutil(ms)");
 	}
 
-	/* Needs to be _bh because record is called from timer interrupt
+	/* Needs to be _irq because record is called from timer interrupt
 	 * context
 	 */
-	spin_lock_bh(ring_lock);
+	spin_lock_irq(ring_lock);
 	while (*head_idx != *tail_idx) {
 		entry = &ring[*head_idx];
 
@@ -8197,7 +8197,7 @@ u32 lpfc_rx_monitor_report(struct lpfc_hba *phba,
 		if (cnt >= max_read_entries)
 			break;
 	}
-	spin_unlock_bh(ring_lock);
+	spin_unlock_irq(ring_lock);
 
 	return cnt;
 }
-- 
2.35.1

[PATCH AUTOSEL 6.1 03/16] scsi: ufs: Reduce the START STOP UNIT timeout

[Sasha Levin]

From: Bart Van Assche <bvanassche@acm.org>

[ Upstream commit dcd5b7637c6d442d957f73780a03047413ed3a10 ]

Reduce the START STOP UNIT command timeout to one second since on Android
devices a kernel panic is triggered if an attempt to suspend the system
takes more than 20 seconds. One second should be enough for the START STOP
UNIT command since this command completes in less than a millisecond for
the UFS devices I have access to.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20221018202958.1902564-7-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/ufs/core/ufshcd.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index b1f59a5fe632..bcc4b8a3c3bc 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8747,8 +8747,6 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	struct scsi_device *sdp;
 	unsigned long flags;
 	int ret, retries;
-	unsigned long deadline;
-	int32_t remaining;
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	sdp = hba->ufs_device_wlun;
@@ -8781,14 +8779,9 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	 * callbacks hence set the RQF_PM flag so that it doesn't resume the
 	 * already suspended childs.
 	 */
-	deadline = jiffies + 10 * HZ;
 	for (retries = 3; retries > 0; --retries) {
-		ret = -ETIMEDOUT;
-		remaining = deadline - jiffies;
-		if (remaining <= 0)
-			break;
 		ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
-				   remaining / HZ, 0, 0, RQF_PM, NULL);
+				   HZ, 0, 0, RQF_PM, NULL);
 		if (!scsi_status_is_check_condition(ret) ||
 				!scsi_sense_valid(&sshdr) ||
 				sshdr.sense_key != UNIT_ATTENTION)
-- 
2.35.1

[PATCH AUTOSEL 6.1 04/16] crypto: hisilicon/qm - increase the memory of local variables

[Sasha Levin]

From: Kai Ye <yekai13@huawei.com>

[ Upstream commit 3efe90af4c0c46c58dba1b306de142827153d9c0 ]

Increase the buffer to prevent stack overflow by fuzz test. The maximum
length of the qos configuration buffer is 256 bytes. Currently, the value
of the 'val buffer' is only 32 bytes. The sscanf does not check the dest
memory length. So the 'val buffer' may stack overflow.

Signed-off-by: Kai Ye <yekai13@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/crypto/hisilicon/qm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 8b387de69d22..335e58018a31 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -250,7 +250,6 @@
 #define QM_QOS_MIN_CIR_B		100
 #define QM_QOS_MAX_CIR_U		6
 #define QM_QOS_MAX_CIR_S		11
-#define QM_QOS_VAL_MAX_LEN		32
 #define QM_DFX_BASE		0x0100000
 #define QM_DFX_STATE1		0x0104000
 #define QM_DFX_STATE2		0x01040C8
@@ -4614,7 +4613,7 @@ static ssize_t qm_get_qos_value(struct hisi_qm *qm, const char *buf,
 			       unsigned int *fun_index)
 {
 	char tbuf_bdf[QM_DBG_READ_LEN] = {0};
-	char val_buf[QM_QOS_VAL_MAX_LEN] = {0};
+	char val_buf[QM_DBG_READ_LEN] = {0};
 	u32 tmp1, device, function;
 	int ret, bus;
 
-- 
2.35.1

[PATCH AUTOSEL 6.1 05/16] Revert "PCI: Clear PCI_STATUS when setting up device"

[Sasha Levin]

From: Bjorn Helgaas <bhelgaas@google.com>

[ Upstream commit 44e985938e85503d0a69ec538e15fd33c1a4df05 ]

This reverts commit 6cd514e58f12b211d638dbf6f791fa18d854f09c.

Christophe Fergeau reported that 6cd514e58f12 ("PCI: Clear PCI_STATUS when
setting up device") causes boot failures when trying to start linux guests
with Apple's virtualization framework (for example using
https://developer.apple.com/documentation/virtualization/running_linux_in_a_virtual_machine?language=objc)

6cd514e58f12 only solved a cosmetic problem, so revert it to fix the boot
failures.

Link: https://bugzilla.redhat.com/show_bug.cgi?id=2137803
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pci/probe.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index b66fa42c4b1f..1d6f7b502020 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1891,9 +1891,6 @@ int pci_setup_device(struct pci_dev *dev)
 
 	dev->broken_intx_masking = pci_intx_mask_broken(dev);
 
-	/* Clear errors left from system firmware */
-	pci_write_config_word(dev, PCI_STATUS, 0xffff);
-
 	switch (dev->hdr_type) {		    /* header type */
 	case PCI_HEADER_TYPE_NORMAL:		    /* standard header */
 		if (class == PCI_CLASS_BRIDGE_PCI)
-- 
2.35.1

[PATCH AUTOSEL 6.1 06/16] scsi: elx: libefc: Fix second parameter type in state callbacks

[Sasha Levin]

From: Nathan Chancellor <nathan@kernel.org>

[ Upstream commit 3d75e766b58a7410d4e835c534e1b4664a8f62d0 ]

With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG),
indirect call targets are validated against the expected function pointer
prototype to make sure the call target is valid to help mitigate ROP
attacks. If they are not identical, there is a failure at run time, which
manifests as either a kernel panic or thread getting killed. A proposed
warning in clang aims to catch these at compile time, which reveals:

  drivers/scsi/elx/libefc/efc_node.c:811:22: error: incompatible function pointer types assigning to 'void (*)(struct efc_sm_ctx *, u32, void *)' (aka 'void (*)(struct efc_sm_ctx *, unsigned int, void *)') from 'void (*)(struct efc_sm_ctx *, enum efc_sm_event, void *)' [-Werror,-Wincompatible-function-pointer-types-strict]
                  ctx->current_state = state;
                                    ^ ~~~~~
  drivers/scsi/elx/libefc/efc_node.c:878:21: error: incompatible function pointer types assigning to 'void (*)(struct efc_sm_ctx *, u32, void *)' (aka 'void (*)(struct efc_sm_ctx *, unsigned int, void *)') from 'void (*)(struct efc_sm_ctx *, enum efc_sm_event, void *)' [-Werror,-Wincompatible-function-pointer-types-strict]
          node->nodedb_state = state;
                            ^ ~~~~~
  drivers/scsi/elx/libefc/efc_node.c:905:6: error: incompatible function pointer types assigning to 'void (*)(struct efc_sm_ctx *, enum efc_sm_event, void *)' from 'void (*)(struct efc_sm_ctx *, u32, void *)' (aka 'void (*)(struct efc_sm_ctx *, unsigned int, void *)') [-Werror,-Wincompatible-function-pointer-types-strict]
                  pf = node->nodedb_state;
                    ^ ~~~~~~~~~~~~~~~~~~

  drivers/scsi/elx/libefc/efc_device.c:455:22: error: incompatible function pointer types assigning to 'void (*)(struct efc_sm_ctx *, u32, void *)' (aka 'void (*)(struct efc_sm_ctx *, unsigned int, void *)') from 'void (struct efc_sm_ctx *, enum efc_sm_event, void *)' [-Werror,-Wincompatible-function-pointer-types-strict]
                  node->nodedb_state = __efc_d_init;
                                    ^ ~~~~~~~~~~~~

  drivers/scsi/elx/libefc/efc_sm.c:41:22: error: incompatible function pointer types assigning to 'void (*)(struct efc_sm_ctx *, u32, void *)' (aka 'void (*)(struct efc_sm_ctx *, unsigned int, void *)') from 'void (*)(struct efc_sm_ctx *, enum efc_sm_event, void *)' [-Werror,-Wincompatible-function-pointer-types-strict]
                  ctx->current_state = state;
                                    ^ ~~~~~

The type of the second parameter in the prototypes of ->current_state() and
->nodedb_state() ('u32') does not match the implementations, which have a
second parameter type of 'enum efc_sm_event'. Update the prototypes to have
the correct second parameter type, clearing up all the warnings and CFI
failures.

