4.14.82-stable review

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Christophe Leroy <[email protected]>

[ Upstream commit daf00ae71dad8aa05965713c62558aeebf2df48e ]

commit b96672dd840f ("powerpc: Machine check interrupt is a non- maskable interrupt") added a call to nmi_enter() at the beginning of machine check restart exception handler. Due to that, in_interrupt() always returns true regardless of the state before entering the exception, and die() panics even when the system was not already in interrupt.

This patch calls nmi_exit() before calling die() in order to restore the interrupt state we had before calling nmi_enter()

---
 arch/powerpc/kernel/traps.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

@@ -694,12 +694,17 @@ void machine_check_exception(struct pt_r
 	if (check_io_access(regs))
 		goto bail;
 
-	die("Machine check", regs, SIGBUS);
-
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
 		nmi_panic(regs, "Unrecoverable Machine check");
 
+	if (!nested)
+		nmi_exit();
+
+	die("Machine check", regs, SIGBUS);
+
+	return;
+
 bail:
 	if (!nested)
 		nmi_exit();

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Nicholas Piggin <[email protected]>

[ Upstream commit b851ba02a6f3075f0f99c60c4bc30a4af80cf428 ]

The recent module relocation overflow crash demonstrated that we have no range checking on REL32 relative relocations. This patch implements a basic check, the same kernel that previously oopsed and rebooted now continues with some of these errors when loading the module:

module_64: x_tables: REL32 527703503449812 out of range!

Possibly other relocations (ADDR32, REL16, TOC16, etc.) should also have overflow checks.

---
 arch/powerpc/kernel/module_64.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

@@ -656,7 +656,14 @@ int apply_relocate_add(Elf64_Shdr *sechd
 
 		case R_PPC64_REL32:
 			/* 32 bits relative (used by relative exception tables) */
-			*(u32 *)location = value - (unsigned long)location;
+			/* Convert value to relative */
+			value -= (unsigned long)location;
+			if (value + 0x80000000 > 0xffffffff) {
+				pr_err("%s: REL32 %li out of range!\n",
+				       me->name, (long int)value);
+				return -ENOEXEC;
+			}
+			*(u32 *)location = value;
 			break;
 
 		case R_PPC64_TOCSAVE:

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Ellerman <[email protected]>

[ Upstream commit 0d923962ab69c27cca664a2d535e90ef655110ca ]

When we're running on Book3S with the Radix MMU enabled the page table dump currently prints the wrong addresses because it uses the wrong start address.

Fix it to use PAGE_OFFSET rather than KERN_VIRT_START.

---
 arch/powerpc/mm/dump_linuxpagetables.c |   12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

@@ -422,12 +422,13 @@ static void walk_pagetables(struct pg_st
 	unsigned int i;
 	unsigned long addr;
 
+	addr = st->start_address;
+
 	/*
 	 * Traverse the linux pagetable structure and dump pages that are in
 	 * the hash pagetable.
 	 */
-	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
-		addr = KERN_VIRT_START + i * PGDIR_SIZE;
+	for (i = 0; i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
 		if (!pgd_none(*pgd) && !pgd_huge(*pgd))
 			/* pgd exists */
 			walk_pud(st, pgd, addr);

@@ -476,9 +477,14 @@ static int ptdump_show(struct seq_file *
 {
 	struct pg_state st = {
 		.seq = m,
-		.start_address = KERN_VIRT_START,
 		.marker = address_markers,
 	};
+
+	if (radix_enabled())
+		st.start_address = PAGE_OFFSET;
+	else
+		st.start_address = KERN_VIRT_START;
+
 	/* Traverse kernel page tables */
 	walk_pagetables(&st);
 	note_page(&st, 0, 0, 0);

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Sam Bobroff <[email protected]>

[ Upstream commit f9bc28aedfb5bbd572d2d365f3095c1becd7209b ]

If an error occurs during an unplug operation, it's possible for eeh_dump_dev_log() to be called when edev->pdn is null, which currently leads to dereferencing a null pointer.

Handle this by skipping the error log for those devices.

---
 arch/powerpc/kernel/eeh.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -169,6 +169,11 @@ static size_t eeh_dump_dev_log(struct ee
 	int n = 0, l = 0;
 	char buffer[128];
 
+	if (!pdn) {
+		pr_warn("EEH: Note: No error log for absent device.\n");
+		return 0;
+	}
+
 	n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n",
 		       pdn->phb->global_number, pdn->busno,
 		       PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Miles Chen <[email protected]>

[ Upstream commit 33a1a7be198657c8ca26ad406c4d2a89b7162bcc ]

The issue is found by a fuzzing test.
If tty_find_polling_driver() recevies an incorrect input such as ',,' or '0b', the len becomes 0 and strncmp() always return 0. In this case, a null p->ops->poll_init() is called and it causes a kernel panic.

Fix this by checking name length against zero in tty_find_polling_driver().