Link: https://github.com/ClangBuiltLinux/linux/issues/1750
Reported-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20221102161906.2781508-1-nathan@kernel.org
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/elx/libefc/efclib.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/elx/libefc/efclib.h b/drivers/scsi/elx/libefc/efclib.h
index dde20891c2dd..57e338612812 100644
--- a/drivers/scsi/elx/libefc/efclib.h
+++ b/drivers/scsi/elx/libefc/efclib.h
@@ -58,10 +58,12 @@ enum efc_node_send_ls_acc {
 #define EFC_LINK_STATUS_UP		0
 #define EFC_LINK_STATUS_DOWN		1
 
+enum efc_sm_event;
+
 /* State machine context header  */
 struct efc_sm_ctx {
 	void (*current_state)(struct efc_sm_ctx *ctx,
-			      u32 evt, void *arg);
+			      enum efc_sm_event evt, void *arg);
 
 	const char	*description;
 	void		*app;
@@ -365,7 +367,7 @@ struct efc_node {
 	int			prev_evt;
 
 	void (*nodedb_state)(struct efc_sm_ctx *ctx,
-			     u32 evt, void *arg);
+			     enum efc_sm_event evt, void *arg);
 	struct timer_list	gidpt_delay_timer;
 	u64			time_last_gidpt_msec;
 
-- 
2.35.1

[PATCH AUTOSEL 6.1 07/16] hugetlbfs: fix null-ptr-deref in hugetlbfs_parse_param()

[Sasha Levin]

From: Hawkins Jiawei <yin31149@gmail.com>

[ Upstream commit 26215b7ee923b9251f7bb12c4e5f09dc465d35f2 ]

Syzkaller reports a null-ptr-deref bug as follows:
======================================================
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:hugetlbfs_parse_param+0x1dd/0x8e0 fs/hugetlbfs/inode.c:1380
[...]
Call Trace:
 <TASK>
 vfs_parse_fs_param fs/fs_context.c:148 [inline]
 vfs_parse_fs_param+0x1f9/0x3c0 fs/fs_context.c:129
 vfs_parse_fs_string+0xdb/0x170 fs/fs_context.c:191
 generic_parse_monolithic+0x16f/0x1f0 fs/fs_context.c:231
 do_new_mount fs/namespace.c:3036 [inline]
 path_mount+0x12de/0x1e20 fs/namespace.c:3370
 do_mount fs/namespace.c:3383 [inline]
 __do_sys_mount fs/namespace.c:3591 [inline]
 __se_sys_mount fs/namespace.c:3568 [inline]
 __x64_sys_mount+0x27f/0x300 fs/namespace.c:3568
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
 [...]
 </TASK>
======================================================

According to commit "vfs: parse: deal with zero length string value",
kernel will set the param->string to null pointer in vfs_parse_fs_string()
if fs string has zero length.

Yet the problem is that, hugetlbfs_parse_param() will dereference the
param->string, without checking whether it is a null pointer.  To be more
specific, if hugetlbfs_parse_param() parses an illegal mount parameter,
such as "size=,", kernel will constructs struct fs_parameter with null
pointer in vfs_parse_fs_string(), then passes this struct fs_parameter to
hugetlbfs_parse_param(), which triggers the above null-ptr-deref bug.

This patch solves it by adding sanity check on param->string
in hugetlbfs_parse_param().

Link: https://lkml.kernel.org/r/20221020231609.4810-1-yin31149@gmail.com
Reported-by: syzbot+a3e6acd85ded5c16a709@syzkaller.appspotmail.com
Tested-by: syzbot+a3e6acd85ded5c16a709@syzkaller.appspotmail.com
  Link: https://lore.kernel.org/all/0000000000005ad00405eb7148c6@google.com/
Signed-off-by: Hawkins Jiawei <yin31149@gmail.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Hawkins Jiawei <yin31149@gmail.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Ian Kent <raven@themaw.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/hugetlbfs/inode.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index df7772335dc0..8eea709e3659 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1377,7 +1377,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	case Opt_size:
 		/* memparse() will accept a K/M/G without a digit */
-		if (!isdigit(param->string[0]))
+		if (!param->string || !isdigit(param->string[0]))
 			goto bad_val;
 		ctx->max_size_opt = memparse(param->string, &rest);
 		ctx->max_val_type = SIZE_STD;
@@ -1387,7 +1387,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	case Opt_nr_inodes:
 		/* memparse() will accept a K/M/G without a digit */
-		if (!isdigit(param->string[0]))
+		if (!param->string || !isdigit(param->string[0]))
 			goto bad_val;
 		ctx->nr_inodes = memparse(param->string, &rest);
 		return 0;
@@ -1403,7 +1403,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par
 
 	case Opt_min_size:
 		/* memparse() will accept a K/M/G without a digit */
-		if (!isdigit(param->string[0]))
+		if (!param->string || !isdigit(param->string[0]))
 			goto bad_val;
 		ctx->min_size_opt = memparse(param->string, &rest);
 		ctx->min_val_type = SIZE_STD;
-- 
2.35.1

[PATCH AUTOSEL 6.1 08/16] scsi: smartpqi: Add new controller PCI IDs

[Sasha Levin]

From: Mike McGowen <mike.mcgowen@microchip.com>

[ Upstream commit 0b93cf2a9097b1c3d75642ef878ba87f15f03043 ]

All PCI ID entries in Hex.
Add PCI IDs for ByteDance controllers:
                                            VID  / DID  / SVID / SDID
                                            ----   ----   ----   ----
    ByteHBA JGH43024-8                      9005 / 028f / 1e93 / 1000
    ByteHBA JGH43034-8                      9005 / 028f / 1e93 / 1001
    ByteHBA JGH44014-8                      9005 / 028f / 1e93 / 1002

Add PCI IDs for new Inspur controllers:
                                            VID  / DID  / SVID / SDID
                                            ----   ----   ----   ----
    INSPUR RT0800M7E                        9005 / 028f / 1bd4 / 0086
    INSPUR RT0800M7H                        9005 / 028f / 1bd4 / 0087
    INSPUR RT0804M7R                        9005 / 028f / 1bd4 / 0088
    INSPUR RT0808M7R                        9005 / 028f / 1bd4 / 0089

Add PCI IDs for new FAB A controllers:
                                            VID  / DID  / SVID / SDID
                                            ----   ----   ----   ----
    Adaptec SmartRAID 3254-16e /e           9005 / 028f / 9005 / 1475
    Adaptec HBA 1200-16e                    9005 / 028f / 9005 / 14c3
    Adaptec HBA 1200-8e                     9005 / 028f / 9005 / 14c4

Add H3C controller PCI IDs:
                                            VID  / DID  / SVID / SDID
                                            ----   ----   ----   ----
    H3C H4508-Mf-8i                         9005 / 028f / 193d / 110b

Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Signed-off-by: Mike McGowen <mike.mcgowen@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/166793530327.322537.6056884426657539311.stgit@brunhilda
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 44 +++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index b971fbe3b3a1..78fc743f46e4 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -9302,6 +9302,10 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x193d, 0x1109)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x193d, 0x110b)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x193d, 0x8460)
@@ -9402,6 +9406,22 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x1bd4, 0x0072)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x0086)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x0087)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x0088)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x0089)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x19e5, 0xd227)
@@ -9650,6 +9670,10 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADAPTEC2, 0x1474)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_ADAPTEC2, 0x1475)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADAPTEC2, 0x1480)
@@ -9706,6 +9730,14 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADAPTEC2, 0x14c2)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_ADAPTEC2, 0x14c3)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_ADAPTEC2, 0x14c4)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADAPTEC2, 0x14d0)
@@ -9942,6 +9974,18 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_LENOVO, 0x0623)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+				0x1e93, 0x1000)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+				0x1e93, 0x1001)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+				0x1e93, 0x1002)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_ANY_ID, PCI_ANY_ID)
-- 
2.35.1

[PATCH AUTOSEL 6.1 09/16] scsi: smartpqi: Correct device removal for multi-actuator devices

[Sasha Levin]

From: Kumar Meiyappan <Kumar.Meiyappan@microchip.com>

[ Upstream commit cc9befcbbb5ebce77726f938508700d913530035 ]

Correct device count for multi-actuator drives which can cause kernel
panics.

Reviewed-by: Scott Benesh <scott.benesh@microchip.com>
Reviewed-by: Scott Teel <scott.teel@microchip.com>
Reviewed-by: Mike Mcgowan <mike.mcgowan@microchip.com>
Reviewed-by: Kevin Barnett <kevin.barnett@microchip.com>
Signed-off-by: Kumar Meiyappan <Kumar.Meiyappan@microchip.com>
Signed-off-by: Don Brace <don.brace@microchip.com>
Link: https://lore.kernel.org/r/166793531872.322537.9003385780343419275.stgit@brunhilda
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/smartpqi/smartpqi.h      |  2 +-
 drivers/scsi/smartpqi/smartpqi_init.c | 33 +++++++++++++++++++--------
 2 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index e550b12e525a..c8235f15728b 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -1130,7 +1130,7 @@ struct pqi_scsi_dev {
 	u8	phy_id;
 	u8	ncq_prio_enable;
 	u8	ncq_prio_support;
-	u8	multi_lun_device_lun_count;
+	u8	lun_count;
 	bool	raid_bypass_configured;	/* RAID bypass configured */
 	bool	raid_bypass_enabled;	/* RAID bypass enabled */
 	u32	next_bypass_group[RAID_MAP_MAX_DATA_DISKS_PER_ROW];
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 78fc743f46e4..9f0f69c1ed66 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -1610,9 +1610,7 @@ static int pqi_get_physical_device_info(struct pqi_ctrl_info *ctrl_info,
 		&id_phys->alternate_paths_phys_connector,
 		sizeof(device->phys_connector));
 	device->bay = id_phys->phys_bay_in_box;
-	device->multi_lun_device_lun_count = id_phys->multi_lun_device_lun_count;
-	if (!device->multi_lun_device_lun_count)
-		device->multi_lun_device_lun_count = 1;
+	device->lun_count = id_phys->multi_lun_device_lun_count;
 	if ((id_phys->even_more_flags & PQI_DEVICE_PHY_MAP_SUPPORTED) &&
 		id_phys->phy_count)
 		device->phy_id =
@@ -1746,7 +1744,7 @@ static bool pqi_keep_device_offline(struct pqi_ctrl_info *ctrl_info,
 	return offline;
 }
 
-static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
+static int pqi_get_device_info_phys_logical(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device,
 	struct bmic_identify_physical_device *id_phys)
 {
@@ -1763,6 +1761,20 @@ static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
 	return rc;
 }
 
+static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
+	struct pqi_scsi_dev *device,
+	struct bmic_identify_physical_device *id_phys)
+{
+	int rc;
+
+	rc = pqi_get_device_info_phys_logical(ctrl_info, device, id_phys);
+
+	if (rc == 0 && device->lun_count == 0)
+		device->lun_count = 1;
+
+	return rc;
+}
+
 static void pqi_show_volume_status(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device)
 {
@@ -1897,7 +1909,7 @@ static inline void pqi_remove_device(struct pqi_ctrl_info *ctrl_info, struct pqi
 	int rc;
 	int lun;
 
-	for (lun = 0; lun < device->multi_lun_device_lun_count; lun++) {
+	for (lun = 0; lun < device->lun_count; lun++) {
 		rc = pqi_device_wait_for_pending_io(ctrl_info, device, lun,
 			PQI_REMOVE_DEVICE_PENDING_IO_TIMEOUT_MSECS);
 		if (rc)
@@ -2076,6 +2088,7 @@ static void pqi_scsi_update_device(struct pqi_ctrl_info *ctrl_info,
 	existing_device->sas_address = new_device->sas_address;
 	existing_device->queue_depth = new_device->queue_depth;
 	existing_device->device_offline = false;
+	existing_device->lun_count = new_device->lun_count;
 
 	if (pqi_is_logical_device(existing_device)) {
 		existing_device->is_external_raid_device = new_device->is_external_raid_device;
@@ -2108,10 +2121,6 @@ static void pqi_scsi_update_device(struct pqi_ctrl_info *ctrl_info,
 		existing_device->phy_connected_dev_type = new_device->phy_connected_dev_type;
 		memcpy(existing_device->box, new_device->box, sizeof(existing_device->box));
 		memcpy(existing_device->phys_connector, new_device->phys_connector, sizeof(existing_device->phys_connector));
-
-		existing_device->multi_lun_device_lun_count = new_device->multi_lun_device_lun_count;
-		if (existing_device->multi_lun_device_lun_count == 0)
-			existing_device->multi_lun_device_lun_count = 1;
 	}
 }
 
@@ -6484,6 +6493,12 @@ static void pqi_slave_destroy(struct scsi_device *sdev)
 		return;
 	}
 
+	device->lun_count--;
+	if (device->lun_count > 0) {
+		mutex_unlock(&ctrl_info->scan_mutex);
+		return;
+	}
+
 	spin_lock_irqsave(&ctrl_info->scsi_device_list_lock, flags);
 	list_del(&device->scsi_device_list_entry);
 	spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);
-- 
2.35.1

[PATCH AUTOSEL 6.1 10/16] drm/fsl-dcu: Fix return type of fsl_dcu_drm_connector_mode_valid()

[Sasha Levin]

From: Nathan Chancellor <nathan@kernel.org>

[ Upstream commit 96d845a67b7e406cfed7880a724c8ca6121e022e ]

With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG),
indirect call targets are validated against the expected function
pointer prototype to make sure the call target is valid to help mitigate
ROP attacks. If they are not identical, there is a failure at run time,
which manifests as either a kernel panic or thread getting killed. A
proposed warning in clang aims to catch these at compile time, which
reveals:

  drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c:74:16: error: incompatible function pointer types initializing 'enum drm_mode_status (*)(struct drm_connector *, struct drm_display_mode *)' with an expression of type 'int (struct drm_connector *, struct drm_display_mode *)' [-Werror,-Wincompatible-function-pointer-types-strict]
          .mode_valid = fsl_dcu_drm_connector_mode_valid,
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  1 error generated.

->mode_valid() in 'struct drm_connector_helper_funcs' expects a return
type of 'enum drm_mode_status', not 'int'. Adjust the return type of
fsl_dcu_drm_connector_mode_valid() to match the prototype's to resolve
the warning and CFI failure.