$echo ,, > /sys/module/kgdboc/parameters/kgdboc

[   20.804451] WARNING: CPU: 1 PID: 104 at drivers/tty/serial/serial_core.c:457
uart_get_baud_rate+0xe8/0x190
[   20.804917] Modules linked in:
[   20.805317] CPU: 1 PID: 104 Comm: sh Not tainted 4.19.0-rc7ajb #8
[   20.805469] Hardware name: linux,dummy-virt (DT)
[   20.805732] pstate: 20000005 (nzCv daif -PAN -UAO)
[   20.805895] pc : uart_get_baud_rate+0xe8/0x190
[   20.806042] lr : uart_get_baud_rate+0xc0/0x190
[   20.806476] sp : ffffffc06acff940
[   20.806676] x29: ffffffc06acff940 x28: 0000000000002580
[   20.806977] x27: 0000000000009600 x26: 0000000000009600
[   20.807231] x25: ffffffc06acffad0 x24: 00000000ffffeff0
[   20.807576] x23: 0000000000000001 x22: 0000000000000000
[   20.807807] x21: 0000000000000001 x20: 0000000000000000
[   20.808049] x19: ffffffc06acffac8 x18: 0000000000000000
[   20.808277] x17: 0000000000000000 x16: 0000000000000000
[   20.808520] x15: ffffffffffffffff x14: ffffffff00000000
[   20.808757] x13: ffffffffffffffff x12: 0000000000000001
[   20.809011] x11: 0101010101010101 x10: ffffff880d59ff5f
[   20.809292] x9 : ffffff880d59ff5e x8 : ffffffc06acffaf3
[   20.809549] x7 : 0000000000000000 x6 : ffffff880d59ff5f
[   20.809803] x5 : 0000000080008001 x4 : 0000000000000003
[   20.810056] x3 : ffffff900853e6b4 x2 : dfffff9000000000
[   20.810693] x1 : ffffffc06acffad0 x0 : 0000000000000cb0
[   20.811005] Call trace:
[   20.811214]  uart_get_baud_rate+0xe8/0x190
[   20.811479]  serial8250_do_set_termios+0xe0/0x6f4
[   20.811719]  serial8250_set_termios+0x48/0x54
[   20.811928]  uart_set_options+0x138/0x1bc
[   20.812129]  uart_poll_init+0x114/0x16c
[   20.812330]  tty_find_polling_driver+0x158/0x200
[   20.812545]  configure_kgdboc+0xbc/0x1bc
[   20.812745]  param_set_kgdboc_var+0xb8/0x150
[   20.812960]  param_attr_store+0xbc/0x150
[   20.813160]  module_attr_store+0x40/0x58
[   20.813364]  sysfs_kf_write+0x8c/0xa8
[   20.813563]  kernfs_fop_write+0x154/0x290
[   20.813764]  vfs_write+0xf0/0x278
[   20.813951]  __arm64_sys_write+0x84/0xf4
[   20.814400]  el0_svc_common+0xf4/0x1dc
[   20.814616]  el0_svc_handler+0x98/0xbc
[   20.814804]  el0_svc+0x8/0xc
[   20.822005] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[   20.826913] Mem abort info:
[   20.827103]   ESR = 0x84000006
[   20.827352]   Exception class = IABT (current EL), IL = 16 bits
[   20.827655]   SET = 0, FnV = 0
[   20.827855]   EA = 0, S1PTW = 0
[   20.828135] user pgtable: 4k pages, 39-bit VAs, pgdp = (____ptrval____)
[   20.828484] [0000000000000000] pgd=00000000aadee003, pud=00000000aadee003, pmd=0000000000000000
[   20.829195] Internal error: Oops: 84000006 [#1] SMP
[   20.829564] Modules linked in:
[   20.829890] CPU: 1 PID: 104 Comm: sh Tainted: G        W         4.19.0-rc7ajb #8
[   20.830545] Hardware name: linux,dummy-virt (DT)
[   20.830829] pstate: 60000085 (nZCv daIf -PAN -UAO)
[   20.831174] pc :           (null)
[   20.831457] lr : serial8250_do_set_termios+0x358/0x6f4
[   20.831727] sp : ffffffc06acff9b0
[   20.831936] x29: ffffffc06acff9b0 x28: ffffff9008d7c000
[   20.832267] x27: ffffff900969e16f x26: 0000000000000000
[   20.832589] x25: ffffff900969dfb0 x24: 0000000000000000
[   20.832906] x23: ffffffc06acffad0 x22: ffffff900969e160
[   20.833232] x21: 0000000000000000 x20: ffffffc06acffac8
[   20.833559] x19: ffffff900969df90 x18: 0000000000000000
[   20.833878] x17: 0000000000000000 x16: 0000000000000000
[   20.834491] x15: ffffffffffffffff x14: ffffffff00000000
[   20.834821] x13: ffffffffffffffff x12: 0000000000000001
[   20.835143] x11: 0101010101010101 x10: ffffff880d59ff5f
[   20.835467] x9 : ffffff880d59ff5e x8 : ffffffc06acffaf3
[   20.835790] x7 : 0000000000000000 x6 : ffffff880d59ff5f
[   20.836111] x5 : c06419717c314100 x4 : 0000000000000007
[   20.836419] x3 : 0000000000000000 x2 : 0000000000000000
[   20.836732] x1 : 0000000000000001 x0 : ffffff900969df90
[   20.837100] Process sh (pid: 104, stack limit = 0x(____ptrval____))
[   20.837396] Call trace:
[   20.837566]            (null)
[   20.837816]  serial8250_set_termios+0x48/0x54
[   20.838089]  uart_set_options+0x138/0x1bc
[   20.838570]  uart_poll_init+0x114/0x16c
[   20.838834]  tty_find_polling_driver+0x158/0x200
[   20.839119]  configure_kgdboc+0xbc/0x1bc
[   20.839380]  param_set_kgdboc_var+0xb8/0x150
[   20.839658]  param_attr_store+0xbc/0x150
[   20.839920]  module_attr_store+0x40/0x58
[   20.840183]  sysfs_kf_write+0x8c/0xa8
[   20.840183]  sysfs_kf_write+0x8c/0xa8
[   20.840440]  kernfs_fop_write+0x154/0x290
[   20.840702]  vfs_write+0xf0/0x278
[   20.840942]  __arm64_sys_write+0x84/0xf4
[   20.841209]  el0_svc_common+0xf4/0x1dc
[   20.841471]  el0_svc_handler+0x98/0xbc
[   20.841713]  el0_svc+0x8/0xc
[   20.842057] Code: bad PC value
[   20.842764] ---[ end trace a8835d7de79aaadf ]---
[   20.843134] Kernel panic - not syncing: Fatal exception
[   20.843515] SMP: stopping secondary CPUs
[   20.844289] Kernel Offset: disabled
[   20.844634] CPU features: 0x0,21806002
[   20.844857] Memory Limit: none
[   20.845172] ---[ end Kernel panic - not syncing: Fatal exception ]---

---
 drivers/tty/tty_io.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -407,7 +407,7 @@ struct tty_driver *tty_find_polling_driv
 	mutex_lock(&tty_mutex);
 	/* Search through the tty devices to look for a match */
 	list_for_each_entry(p, &tty_drivers, tty_drivers) {
-		if (strncmp(name, p->name, len) != 0)
+		if (!len || strncmp(name, p->name, len) != 0)
 			continue;
 		stp = str;
 		if (*stp == ',')

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Fabio Estevam <[email protected]>

[ Upstream commit 35d3cbe84544da74e39e1cec01374092467e3119 ]

Andreas Müller reports:

"Fixes:

| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[220]: Failed to apply ACL on /dev/v4l-subdev0: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[224]: Failed to apply ACL on /dev/v4l-subdev1: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[215]: Failed to apply ACL on /dev/v4l-subdev10: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[228]: Failed to apply ACL on /dev/v4l-subdev2: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[232]: Failed to apply ACL on /dev/v4l-subdev5: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[217]: Failed to apply ACL on /dev/v4l-subdev11: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[214]: Failed to apply ACL on /dev/dri/card1: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[216]: Failed to apply ACL on /dev/v4l-subdev8: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[226]: Failed to apply ACL on /dev/v4l-subdev9: Operation not supported

and nasty follow-ups: Starting weston from sddm as unpriviledged user fails with some hints on missing access rights."

Select the CONFIG_TMPFS_POSIX_ACL option to fix these issues.

---
 arch/arm/configs/imx_v6_v7_defconfig |    1 +
 1 file changed, 1 insertion(+)

@@ -383,6 +383,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=y
+CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_JFFS2_FS=y
 CONFIG_UBIFS_FS=y
 CONFIG_NFS_FS=y

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Daniel Axtens <[email protected]>

[ Upstream commit f5e284803a7206d43e26f9ffcae5de9626d95e37 ]

When enumerating page size definitions to check hardware support, we construct a constant which is (1U << (def->shift - 10)).

However, the array of page size definitions is only initalised for various MMU_PAGE_* constants, so it contains a number of 0-initialised elements with def->shift == 0. This means we end up shifting by a very large number, which gives the following UBSan splat:

================================================================================

UBSAN: Undefined behaviour in /home/dja/dev/linux/linux/arch/powerpc/mm/tlb_nohash.c:506:21
shift exponent 4294967286 is too large for 32-bit type 'unsigned int'
CPU: 0 PID: 0 Comm: swapper Not tainted 4.19.0-rc3-00045-ga604f927b012-dirty #6
Call Trace:
[c00000000101bc20] [c000000000a13d54] .dump_stack+0xa8/0xec (unreliable)
[c00000000101bcb0] [c0000000004f20a8] .ubsan_epilogue+0x18/0x64
[c00000000101bd30] [c0000000004f2b10] .__ubsan_handle_shift_out_of_bounds+0x110/0x1a4
[c00000000101be20] [c000000000d21760] .early_init_mmu+0x1b4/0x5a0
[c00000000101bf10] [c000000000d1ba28] .early_setup+0x100/0x130
[c00000000101bf90] [c000000000000528] start_here_multiplatform+0x68/0x80
================================================================================

Fix this by first checking if the element exists (shift != 0) before constructing the constant.

---
 arch/powerpc/mm/tlb_nohash.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -500,6 +500,9 @@ static void setup_page_sizes(void)
 		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 			struct mmu_psize_def *def = &mmu_psize_defs[psize];
 
+			if (!def->shift)
+				continue;
+
 			if (tlb1ps & (1U << (def->shift - 10))) {
 				def->flags |= MMU_PAGE_SIZE_DIRECT;
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Christophe Leroy <[email protected]>

[ Upstream commit 803d690e68f0c5230183f1a42c7d50a41d16e380 ]

When a process allocates a hugepage, the following leak is reported by kmemleak. This is a false positive which is due to the pointer to the table being stored in the PGD as physical memory address and not virtual memory pointer.

unreferenced object 0xc30f8200 (size 512):
comm "mmap", pid 374, jiffies 4872494 (age 627.630s) hex dump (first 32 bytes):

    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<e32b68da>] huge_pte_alloc+0xdc/0x1f8
    [<9e0df1e1>] hugetlb_fault+0x560/0x8f8
    [<7938ec6c>] follow_hugetlb_page+0x14c/0x44c
    [<afbdb405>] __get_user_pages+0x1c4/0x3dc
    [<b8fd7cd9>] __mm_populate+0xac/0x140
    [<3215421e>] vm_mmap_pgoff+0xb4/0xb8
    [<c148db69>] ksys_mmap_pgoff+0xcc/0x1fc
    [<4fcd760f>] ret_from_syscall+0x0/0x38

See commit a984506c542e2 ("powerpc/mm: Don't report PUDs as memory leaks when using kmemleak") for detailed explanation.

To fix that, this patch tells kmemleak to ignore the allocated hugepage table.

---
 arch/powerpc/mm/hugetlbpage.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -19,6 +19,7 @@
 #include <linux/moduleparam.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/kmemleak.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>

@@ -110,6 +111,8 @@ static int __hugepte_alloc(struct mm_str
 		for (i = i - 1 ; i >= 0; i--, hpdp--)
 			*hpdp = __hugepd(0);
 		kmem_cache_free(cachep, new);
+	} else {
+		kmemleak_ignore(new);
 	}
 	spin_unlock(&mm->page_table_lock);
 	return 0;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Tomi Valkeinen <[email protected]>

[ Upstream commit 538f66ba204944470a653a4cccc5f8befdf97c22 ]

A DMM timeout "timed out waiting for done" has been observed on DRA7 devices. The timeout happens rarely, and only when the system is under heavy load.

Debugging showed that the timeout can be made to happen much more frequently by optimizing the DMM driver, so that there's almost no code between writing the last DMM descriptors to RAM, and writing to DMM register which starts the DMM transaction.

The current theory is that a wmb() does not properly ensure that the data written to RAM is observable by all the components in the system.

This DMM timeout has caused interesting (and rare) bugs as the error handling was not functioning properly (the error handling has been fixed in previous commits):

* If a DMM timeout happened when a GEM buffer was being pinned for display on the screen, a timeout error would be shown, but the driver would continue programming DSS HW with broken buffer, leading to SYNCLOST floods and possible crashes.