Link: https://github.com/ClangBuiltLinux/linux/issues/1750
Reported-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20221102154215.78059-1-nathan@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index 4d4a715b429d..2c2b92324a2e 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -60,8 +60,9 @@ static int fsl_dcu_drm_connector_get_modes(struct drm_connector *connector)
 	return drm_panel_get_modes(fsl_connector->panel, connector);
 }
 
-static int fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector,
-					    struct drm_display_mode *mode)
+static enum drm_mode_status
+fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector,
+				 struct drm_display_mode *mode)
 {
 	if (mode->hdisplay & 0xf)
 		return MODE_ERROR;
-- 
2.35.1

[PATCH AUTOSEL 6.1 11/16] drm/sti: Fix return type of sti_{dvo,hda,hdmi}_connector_mode_valid()

[Sasha Levin]

From: Nathan Chancellor <nathan@kernel.org>

[ Upstream commit 0ad811cc08a937d875cbad0149c1bab17f84ba05 ]

With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG),
indirect call targets are validated against the expected function
pointer prototype to make sure the call target is valid to help mitigate
ROP attacks. If they are not identical, there is a failure at run time,
which manifests as either a kernel panic or thread getting killed. A
proposed warning in clang aims to catch these at compile time, which
reveals:

  drivers/gpu/drm/sti/sti_hda.c:637:16: error: incompatible function pointer types initializing 'enum drm_mode_status (*)(struct drm_connector *, struct drm_display_mode *)' with an expression of type 'int (struct drm_connector *, struct drm_display_mode *)' [-Werror,-Wincompatible-function-pointer-types-strict]
          .mode_valid = sti_hda_connector_mode_valid,
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
  drivers/gpu/drm/sti/sti_dvo.c:376:16: error: incompatible function pointer types initializing 'enum drm_mode_status (*)(struct drm_connector *, struct drm_display_mode *)' with an expression of type 'int (struct drm_connector *, struct drm_display_mode *)' [-Werror,-Wincompatible-function-pointer-types-strict]
          .mode_valid = sti_dvo_connector_mode_valid,
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
  drivers/gpu/drm/sti/sti_hdmi.c:1035:16: error: incompatible function pointer types initializing 'enum drm_mode_status (*)(struct drm_connector *, struct drm_display_mode *)' with an expression of type 'int (struct drm_connector *, struct drm_display_mode *)' [-Werror,-Wincompatible-function-pointer-types-strict]
          .mode_valid = sti_hdmi_connector_mode_valid,
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~

->mode_valid() in 'struct drm_connector_helper_funcs' expects a return
type of 'enum drm_mode_status', not 'int'. Adjust the return type of
sti_{dvo,hda,hdmi}_connector_mode_valid() to match the prototype's to
resolve the warning and CFI failure.

Link: https://github.com/ClangBuiltLinux/linux/issues/1750
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20221102155623.3042869-1-nathan@kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/sti/sti_dvo.c  | 5 +++--
 drivers/gpu/drm/sti/sti_hda.c  | 5 +++--
 drivers/gpu/drm/sti/sti_hdmi.c | 5 +++--
 3 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index b6ee8a82e656..076d5f30a09c 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -346,8 +346,9 @@ static int sti_dvo_connector_get_modes(struct drm_connector *connector)
 
 #define CLK_TOLERANCE_HZ 50
 
-static int sti_dvo_connector_mode_valid(struct drm_connector *connector,
-					struct drm_display_mode *mode)
+static enum drm_mode_status
+sti_dvo_connector_mode_valid(struct drm_connector *connector,
+			     struct drm_display_mode *mode)
 {
 	int target = mode->clock * 1000;
 	int target_min = target - CLK_TOLERANCE_HZ;
diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c
index 03cc401ed593..a53b5a15c2a9 100644
--- a/drivers/gpu/drm/sti/sti_hda.c
+++ b/drivers/gpu/drm/sti/sti_hda.c
@@ -601,8 +601,9 @@ static int sti_hda_connector_get_modes(struct drm_connector *connector)
 
 #define CLK_TOLERANCE_HZ 50
 
-static int sti_hda_connector_mode_valid(struct drm_connector *connector,
-					struct drm_display_mode *mode)
+static enum drm_mode_status
+sti_hda_connector_mode_valid(struct drm_connector *connector,
+			     struct drm_display_mode *mode)
 {
 	int target = mode->clock * 1000;
 	int target_min = target - CLK_TOLERANCE_HZ;
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index cb82622877d2..09e0cadb6368 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -1004,8 +1004,9 @@ static int sti_hdmi_connector_get_modes(struct drm_connector *connector)
 
 #define CLK_TOLERANCE_HZ 50
 
-static int sti_hdmi_connector_mode_valid(struct drm_connector *connector,
-					struct drm_display_mode *mode)
+static enum drm_mode_status
+sti_hdmi_connector_mode_valid(struct drm_connector *connector,
+			      struct drm_display_mode *mode)
 {
 	int target = mode->clock * 1000;
 	int target_min = target - CLK_TOLERANCE_HZ;
-- 
2.35.1

[PATCH AUTOSEL 6.1 12/16] scsi: target: iscsi: Fix a race condition between login_work and the login thread

[Sasha Levin]

From: Maurizio Lombardi <mlombard@redhat.com>

[ Upstream commit fec1b2fa62c162d03f5dcd7b03e3c89d3116d49f ]

In case a malicious initiator sends some random data immediately after a
login PDU; the iscsi_target_sk_data_ready() callback will schedule the
login_work and, at the same time, the negotiation may end without clearing
the LOGIN_FLAGS_INITIAL_PDU flag (because no additional PDU exchanges are
required to complete the login).

The login has been completed but the login_work function will find the
LOGIN_FLAGS_INITIAL_PDU flag set and will never stop from rescheduling
itself; at this point, if the initiator drops the connection, the
iscsit_conn structure will be freed, login_work will dereference a released
socket structure and the kernel crashes.

BUG: kernel NULL pointer dereference, address: 0000000000000230
PF: supervisor write access in kernel mode
PF: error_code(0x0002) - not-present page
Workqueue: events iscsi_target_do_login_rx [iscsi_target_mod]
RIP: 0010:_raw_read_lock_bh+0x15/0x30
Call trace:
 iscsi_target_do_login_rx+0x75/0x3f0 [iscsi_target_mod]
 process_one_work+0x1e8/0x3c0

Fix this bug by forcing login_work to stop after the login has been
completed and the socket callbacks have been restored.

Add a comment to clearify the return values of iscsi_target_do_login()

Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Link: https://lore.kernel.org/r/20221115125638.102517-1-mlombard@redhat.com
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/target/iscsi/iscsi_target_nego.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index f2919319ad38..ff49c8f3fe24 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -1018,6 +1018,13 @@ static int iscsi_target_handle_csg_one(struct iscsit_conn *conn, struct iscsi_lo
 	return 0;
 }
 
+/*
+ * RETURN VALUE:
+ *
+ *  1 = Login successful
+ * -1 = Login failed
+ *  0 = More PDU exchanges required
+ */
 static int iscsi_target_do_login(struct iscsit_conn *conn, struct iscsi_login *login)
 {
 	int pdu_count = 0;
@@ -1363,12 +1370,13 @@ int iscsi_target_start_negotiation(
 		ret = -1;
 
 	if (ret < 0) {
-		cancel_delayed_work_sync(&conn->login_work);
 		iscsi_target_restore_sock_callbacks(conn);
 		iscsi_remove_failed_auth_entry(conn);
 	}
-	if (ret != 0)
+	if (ret != 0) {
+		cancel_delayed_work_sync(&conn->login_work);
 		iscsi_target_nego_release(conn);
+	}
 
 	return ret;
 }
-- 
2.35.1

[PATCH AUTOSEL 6.1 13/16] iomap: write iomap validity checks

[Sasha Levin]

From: Dave Chinner <dchinner@redhat.com>

[ Upstream commit d7b64041164ca177170191d2ad775da074ab2926 ]

A recent multithreaded write data corruption has been uncovered in
the iomap write code. The core of the problem is partial folio
writes can be flushed to disk while a new racing write can map it
and fill the rest of the page:

writeback			new write

allocate blocks
  blocks are unwritten
submit IO
.....
				map blocks
				iomap indicates UNWRITTEN range
				loop {
				  lock folio
				  copyin data
.....
IO completes
  runs unwritten extent conv
    blocks are marked written
				  <iomap now stale>
				  get next folio
				}

Now add memory pressure such that memory reclaim evicts the
partially written folio that has already been written to disk.