* If a DMM timeout happened when other user (say, video decoder) was pinning a GEM buffer, a timeout would be shown but if the user handled the error properly, no other issues followed.

* If a DMM timeout happened when a GEM buffer was being released, the driver does not even notice the error, leading to crashes or hang later.

This patch adds wmb() and readl() calls after the last bit is written to RAM, which should ensure that the execution proceeds only after the data is actually in RAM, and thus observable by DMM.

The read-back should not be needed. Further study is required to understand if DMM is somehow special case and read-back is ok, or if DRA7's memory barriers do not work correctly.

---
 drivers/gpu/drm/omapdrm/omap_dmm_tiler.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -273,6 +273,17 @@ static int dmm_txn_commit(struct dmm_txn
 	}
 
 	txn->last_pat->next_pa = 0;
+	/* ensure that the written descriptors are visible to DMM */
+	wmb();
+
+	/*
+	 * NOTE: the wmb() above should be enough, but there seems to be a bug
+	 * in OMAP's memory barrier implementation, which in some rare cases may
+	 * cause the writes not to be observable after wmb().
+	 */
+
+	/* read back to ensure the data is in RAM */
+	readl(&txn->last_pat->next_pa);
 
 	/* write to PAT_DESCR to clear out any pending transaction */
 	dmm_write(dmm, 0x0, reg[PAT_DESCR][engine->id]);

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: John Garry <[email protected]>

[ Upstream commit 331d880b35a76b5de0eec8cbcecbf615d758a5f9 ]

In hibmc_drm_fb_create(), when the call to hibmc_framebuffer_init() fails with error, do not store the error code in the HiBMC device frame-buffer pointer, as this will be later checked for non-zero value in hibmc_fbdev_destroy() when our intention is to check for a valid function pointer.

This fixes the following crash:

[    9.699791] Unable to handle kernel NULL pointer dereference at virtual address 000000000000001a
[    9.708672] Mem abort info:
[    9.711489]   ESR = 0x96000004
[    9.714570]   Exception class = DABT (current EL), IL = 32 bits
[    9.720551]   SET = 0, FnV = 0
[    9.723631]   EA = 0, S1PTW = 0
[    9.726799] Data abort info:
[    9.729702]   ISV = 0, ISS = 0x00000004
[    9.733573]   CM = 0, WnR = 0
[    9.736566] [000000000000001a] user address but active_mm is swapper
[    9.742987] Internal error: Oops: 96000004 [#1] PREEMPT SMP
[    9.748614] Modules linked in:
[    9.751694] CPU: 16 PID: 293 Comm: kworker/16:1 Tainted: G        W         4.19.0-rc4-next-20180920-00001-g9b0012c #322
[    9.762681] Hardware name: Huawei Taishan 2280 /D05, BIOS Hisilicon D05 IT21 Nemo 2.0 RC0 04/18/2018
[    9.771915] Workqueue: events work_for_cpu_fn
[    9.776312] pstate: 60000005 (nZCv daif -PAN -UAO)
[    9.781150] pc : drm_mode_object_put+0x0/0x20
[    9.785547] lr : hibmc_fbdev_fini+0x40/0x58
[    9.789767] sp : ffff00000af1bcf0
[    9.793108] x29: ffff00000af1bcf0 x28: 0000000000000000
[    9.798473] x27: 0000000000000000 x26: ffff000008f66630
[    9.803838] x25: 0000000000000000 x24: ffff0000095abb98
[    9.809203] x23: ffff8017db92fe00 x22: ffff8017d2b13000
[    9.814568] x21: ffffffffffffffea x20: ffff8017d2f80018
[    9.819933] x19: ffff8017d28a0018 x18: ffffffffffffffff
[    9.825297] x17: 0000000000000000 x16: 0000000000000000
[    9.830662] x15: ffff0000092296c8 x14: ffff00008939970f
[    9.836026] x13: ffff00000939971d x12: ffff000009229940
[    9.841391] x11: ffff0000085f8fc0 x10: ffff00000af1b9a0
[    9.846756] x9 : 000000000000000d x8 : 6620657a696c6169
[    9.852121] x7 : ffff8017d3340580 x6 : ffff8017d4168000
[    9.857486] x5 : 0000000000000000 x4 : ffff8017db92fb20
[    9.862850] x3 : 0000000000002690 x2 : ffff8017d3340480
[    9.868214] x1 : 0000000000000028 x0 : 0000000000000002
[    9.873580] Process kworker/16:1 (pid: 293, stack limit = 0x(____ptrval____))
[    9.880788] Call trace:
[    9.883252]  drm_mode_object_put+0x0/0x20
[    9.887297]  hibmc_unload+0x1c/0x80
[    9.890815]  hibmc_pci_probe+0x170/0x3c8
[    9.894773]  local_pci_probe+0x3c/0xb0
[    9.898555]  work_for_cpu_fn+0x18/0x28
[    9.902337]  process_one_work+0x1e0/0x318
[    9.906382]  worker_thread+0x228/0x450
[    9.910164]  kthread+0x128/0x130
[    9.913418]  ret_from_fork+0x10/0x18
[    9.917024] Code: a94153f3 a8c27bfd d65f03c0 d503201f (f9400c01)
[    9.923180] ---[ end trace 2695ffa0af5be375 ]---

---
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_fbdev.c |    1 +
 1 file changed, 1 insertion(+)

@@ -122,6 +122,7 @@ static int hibmc_drm_fb_create(struct dr
 	hi_fbdev->fb = hibmc_framebuffer_init(priv->dev, &mode_cmd, gobj);
 	if (IS_ERR(hi_fbdev->fb)) {
 		ret = PTR_ERR(hi_fbdev->fb);
+		hi_fbdev->fb = NULL;
 		DRM_ERROR("failed to initialize framebuffer: %d\n", ret);
 		goto out_release_fbi;
 	}

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Nicholas Mc Guire <[email protected]>

[ Upstream commit c5d59528e24ad22500347b199d52b9368e686a42 ]

altera_hw_filt_init() which calls append_internal() assumes that the node was successfully linked in while in fact it can silently fail. So the call-site needs to set return to -ENOMEM on append_internal() returning NULL and exit through the err path.

---
 drivers/media/pci/cx23885/altera-ci.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

@@ -665,6 +665,10 @@ static int altera_hw_filt_init(struct al
 		}
 
 		temp_int = append_internal(inter);
+		if (!temp_int) {
+			ret = -ENOMEM;
+			goto err;
+		}
 		inter->filts_used = 1;
 		inter->dev = config->dev;
 		inter->fpga_rw = config->fpga_rw;

@@ -699,6 +703,7 @@ err:
 		     __func__, ret);
 
 	kfree(pid_filt);
+	kfree(inter);
 
 	return ret;
 }

@@ -733,6 +738,10 @@ int altera_ci_init(struct altera_ci_conf
 		}
 
 		temp_int = append_internal(inter);
+		if (!temp_int) {
+			ret = -ENOMEM;
+			goto err;
+		}
 		inter->cis_used = 1;
 		inter->dev = config->dev;
 		inter->fpga_rw = config->fpga_rw;

@@ -801,6 +810,7 @@ err:
 	ci_dbg_print("%s: Cannot initialize CI: Error %d.\n", __func__, ret);
 
 	kfree(state);
+	kfree(inter);
 
 	return ret;
 }

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lucas Stach <[email protected]>

[ Upstream commit 1f32061e843205f6fe8404d5100d5adcec334e75 ]

On a decoder instance, after the profile has been parsed from the stream __v4l2_ctrl_s_ctrl() is called to notify userspace about changes in the read-only profile control. This ends up calling back into the CODA driver where a missing check on the s_ctrl caused the profile information that has just been parsed from the stream to be overwritten with the default baseline profile.

Later on the driver fails to enable frame reordering, based on the wrong profile information.

profile/level controls)

---
 drivers/media/platform/coda/coda-common.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -1686,7 +1686,8 @@ static int coda_s_ctrl(struct v4l2_ctrl
 		break;
 	case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
 		/* TODO: switch between baseline and constrained baseline */
-		ctx->params.h264_profile_idc = 66;
+		if (ctx->inst_type == CODA_INST_ENCODER)
+			ctx->params.h264_profile_idc = 66;
 		break;
 	case V4L2_CID_MPEG_VIDEO_H264_LEVEL:
 		/* nothing to do, this is set by the encoder */

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Dengcheng Zhu <[email protected]>

[ Upstream commit dc57aaf95a516f70e2d527d8287a0332c481a226 ]

After changing CPU online status, it will not be sent any IPIs such as in __flush_cache_all() on software coherency systems. Do this before disabling local IRQ.

Patchwork: https://patchwork.linux-mips.org/patch/20571/

---
 arch/mips/kernel/crash.c         |    3 +++
 arch/mips/kernel/machine_kexec.c |    3 +++
 2 files changed, 6 insertions(+)

@@ -36,6 +36,9 @@ static void crash_shutdown_secondary(voi
 	if (!cpu_online(cpu))
 		return;
 
+	/* We won't be sent IPIs any more. */
+	set_cpu_online(cpu, false);
+
 	local_irq_disable();
 	if (!cpumask_test_cpu(cpu, &cpus_in_crash))
 		crash_save_cpu(regs, cpu);

@@ -118,6 +118,9 @@ machine_kexec(struct kimage *image)
 			*ptr = (unsigned long) phys_to_virt(*ptr);
 	}
 
+	/* Mark offline BEFORE disabling local irq. */
+	set_cpu_online(smp_processor_id(), false);
+
 	/*
 	 * we do not want to be bothered.
 	 */

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Joel Stanley <[email protected]>

[ Upstream commit ee9d21b3b3583712029a0db65a4b7c081d08d3b3 ]

When building with clang crt0's _zimage_start is not marked weak, which breaks the build when linking the kernel image:

 $ objdump -t arch/powerpc/boot/crt0.o |grep _zimage_start$
 0000000000000058 g       .text  0000000000000000 _zimage_start

ld: arch/powerpc/boot/wrapper.a(crt0.o): in function '_zimage_start':
(.text+0x58): multiple definition of '_zimage_start'; arch/powerpc/boot/pseries-head.o:(.text+0x0): first defined here

Clang requires the .weak directive to appear after the symbol is declared. The binutils manual says:

This directive sets the weak attribute on the comma separated list of symbol names. If the symbols do not already exist, they will be created.

So it appears this is different with clang. The only reference I could see for this was an OpenBSD mailing list post[1].

Changing it to be after the declaration fixes building with Clang, and still works with GCC.

 $ objdump -t arch/powerpc/boot/crt0.o |grep _zimage_start$
 0000000000000058  w      .text	0000000000000000 _zimage_start

Reported to clang as https://bugs.llvm.org/show_bug.cgi?id=38921

[1] https://groups.google.com/forum/#!topic/fa.openbsd.tech/PAgKKen2YCY

---
 arch/powerpc/boot/crt0.S |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -47,8 +47,10 @@ p_end:		.long	_end
 p_pstack:	.long	_platform_stack_top
 #endif
 
-	.weak	_zimage_start
 	.globl	_zimage_start
+	/* Clang appears to require the .weak directive to be after the symbol
+	 * is defined. See https://bugs.llvm.org/show_bug.cgi?id=38921  */
+	.weak	_zimage_start
 _zimage_start:
 	.globl	_zimage_start_lib
 _zimage_start_lib:

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Rashmica Gupta <[email protected]>

[ Upstream commit 3f7daf3d7582dc6628ac40a9045dd1bbd80c5f35 ]

When hot-removing memory release_mem_region_adjustable() splits iomem resources if they are not the exact size of the memory being hot-deleted. Adding this memory back to the kernel adds a new resource.

Eg a node has memory 0x0 - 0xfffffffff. Hot-removing 1GB from 0xf40000000 results in the single resource 0x0-0xfffffffff being split into two resources: 0x0-0xf3fffffff and 0xf80000000-0xfffffffff.