When the new write finally gets to the last partial page of the new
write, it does not find it in cache, so it instantiates a new page,
sees the iomap is unwritten, and zeros the part of the page that
it does not have data from. This overwrites the data on disk that
was originally written.

The full description of the corruption mechanism can be found here:

https://lore.kernel.org/linux-xfs/20220817093627.GZ3600936@dread.disaster.area/

To solve this problem, we need to check whether the iomap is still
valid after we lock each folio during the write. We have to do it
after we lock the page so that we don't end up with state changes
occurring while we wait for the folio to be locked.

Hence we need a mechanism to be able to check that the cached iomap
is still valid (similar to what we already do in buffered
writeback), and we need a way for ->begin_write to back out and
tell the high level iomap iterator that we need to remap the
remaining write range.

The iomap needs to grow some storage for the validity cookie that
the filesystem provides to travel with the iomap. XFS, in
particular, also needs to know some more information about what the
iomap maps (attribute extents rather than file data extents) to for
the validity cookie to cover all the types of iomaps we might need
to validate.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/iomap/buffered-io.c | 29 +++++++++++++++++++++++++++-
 fs/iomap/iter.c        | 19 ++++++++++++++++++-
 include/linux/iomap.h  | 43 ++++++++++++++++++++++++++++++++++--------
 3 files changed, 81 insertions(+), 10 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 91ee0b308e13..8354b0fdaa94 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -584,7 +584,7 @@ static int iomap_write_begin_inline(const struct iomap_iter *iter,
 	return iomap_read_inline_data(iter, folio);
 }
 
-static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
+static int iomap_write_begin(struct iomap_iter *iter, loff_t pos,
 		size_t len, struct folio **foliop)
 {
 	const struct iomap_page_ops *page_ops = iter->iomap.page_ops;
@@ -618,6 +618,27 @@ static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 		status = (iter->flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOMEM;
 		goto out_no_page;
 	}
+
+	/*
+	 * Now we have a locked folio, before we do anything with it we need to
+	 * check that the iomap we have cached is not stale. The inode extent
+	 * mapping can change due to concurrent IO in flight (e.g.
+	 * IOMAP_UNWRITTEN state can change and memory reclaim could have
+	 * reclaimed a previously partially written page at this index after IO
+	 * completion before this write reaches this file offset) and hence we
+	 * could do the wrong thing here (zero a page range incorrectly or fail
+	 * to zero) and corrupt data.
+	 */
+	if (page_ops && page_ops->iomap_valid) {
+		bool iomap_valid = page_ops->iomap_valid(iter->inode,
+							&iter->iomap);
+		if (!iomap_valid) {
+			iter->iomap.flags |= IOMAP_F_STALE;
+			status = 0;
+			goto out_unlock;
+		}
+	}
+
 	if (pos + len > folio_pos(folio) + folio_size(folio))
 		len = folio_pos(folio) + folio_size(folio) - pos;
 
@@ -773,6 +794,8 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (unlikely(status))
 			break;
+		if (iter->iomap.flags & IOMAP_F_STALE)
+			break;
 
 		page = folio_file_page(folio, pos >> PAGE_SHIFT);
 		if (mapping_writably_mapped(mapping))
@@ -856,6 +879,8 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (unlikely(status))
 			return status;
+		if (iter->iomap.flags & IOMAP_F_STALE)
+			break;
 
 		status = iomap_write_end(iter, pos, bytes, bytes, folio);
 		if (WARN_ON_ONCE(status == 0))
@@ -911,6 +936,8 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (status)
 			return status;
+		if (iter->iomap.flags & IOMAP_F_STALE)
+			break;
 
 		offset = offset_in_folio(folio, pos);
 		if (bytes > folio_size(folio) - offset)
diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c
index a1c7592d2ade..79a0614eaab7 100644
--- a/fs/iomap/iter.c
+++ b/fs/iomap/iter.c
@@ -7,12 +7,28 @@
 #include <linux/iomap.h>
 #include "trace.h"
 
+/*
+ * Advance to the next range we need to map.
+ *
+ * If the iomap is marked IOMAP_F_STALE, it means the existing map was not fully
+ * processed - it was aborted because the extent the iomap spanned may have been
+ * changed during the operation. In this case, the iteration behaviour is to
+ * remap the unprocessed range of the iter, and that means we may need to remap
+ * even when we've made no progress (i.e. iter->processed = 0). Hence the
+ * "finished iterating" case needs to distinguish between
+ * (processed = 0) meaning we are done and (processed = 0 && stale) meaning we
+ * need to remap the entire remaining range.
+ */
 static inline int iomap_iter_advance(struct iomap_iter *iter)
 {
+	bool stale = iter->iomap.flags & IOMAP_F_STALE;
+
 	/* handle the previous iteration (if any) */
 	if (iter->iomap.length) {
-		if (iter->processed <= 0)
+		if (iter->processed < 0)
 			return iter->processed;
+		if (!iter->processed && !stale)
+			return 0;
 		if (WARN_ON_ONCE(iter->processed > iomap_length(iter)))
 			return -EIO;
 		iter->pos += iter->processed;
@@ -33,6 +49,7 @@ static inline void iomap_iter_done(struct iomap_iter *iter)
 	WARN_ON_ONCE(iter->iomap.offset > iter->pos);
 	WARN_ON_ONCE(iter->iomap.length == 0);
 	WARN_ON_ONCE(iter->iomap.offset + iter->iomap.length <= iter->pos);
+	WARN_ON_ONCE(iter->iomap.flags & IOMAP_F_STALE);
 
 	trace_iomap_iter_dstmap(iter->inode, &iter->iomap);
 	if (iter->srcmap.type != IOMAP_HOLE)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 238a03087e17..f166d80b68bf 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -49,26 +49,35 @@ struct vm_fault;
  *
  * IOMAP_F_BUFFER_HEAD indicates that the file system requires the use of
  * buffer heads for this mapping.
+ *
+ * IOMAP_F_XATTR indicates that the iomap is for an extended attribute extent
+ * rather than a file data extent.
  */
-#define IOMAP_F_NEW		0x01
-#define IOMAP_F_DIRTY		0x02
-#define IOMAP_F_SHARED		0x04
-#define IOMAP_F_MERGED		0x08
-#define IOMAP_F_BUFFER_HEAD	0x10
-#define IOMAP_F_ZONE_APPEND	0x20
+#define IOMAP_F_NEW		(1U << 0)
+#define IOMAP_F_DIRTY		(1U << 1)
+#define IOMAP_F_SHARED		(1U << 2)
+#define IOMAP_F_MERGED		(1U << 3)
+#define IOMAP_F_BUFFER_HEAD	(1U << 4)
+#define IOMAP_F_ZONE_APPEND	(1U << 5)
+#define IOMAP_F_XATTR		(1U << 6)
 
 /*
  * Flags set by the core iomap code during operations:
  *
  * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size
  * has changed as the result of this write operation.
+ *
+ * IOMAP_F_STALE indicates that the iomap is not valid any longer and the file
+ * range it covers needs to be remapped by the high level before the operation
+ * can proceed.
  */
-#define IOMAP_F_SIZE_CHANGED	0x100
+#define IOMAP_F_SIZE_CHANGED	(1U << 8)
+#define IOMAP_F_STALE		(1U << 9)
 
 /*
  * Flags from 0x1000 up are for file system specific usage:
  */
-#define IOMAP_F_PRIVATE		0x1000
+#define IOMAP_F_PRIVATE		(1U << 12)
 