When we hot-add the memory back we now have three resources:
0x0-0xf3fffffff, 0xf40000000-0xf7fffffff, and 0xf80000000-0xfffffffff.

This is an issue if we try to remove some memory that overlaps resources. Eg when trying to remove 2GB at address 0xf40000000, release_mem_region_adjustable() fails as it expects the chunk of memory to be within the boundaries of a single resource. We then get the
warning: "Unable to release resource" and attempting to use memtrace again gives us this error: "bash: echo: write error: Resource temporarily unavailable"

This patch makes memtrace remove memory in chunks that are always the same size from an address that is always equal to end_of_memory - n*size, for some n. So hotremoving and hotadding memory of different sizes will now not attempt to remove memory that spans multiple resources.

---
 arch/powerpc/platforms/powernv/memtrace.c |   21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

@@ -119,17 +119,15 @@ static bool memtrace_offline_pages(u32 n
 	walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
 			  change_memblock_state);
 
-	lock_device_hotplug();
-	remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
-	unlock_device_hotplug();
 
 	return true;
 }
 
 static u64 memtrace_alloc_node(u32 nid, u64 size)
 {
-	u64 start_pfn, end_pfn, nr_pages;
+	u64 start_pfn, end_pfn, nr_pages, pfn;
 	u64 base_pfn;
+	u64 bytes = memory_block_size_bytes();
 
 	if (!NODE_DATA(nid) || !node_spanned_pages(nid))
 		return 0;

@@ -142,8 +140,21 @@ static u64 memtrace_alloc_node(u32 nid,
 	end_pfn = round_down(end_pfn - nr_pages, nr_pages);
 
 	for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) {
-		if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true)
+		if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) {
+			/*
+			 * Remove memory in memory block size chunks so that
+			 * iomem resources are always split to the same size and
+			 * we never try to remove memory that spans two iomem
+			 * resources.
+			 */
+			lock_device_hotplug();
+			end_pfn = base_pfn + nr_pages;
+			for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) {
+				remove_memory(nid, pfn << PAGE_SHIFT, bytes);
+			}
+			unlock_device_hotplug();
 			return base_pfn << PAGE_SHIFT;
+		}
 	}
 
 	return 0;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Huacai Chen <[email protected]>

[ Upstream commit 2794f688b2c336e0da85e9f91fed33febbd9f54a ]

Call pcie_bus_configure_settings() on MIPS, like for other platforms. The function pcie_bus_configure_settings() makes sure the MPS (Max Payload Size) across the bus is uniform and provides the ability to tune the MRSS (Max Read Request Size) and MPS (Max Payload Size) to higher performance values. Some devices will not operate properly if these aren't set correctly because the firmware doesn't always do it.

Patchwork: https://patchwork.linux-mips.org/patch/20649/

---
 arch/mips/pci/pci-legacy.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -127,8 +127,12 @@ static void pcibios_scanbus(struct pci_c
 	if (pci_has_flag(PCI_PROBE_ONLY)) {
 		pci_bus_claim_resources(bus);
 	} else {
+		struct pci_bus *child;
+
 		pci_bus_size_bridges(bus);
 		pci_bus_assign_resources(bus);
+		list_for_each_entry(child, &bus->children, node)
+			pcie_bus_configure_settings(child);
 	}
 	pci_bus_add_devices(bus);
 }

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Phil Elwell <[email protected]>

[ Upstream commit 8344498721059754e09d30fe255a12dab8fb03ef ]

The SC16IS752 is a dual-channel device. The two channels are largely independent, but the IRQ signals are wired together as an open-drain, active low signal which will be driven low while either of the channels requires attention, which can be for significant periods of time until operations complete and the interrupt can be acknowledged. In that respect it is should be treated as a true level-sensitive IRQ.

The kernel, however, needs to be able to exit interrupt context in order to use I2C or SPI to access the device registers (which may involve sleeping). Therefore the interrupt needs to be masked out or paused in some way.

The usual way to manage sleeping from within an interrupt handler is to use a threaded interrupt handler - a regular interrupt routine does the minimum amount of work needed to triage the interrupt before waking the interrupt service thread. If the threaded IRQ is marked as IRQF_ONESHOT the kernel will automatically mask out the interrupt until the thread runs to completion. The sc16is7xx driver used to use a threaded IRQ, but a patch switched to using a kthread_worker in order to set realtime priorities on the handler thread and for other optimisations. The end result is non-threaded IRQ that schedules some work then returns IRQ_HANDLED, making the kernel think that all IRQ processing has completed.

The work-around to prevent a constant stream of interrupts is to mark the interrupt as edge-sensitive rather than level-sensitive, but interpreting an active-low source as a falling-edge source requires care to prevent a total cessation of interrupts. Whereas an edge-triggering source will generate a new edge for every interrupt condition a level-triggering source will keep the signal at the interrupting level until it no longer requires attention; in other words, the host won't see another edge until all interrupt conditions are cleared. It is therefore vital that the interrupt handler does not exit with an outstanding interrupt condition, otherwise the kernel will not receive another interrupt unless some other operation causes the interrupt state on the device to be cleared.

The existing sc16is7xx driver has a very simple interrupt "thread" (kthread_work job) that processes interrupts on each channel in turn until there are no more. If both channels are active and the first channel starts interrupting while the handler for the second channel is running then it will not be detected and an IRQ stall ensues. This could be handled easily if there was a shared IRQ status register, or a convenient way to determine if the IRQ had been deasserted for any length of time, but both appear to be lacking.

Avoid this problem (or at least make it much less likely to happen) by reducing the granularity of per-channel interrupt processing to one condition per iteration, only exiting the overall loop when both channels are no longer interrupting.

---
 drivers/tty/serial/sc16is7xx.c |   19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

@@ -662,7 +662,7 @@ static void sc16is7xx_handle_tx(struct u
 		uart_write_wakeup(port);
 }
 
-static void sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
+static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
 {
 	struct uart_port *port = &s->p[portno].port;
 

@@ -671,7 +671,7 @@ static void sc16is7xx_port_irq(struct sc
 
 		iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG);
 		if (iir & SC16IS7XX_IIR_NO_INT_BIT)
-			break;
+			return false;
 
 		iir &= SC16IS7XX_IIR_ID_MASK;
 

@@ -693,16 +693,23 @@ static void sc16is7xx_port_irq(struct sc
 					    port->line, iir);
 			break;
 		}
-	} while (1);
+	} while (0);
+	return true;
 }
 
 static void sc16is7xx_ist(struct kthread_work *ws)
 {
 	struct sc16is7xx_port *s = to_sc16is7xx_port(ws, irq_work);
-	int i;
 
-	for (i = 0; i < s->devtype->nr_uart; ++i)
-		sc16is7xx_port_irq(s, i);
+	while (1) {
+		bool keep_polling = false;
+		int i;
+
+		for (i = 0; i < s->devtype->nr_uart; ++i)
+			keep_polling |= sc16is7xx_port_irq(s, i);
+		if (!keep_polling)
+			break;
+	}
 }
 
 static irqreturn_t sc16is7xx_irq(int irq, void *dev_id)

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Marco Felsch <[email protected]>

[ Upstream commit bd24db04101f45a9c1d874fe21b0c7eab7bcadec ]

The driver ignored the width alignment which exists due to the UYVY colorspace format. Fix the width alignment and make use of the the provided v4l2 helper function to set the width, height and all alignments in one.

---
 drivers/media/i2c/tvp5150.c |   14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

@@ -900,9 +900,6 @@ static int tvp5150_set_selection(struct
 
 	/* tvp5150 has some special limits */
 	rect.left = clamp(rect.left, 0, TVP5150_MAX_CROP_LEFT);
-	rect.width = clamp_t(unsigned int, rect.width,
-			     TVP5150_H_MAX - TVP5150_MAX_CROP_LEFT - rect.left,
-			     TVP5150_H_MAX - rect.left);
 	rect.top = clamp(rect.top, 0, TVP5150_MAX_CROP_TOP);
 
 	/* Calculate height based on current standard */

@@ -916,9 +913,16 @@ static int tvp5150_set_selection(struct
 	else
 		hmax = TVP5150_V_MAX_OTHERS;
 
-	rect.height = clamp_t(unsigned int, rect.height,
+	/*
+	 * alignments:
+	 *  - width = 2 due to UYVY colorspace
+	 *  - height, image = no special alignment
+	 */
+	v4l_bound_align_image(&rect.width,
+			      TVP5150_H_MAX - TVP5150_MAX_CROP_LEFT - rect.left,
+			      TVP5150_H_MAX - rect.left, 1, &rect.height,
 			      hmax - TVP5150_MAX_CROP_TOP - rect.top,
-			      hmax - rect.top);
+			      hmax - rect.top, 0, 0);
 
 	tvp5150_write(sd, TVP5150_VERT_BLANKING_START, rect.top);
 	tvp5150_write(sd, TVP5150_VERT_BLANKING_STOP,

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Breno Leitao <[email protected]>

[ Upstream commit 693b31b2fc1636f0aa7af53136d3b49f6ad9ff39 ]

Test tm-tmspr might exit before all threads stop executing, because it just waits for the very last thread to join before proceeding/exiting.

This patch makes sure that all threads that were created will join before proceeding/exiting.

This patch also guarantees that the amount of threads being created is equal to thread_num.

---
 tools/testing/selftests/powerpc/tm/tm-tmspr.c |   27 ++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

@@ -98,7 +98,7 @@ void texasr(void *in)
 
 int test_tmspr()
 {
-	pthread_t 	thread;
+	pthread_t	*thread;
 	int	   	thread_num;
 	unsigned long	i;
 

@@ -107,21 +107,28 @@ int test_tmspr()
 	/* To cause some context switching */
 	thread_num = 10 * sysconf(_SC_NPROCESSORS_ONLN);
 
+	thread = malloc(thread_num * sizeof(pthread_t));
+	if (thread == NULL)
+		return EXIT_FAILURE;
+
 	/* Test TFIAR and TFHAR */
-	for (i = 0 ; i < thread_num ; i += 2){
-		if (pthread_create(&thread, NULL, (void*)tfiar_tfhar, (void *)i))
+	for (i = 0; i < thread_num; i += 2) {
+		if (pthread_create(&thread[i], NULL, (void *)tfiar_tfhar,
+				   (void *)i))
 			return EXIT_FAILURE;
 	}
-	if (pthread_join(thread, NULL) != 0)
-		return EXIT_FAILURE;
-
 	/* Test TEXASR */
-	for (i = 0 ; i < thread_num ; i++){
-		if (pthread_create(&thread, NULL, (void*)texasr, (void *)i))
+	for (i = 1; i < thread_num; i += 2) {
+		if (pthread_create(&thread[i], NULL, (void *)texasr, (void *)i))
 			return EXIT_FAILURE;
 	}
-	if (pthread_join(thread, NULL) != 0)
-		return EXIT_FAILURE;
+
+	for (i = 0; i < thread_num; i++) {
+		if (pthread_join(thread[i], NULL) != 0)
+			return EXIT_FAILURE;
+	}
+
+	free(thread);
 
 	if (passed)
 		return 0;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Alexandru Ardelean <[email protected]>

[ Upstream commit 4ee033301c898dd0835d035d0e0eb768a3d35da1 ]

Fixes commit 17be2a2905a6ec9aa27cd59521495e2f490d2af0 ("staging: iio:
ad7606: replace range/range_available with corresponding scale").

The AD7606 devices don't have a 2.5V voltage range, they have 5V & 10V voltage range, which is selectable via the gpio_range descriptor.

The scales also seem to have been miscomputed, because when they were applied to the raw values, the results differ from the expected values. After checking the ADC transfer function in the datasheet, these were re-computed.