 
 /*
@@ -89,6 +98,7 @@ struct iomap {
 	void			*inline_data;
 	void			*private; /* filesystem private */
 	const struct iomap_page_ops *page_ops;
+	u64			validity_cookie; /* used with .iomap_valid() */
 };
 
 static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos)
@@ -128,6 +138,23 @@ struct iomap_page_ops {
 	int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len);
 	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
 			struct page *page);
+
+	/*
+	 * Check that the cached iomap still maps correctly to the filesystem's
+	 * internal extent map. FS internal extent maps can change while iomap
+	 * is iterating a cached iomap, so this hook allows iomap to detect that
+	 * the iomap needs to be refreshed during a long running write
+	 * operation.
+	 *
+	 * The filesystem can store internal state (e.g. a sequence number) in
+	 * iomap->validity_cookie when the iomap is first mapped to be able to
+	 * detect changes between mapping time and whenever .iomap_valid() is
+	 * called.
+	 *
+	 * This is called with the folio over the specified file position held
+	 * locked by the iomap code.
+	 */
+	bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap);
 };
 
 /*
-- 
2.35.1

Re: [PATCH AUTOSEL 6.1 13/16] iomap: write iomap validity checks

[Dave Chinner]

On Mon, Dec 19, 2022 at 08:20:50PM -0500, Sasha Levin wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> [ Upstream commit d7b64041164ca177170191d2ad775da074ab2926 ]
> 
> A recent multithreaded write data corruption has been uncovered in
> the iomap write code. The core of the problem is partial folio
> writes can be flushed to disk while a new racing write can map it
> and fill the rest of the page:
> 
> writeback			new write
> 
> allocate blocks
>   blocks are unwritten
> submit IO
> .....
> 				map blocks
> 				iomap indicates UNWRITTEN range
> 				loop {
> 				  lock folio
> 				  copyin data
> .....
> IO completes
>   runs unwritten extent conv
>     blocks are marked written
> 				  <iomap now stale>
> 				  get next folio
> 				}
> 
> Now add memory pressure such that memory reclaim evicts the
> partially written folio that has already been written to disk.
> 
> When the new write finally gets to the last partial page of the new
> write, it does not find it in cache, so it instantiates a new page,
> sees the iomap is unwritten, and zeros the part of the page that
> it does not have data from. This overwrites the data on disk that
> was originally written.
> 
> The full description of the corruption mechanism can be found here:
> 
> https://lore.kernel.org/linux-xfs/20220817093627.GZ3600936@dread.disaster.area/
> 
> To solve this problem, we need to check whether the iomap is still
> valid after we lock each folio during the write. We have to do it
> after we lock the page so that we don't end up with state changes
> occurring while we wait for the folio to be locked.
> 
> Hence we need a mechanism to be able to check that the cached iomap
> is still valid (similar to what we already do in buffered
> writeback), and we need a way for ->begin_write to back out and
> tell the high level iomap iterator that we need to remap the
> remaining write range.
> 
> The iomap needs to grow some storage for the validity cookie that
> the filesystem provides to travel with the iomap. XFS, in
> particular, also needs to know some more information about what the
> iomap maps (attribute extents rather than file data extents) to for
> the validity cookie to cover all the types of iomaps we might need
> to validate.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Darrick J. Wong <djwong@kernel.org>
> Signed-off-by: Sasha Levin <sashal@kernel.org>

This commit is not a standalone backport candidate. It is a pure
infrastructure change that does nothing by itself except to add more
code that won't get executed. There are another 7-8 patches that
need to be backported along with this patch to fix the data
corruption that is mentioned in this commit.

I'd stronly suggest that you leave this whole series of commits to
the XFS LTS maintainers to backport if they so choose to - randomly
backporting commits from the middle of the series only makes their
job more complex....

-Dave.
-- 
Dave Chinner
david@fromorbit.com

Re: [PATCH AUTOSEL 6.1 13/16] iomap: write iomap validity checks

[Sasha Levin]

On Tue, Dec 20, 2022 at 03:01:12PM +1100, Dave Chinner wrote:
>On Mon, Dec 19, 2022 at 08:20:50PM -0500, Sasha Levin wrote:
>> From: Dave Chinner <dchinner@redhat.com>
>>
>> [ Upstream commit d7b64041164ca177170191d2ad775da074ab2926 ]
>>
>> A recent multithreaded write data corruption has been uncovered in
>> the iomap write code. The core of the problem is partial folio
>> writes can be flushed to disk while a new racing write can map it
>> and fill the rest of the page:
>>
>> writeback			new write
>>
>> allocate blocks
>>   blocks are unwritten
>> submit IO
>> .....
>> 				map blocks
>> 				iomap indicates UNWRITTEN range
>> 				loop {
>> 				  lock folio
>> 				  copyin data
>> .....
>> IO completes
>>   runs unwritten extent conv
>>     blocks are marked written
>> 				  <iomap now stale>
>> 				  get next folio
>> 				}
>>
>> Now add memory pressure such that memory reclaim evicts the
>> partially written folio that has already been written to disk.
>>
>> When the new write finally gets to the last partial page of the new
>> write, it does not find it in cache, so it instantiates a new page,
>> sees the iomap is unwritten, and zeros the part of the page that
>> it does not have data from. This overwrites the data on disk that
>> was originally written.
>>
>> The full description of the corruption mechanism can be found here:
>>
>> https://lore.kernel.org/linux-xfs/20220817093627.GZ3600936@dread.disaster.area/
>>
>> To solve this problem, we need to check whether the iomap is still
>> valid after we lock each folio during the write. We have to do it
>> after we lock the page so that we don't end up with state changes
>> occurring while we wait for the folio to be locked.
>>
>> Hence we need a mechanism to be able to check that the cached iomap
>> is still valid (similar to what we already do in buffered
>> writeback), and we need a way for ->begin_write to back out and
>> tell the high level iomap iterator that we need to remap the
>> remaining write range.
>>
>> The iomap needs to grow some storage for the validity cookie that
>> the filesystem provides to travel with the iomap. XFS, in
>> particular, also needs to know some more information about what the
>> iomap maps (attribute extents rather than file data extents) to for
>> the validity cookie to cover all the types of iomaps we might need
>> to validate.
>>
>> Signed-off-by: Dave Chinner <dchinner@redhat.com>
>> Reviewed-by: Christoph Hellwig <hch@lst.de>
>> Reviewed-by: Darrick J. Wong <djwong@kernel.org>
>> Signed-off-by: Sasha Levin <sashal@kernel.org>
>
>This commit is not a standalone backport candidate. It is a pure
>infrastructure change that does nothing by itself except to add more
>code that won't get executed. There are another 7-8 patches that
>need to be backported along with this patch to fix the data
>corruption that is mentioned in this commit.
>
>I'd stronly suggest that you leave this whole series of commits to
>the XFS LTS maintainers to backport if they so choose to - randomly
>backporting commits from the middle of the series only makes their
>job more complex....

Ack, I'll drop it, thanks!

-- 
Thanks,
Sasha

[PATCH AUTOSEL 6.1 14/16] orangefs: Fix kmemleak in orangefs_prepare_debugfs_help_string()

[Sasha Levin]

From: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>

[ Upstream commit d23417a5bf3a3afc55de5442eb46e1e60458b0a1 ]

When insert and remove the orangefs module, then debug_help_string will
be leaked:

  unreferenced object 0xffff8881652ba000 (size 4096):
    comm "insmod", pid 1701, jiffies 4294893639 (age 13218.530s)
    hex dump (first 32 bytes):
      43 6c 69 65 6e 74 20 44 65 62 75 67 20 4b 65 79  Client Debug Key
      77 6f 72 64 73 20 61 72 65 20 75 6e 6b 6e 6f 77  words are unknow
    backtrace:
      [<0000000004e6f8e3>] kmalloc_trace+0x27/0xa0
      [<0000000006f75d85>] orangefs_prepare_debugfs_help_string+0x5e/0x480 [orangefs]
      [<0000000091270a2a>] _sub_I_65535_1+0x57/0xf70 [crc_itu_t]
      [<000000004b1ee1a3>] do_one_initcall+0x87/0x2a0
      [<000000001d0614ae>] do_init_module+0xdf/0x320
      [<00000000efef068c>] load_module+0x2f98/0x3330
      [<000000006533b44d>] __do_sys_finit_module+0x113/0x1b0
      [<00000000a0da6f99>] do_syscall_64+0x35/0x80
      [<000000007790b19b>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

When remove the module, should always free debug_help_string. Should
always free the allocated buffer when change the free_debug_help_string.

Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/orangefs/orangefs-debugfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index 29eaa4544372..a848b6ef9599 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -222,6 +222,8 @@ static void orangefs_kernel_debug_init(void)
 void orangefs_debugfs_cleanup(void)
 {
 	debugfs_remove_recursive(debug_dir);
+	kfree(debug_help_string);
+	debug_help_string = NULL;
 }
 
 /* open ORANGEFS_KMOD_DEBUG_HELP_FILE */
@@ -671,6 +673,7 @@ int orangefs_prepare_debugfs_help_string(int at_boot)
 		memset(debug_help_string, 0, DEBUG_HELP_STRING_SIZE);
 		strlcat(debug_help_string, new, string_size);
 		mutex_unlock(&orangefs_help_file_lock);
+		kfree(new);
 	}
 
 	rc = 0;
-- 
2.35.1

[PATCH AUTOSEL 6.1 15/16] orangefs: Fix kmemleak in orangefs_sysfs_init()

[Sasha Levin]

From: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>

[ Upstream commit 1f2c0e8a587bcafad85019a2d80f158d8d41a868 ]

When insert and remove the orangefs module, there are kobjects memory
leaked as below:

unreferenced object 0xffff88810f95af00 (size 64):
  comm "insmod", pid 783, jiffies 4294813439 (age 65.512s)
  hex dump (first 32 bytes):
    a0 83 af 01 81 88 ff ff 08 af 95 0f 81 88 ff ff  ................
    08 af 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000031ab7788>] kmalloc_trace+0x27/0xa0
    [<000000005a6e4dfe>] orangefs_sysfs_init+0x42/0x3a0
    [<00000000722645ca>] 0xffffffffa02780fe
    [<000000004232d9f7>] do_one_initcall+0x87/0x2a0
    [<0000000054f22384>] do_init_module+0xdf/0x320
    [<000000003263bdea>] load_module+0x2f98/0x3330
    [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0
    [<00000000250ae02b>] do_syscall_64+0x35/0x80
    [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

unreferenced object 0xffff88810f95ae80 (size 64):
  comm "insmod", pid 783, jiffies 4294813439 (age 65.512s)
  hex dump (first 32 bytes):
    c8 90 0f 02 81 88 ff ff 88 ae 95 0f 81 88 ff ff  ................
    88 ae 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000031ab7788>] kmalloc_trace+0x27/0xa0
    [<000000001a4841fa>] orangefs_sysfs_init+0xc7/0x3a0
    [<00000000722645ca>] 0xffffffffa02780fe
    [<000000004232d9f7>] do_one_initcall+0x87/0x2a0
    [<0000000054f22384>] do_init_module+0xdf/0x320
    [<000000003263bdea>] load_module+0x2f98/0x3330
    [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0
    [<00000000250ae02b>] do_syscall_64+0x35/0x80
    [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

unreferenced object 0xffff88810f95ae00 (size 64):
  comm "insmod", pid 783, jiffies 4294813440 (age 65.511s)
  hex dump (first 32 bytes):
    60 87 a1 00 81 88 ff ff 08 ae 95 0f 81 88 ff ff  `...............
    08 ae 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000031ab7788>] kmalloc_trace+0x27/0xa0
    [<000000005915e797>] orangefs_sysfs_init+0x12b/0x3a0
    [<00000000722645ca>] 0xffffffffa02780fe
    [<000000004232d9f7>] do_one_initcall+0x87/0x2a0
    [<0000000054f22384>] do_init_module+0xdf/0x320
    [<000000003263bdea>] load_module+0x2f98/0x3330
    [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0
    [<00000000250ae02b>] do_syscall_64+0x35/0x80
    [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

unreferenced object 0xffff88810f95ad80 (size 64):
  comm "insmod", pid 783, jiffies 4294813440 (age 65.511s)
  hex dump (first 32 bytes):
    78 90 0f 02 81 88 ff ff 88 ad 95 0f 81 88 ff ff  x...............
    88 ad 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000031ab7788>] kmalloc_trace+0x27/0xa0
    [<000000007a14eb35>] orangefs_sysfs_init+0x1ac/0x3a0
    [<00000000722645ca>] 0xffffffffa02780fe
    [<000000004232d9f7>] do_one_initcall+0x87/0x2a0
    [<0000000054f22384>] do_init_module+0xdf/0x320
    [<000000003263bdea>] load_module+0x2f98/0x3330
    [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0
    [<00000000250ae02b>] do_syscall_64+0x35/0x80
    [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

unreferenced object 0xffff88810f95ac00 (size 64):
  comm "insmod", pid 783, jiffies 4294813440 (age 65.531s)
  hex dump (first 32 bytes):
    e0 ff 67 02 81 88 ff ff 08 ac 95 0f 81 88 ff ff  ..g.............
    08 ac 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000031ab7788>] kmalloc_trace+0x27/0xa0
    [<000000001f38adcb>] orangefs_sysfs_init+0x291/0x3a0
    [<00000000722645ca>] 0xffffffffa02780fe
    [<000000004232d9f7>] do_one_initcall+0x87/0x2a0
    [<0000000054f22384>] do_init_module+0xdf/0x320
    [<000000003263bdea>] load_module+0x2f98/0x3330
    [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0
    [<00000000250ae02b>] do_syscall_64+0x35/0x80
    [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

unreferenced object 0xffff88810f95ab80 (size 64):
  comm "insmod", pid 783, jiffies 4294813441 (age 65.530s)
  hex dump (first 32 bytes):
    50 bf 2f 02 81 88 ff ff 88 ab 95 0f 81 88 ff ff  P./.............
    88 ab 95 0f 81 88 ff ff 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000031ab7788>] kmalloc_trace+0x27/0xa0
    [<000000009cc7d95b>] orangefs_sysfs_init+0x2f5/0x3a0
    [<00000000722645ca>] 0xffffffffa02780fe
    [<000000004232d9f7>] do_one_initcall+0x87/0x2a0
    [<0000000054f22384>] do_init_module+0xdf/0x320
    [<000000003263bdea>] load_module+0x2f98/0x3330
    [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0
    [<00000000250ae02b>] do_syscall_64+0x35/0x80
    [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

Should add release function for each kobject_type to free the memory.

Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/orangefs/orangefs-sysfs.c | 71 ++++++++++++++++++++++++++++++++----
 1 file changed, 63 insertions(+), 8 deletions(-)

diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c
index de80b62553bb..be4ba03a01a0 100644
--- a/fs/orangefs/orangefs-sysfs.c
+++ b/fs/orangefs/orangefs-sysfs.c
@@ -896,9 +896,18 @@ static struct attribute *orangefs_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(orangefs_default);
 
+static struct kobject *orangefs_obj;
+
+static void orangefs_obj_release(struct kobject *kobj)
+{
+	kfree(orangefs_obj);
+	orangefs_obj = NULL;
+}
+
 static struct kobj_type orangefs_ktype = {
 	.sysfs_ops = &orangefs_sysfs_ops,
 	.default_groups = orangefs_default_groups,
+	.release = orangefs_obj_release,
 };
 
 static struct orangefs_attribute acache_hard_limit_attribute =
@@ -934,9 +943,18 @@ static struct attribute *acache_orangefs_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(acache_orangefs_default);
 
+static struct kobject *acache_orangefs_obj;
+
+static void acache_orangefs_obj_release(struct kobject *kobj)
+{
+	kfree(acache_orangefs_obj);
+	acache_orangefs_obj = NULL;
+}
+
 static struct kobj_type acache_orangefs_ktype = {
 	.sysfs_ops = &orangefs_sysfs_ops,
 	.default_groups = acache_orangefs_default_groups,
+	.release = acache_orangefs_obj_release,
 };
 
 static struct orangefs_attribute capcache_hard_limit_attribute =
@@ -972,9 +990,18 @@ static struct attribute *capcache_orangefs_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(capcache_orangefs_default);
 
+static struct kobject *capcache_orangefs_obj;
+
+static void capcache_orangefs_obj_release(struct kobject *kobj)
+{
+	kfree(capcache_orangefs_obj);
+	capcache_orangefs_obj = NULL;
+}
+
 static struct kobj_type capcache_orangefs_ktype = {
 	.sysfs_ops = &orangefs_sysfs_ops,
 	.default_groups = capcache_orangefs_default_groups,
+	.release = capcache_orangefs_obj_release,
 };
 
 static struct orangefs_attribute ccache_hard_limit_attribute =
@@ -1010,9 +1037,18 @@ static struct attribute *ccache_orangefs_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ccache_orangefs_default);
 
+static struct kobject *ccache_orangefs_obj;
+
+static void ccache_orangefs_obj_release(struct kobject *kobj)
+{
+	kfree(ccache_orangefs_obj);
+	ccache_orangefs_obj = NULL;
+}
+
 static struct kobj_type ccache_orangefs_ktype = {
 	.sysfs_ops = &orangefs_sysfs_ops,
 	.default_groups = ccache_orangefs_default_groups,
+	.release = ccache_orangefs_obj_release,
 };
 
 static struct orangefs_attribute ncache_hard_limit_attribute =
@@ -1048,9 +1084,18 @@ static struct attribute *ncache_orangefs_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ncache_orangefs_default);
 
+static struct kobject *ncache_orangefs_obj;
+
+static void ncache_orangefs_obj_release(struct kobject *kobj)
+{
+	kfree(ncache_orangefs_obj);
+	ncache_orangefs_obj = NULL;
+}
+
 static struct kobj_type ncache_orangefs_ktype = {
 	.sysfs_ops = &orangefs_sysfs_ops,
 	.default_groups = ncache_orangefs_default_groups,
+	.release = ncache_orangefs_obj_release,
 };
 
 static struct orangefs_attribute pc_acache_attribute =
@@ -1079,9 +1124,18 @@ static struct attribute *pc_orangefs_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(pc_orangefs_default);
 
+static struct kobject *pc_orangefs_obj;
+
+static void pc_orangefs_obj_release(struct kobject *kobj)
+{
+	kfree(pc_orangefs_obj);
+	pc_orangefs_obj = NULL;
+}
+
 static struct kobj_type pc_orangefs_ktype = {
 	.sysfs_ops = &orangefs_sysfs_ops,
 	.default_groups = pc_orangefs_default_groups,
+	.release = pc_orangefs_obj_release,
 };
 
 static struct orangefs_attribute stats_reads_attribute =
@@ -1103,19 +1157,20 @@ static struct attribute *stats_orangefs_default_attrs[] = {
 };
 ATTRIBUTE_GROUPS(stats_orangefs_default);
 
+static struct kobject *stats_orangefs_obj;
+
+static void stats_orangefs_obj_release(struct kobject *kobj)
+{
+	kfree(stats_orangefs_obj);
+	stats_orangefs_obj = NULL;
+}
+
 static struct kobj_type stats_orangefs_ktype = {
 	.sysfs_ops = &orangefs_sysfs_ops,
 	.default_groups = stats_orangefs_default_groups,
+	.release = stats_orangefs_obj_release,
 };
 
-static struct kobject *orangefs_obj;
-static struct kobject *acache_orangefs_obj;
-static struct kobject *capcache_orangefs_obj;
-static struct kobject *ccache_orangefs_obj;
-static struct kobject *ncache_orangefs_obj;
-static struct kobject *pc_orangefs_obj;
-static struct kobject *stats_orangefs_obj;
-
 int orangefs_sysfs_init(void)
 {
 	int rc = -EINVAL;
-- 
2.35.1

[PATCH AUTOSEL 6.1 16/16] orangefs: Fix kmemleak in orangefs_{kernel,client}_debug_init()

[Sasha Levin]

From: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>

[ Upstream commit 31720a2b109b3080eb77e97b8f6f50a27b4ae599 ]

When insert and remove the orangefs module, there are memory leaked
as below:

unreferenced object 0xffff88816b0cc000 (size 2048):
  comm "insmod", pid 783, jiffies 4294813439 (age 65.512s)
  hex dump (first 32 bytes):
    6e 6f 6e 65 0a 00 00 00 00 00 00 00 00 00 00 00  none............
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000031ab7788>] kmalloc_trace+0x27/0xa0
    [<000000005b405fee>] orangefs_debugfs_init.cold+0xaf/0x17f
    [<00000000e5a0085b>] 0xffffffffa02780f9
    [<000000004232d9f7>] do_one_initcall+0x87/0x2a0
    [<0000000054f22384>] do_init_module+0xdf/0x320
    [<000000003263bdea>] load_module+0x2f98/0x3330
    [<0000000052cd4153>] __do_sys_finit_module+0x113/0x1b0
    [<00000000250ae02b>] do_syscall_64+0x35/0x80
    [<00000000f11c03c7>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

Use the golbal variable as the buffer rather than dynamic allocate to
slove the problem.

Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/orangefs/orangefs-debugfs.c | 26 +++-----------------------
 1 file changed, 3 insertions(+), 23 deletions(-)

diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index a848b6ef9599..1b508f543384 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -194,15 +194,10 @@ void orangefs_debugfs_init(int debug_mask)
  */
 static void orangefs_kernel_debug_init(void)
 {
-	int rc = -ENOMEM;
-	char *k_buffer = NULL;
+	static char k_buffer[ORANGEFS_MAX_DEBUG_STRING_LEN] = { };
 
 	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__);
 
-	k_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
-	if (!k_buffer)
-		goto out;
-
 	if (strlen(kernel_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) {
 		strcpy(k_buffer, kernel_debug_string);
 		strcat(k_buffer, "\n");
@@ -213,9 +208,6 @@ static void orangefs_kernel_debug_init(void)
 
 	debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer,
 			    &kernel_debug_fops);
-
-out:
-	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc);
 }
 
 
@@ -299,18 +291,13 @@ static int help_show(struct seq_file *m, void *v)
 /*
  * initialize the client-debug file.
  */
-static int orangefs_client_debug_init(void)
+static void orangefs_client_debug_init(void)
 {
 
-	int rc = -ENOMEM;
-	char *c_buffer = NULL;
+	static char c_buffer[ORANGEFS_MAX_DEBUG_STRING_LEN] = { };
 
 	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__);
 
-	c_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
-	if (!c_buffer)
-		goto out;
-
 	if (strlen(client_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) {
 		strcpy(c_buffer, client_debug_string);
 		strcat(c_buffer, "\n");
@@ -324,13 +311,6 @@ static int orangefs_client_debug_init(void)
 						  debug_dir,
 						  c_buffer,
 						  &kernel_debug_fops);
-
-	rc = 0;
-
-out:
-
-	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc);
-	return rc;
 }
 
 /* open ORANGEFS_KMOD_DEBUG_FILE or ORANGEFS_CLIENT_DEBUG_FILE.*/
-- 
2.35.1