---
 drivers/staging/iio/adc/ad7606.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

@@ -26,9 +26,12 @@
 
 #include "ad7606.h"
 
-/* Scales are computed as 2.5/2**16 and 5/2**16 respectively */
+/*
+ * Scales are computed as 5000/32768 and 10000/32768 respectively,
+ * so that when applied to the raw values they provide mV values
+ */
 static const unsigned int scale_avail[2][2] = {
-	{0, 38147}, {0, 76294}
+	{0, 152588}, {0, 305176}
 };
 
 static int ad7606_reset(struct ad7606_state *st)

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Dominique Martinet <[email protected]>

[ Upstream commit b4dc44b3cac9e8327e0655f530ed0c46f2e6214c ]

the 9p client code overwrites our glock.client_id pointing to a static buffer by an allocated string holding the network provided value which we do not care about; free and reset the value as appropriate.

This is almost identical to the leak in v9fs_file_getlock() fixed by Al Viro in commit ce85dd58ad5a6 ("9p: we are leaking glock.client_id in v9fs_file_getlock()"), which was returned as an error by a coverity false positive -- while we are here attempt to make the code slightly more robust to future change of the net/9p/client code and hopefully more clear to coverity that there is no problem.

---
 fs/9p/vfs_file.c |   16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

@@ -204,6 +204,14 @@ static int v9fs_file_do_lock(struct file
 			break;
 		if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0)
 			break;
+		/*
+		 * p9_client_lock_dotl overwrites flock.client_id with the
+		 * server message, free and reuse the client name
+		 */
+		if (flock.client_id != fid->clnt->name) {
+			kfree(flock.client_id);
+			flock.client_id = fid->clnt->name;
+		}
 	}
 
 	/* map 9p status to VFS status */

@@ -235,6 +243,8 @@ out_unlock:
 		locks_lock_file_wait(filp, fl);
 		fl->fl_type = fl_type;
 	}
+	if (flock.client_id != fid->clnt->name)
+		kfree(flock.client_id);
 out:
 	return res;
 }

@@ -269,7 +279,7 @@ static int v9fs_file_getlock(struct file
 
 	res = p9_client_getlock_dotl(fid, &glock);
 	if (res < 0)
-		return res;
+		goto out;
 	/* map 9p lock type to os lock type */
 	switch (glock.type) {
 	case P9_LOCK_TYPE_RDLCK:

@@ -290,7 +300,9 @@ static int v9fs_file_getlock(struct file
 			fl->fl_end = glock.start + glock.length - 1;
 		fl->fl_pid = -glock.proc_id;
 	}
-	kfree(glock.client_id);
+out:
+	if (glock.client_id != fid->clnt->name)
+		kfree(glock.client_id);
 	return res;
 }
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Dominique Martinet <[email protected]>

[ Upstream commit 62e3941776fea8678bb8120607039410b1b61a65 ]

p9stat_free is more of a cleanup function than a 'free' function as it only frees the content of the struct; there are chances of use-after-free if it is improperly used (e.g. p9stat_free called twice as it used to be possible to)

Clearing dangling pointers makes the function idempotent and safer to use.

---
 net/9p/protocol.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -46,10 +46,15 @@ p9pdu_writef(struct p9_fcall *pdu, int p
 void p9stat_free(struct p9_wstat *stbuf)
 {
 	kfree(stbuf->name);
+	stbuf->name = NULL;
 	kfree(stbuf->uid);
+	stbuf->uid = NULL;
 	kfree(stbuf->gid);
+	stbuf->gid = NULL;
 	kfree(stbuf->muid);
+	stbuf->muid = NULL;
 	kfree(stbuf->extension);
+	stbuf->extension = NULL;
 }
 EXPORT_SYMBOL(p9stat_free);
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Young_X <[email protected]>

commit e4f3aa2e1e67bb48dfbaaf1cad59013d5a5bc276 upstream.

There is another cast from unsigned long to int which causes a bounds check to fail with specially crafted input. The value is then used as an index in the slot array in cdrom_slot_status().

This issue is similar to CVE-2018-16658 and CVE-2018-10940.

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

@@ -2441,7 +2441,7 @@ static int cdrom_ioctl_select_disc(struc
 		return -ENOSYS;
 
 	if (arg != CDSL_CURRENT && arg != CDSL_NONE) {
-		if ((int)arg >= cdi->capacity)
+		if (arg >= cdi->capacity)
 			return -EINVAL;
 	}
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Quinn Tran <[email protected]>

commit 7c388f91ec1a59b0ed815b07b90536e2d57e1e1f upstream.

Remove stale debug trace.

---
 drivers/scsi/qla2xxx/tcm_qla2xxx.c |    4 ----
 1 file changed, 4 deletions(-)

@@ -693,10 +693,6 @@ static int tcm_qla2xxx_queue_status(stru
 	cmd->sg_cnt = 0;
 	cmd->offset = 0;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
-	if (cmd->trc_flags & TRC_XMIT_STATUS) {
-		pr_crit("Multiple calls for status = %p.\n", cmd);
-		dump_stack();
-	}
 	cmd->trc_flags |= TRC_XMIT_STATUS;
 
 	if (se_cmd->data_direction == DMA_FROM_DEVICE) {

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Kirill Tkhai <[email protected]>

commit d2d2d4fb1f54eff0f3faa9762d84f6446a4bc5d0 upstream.

After we found req in request_find() and released the lock, everything may happen with the req in parallel:

cpu0                              cpu1
fuse_dev_do_write()               fuse_dev_do_write()
  req = request_find(fpq, ...)    ...
  spin_unlock(&fpq->lock)         ...
  ...                             req = request_find(fpq, oh.unique)
  ...                             spin_unlock(&fpq->lock)
  queue_interrupt(&fc->iq, req);   ...
  ...                              ...
  ...                              ...
  request_end(fc, req);
    fuse_put_request(fc, req);

... queue_interrupt(&fc->iq, req);

---
 fs/fuse/dev.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -1874,16 +1874,20 @@ static ssize_t fuse_dev_do_write(struct
 
 	/* Is it an interrupt reply? */
 	if (req->intr_unique == oh.unique) {
+		__fuse_get_request(req);
 		spin_unlock(&fpq->lock);
 
 		err = -EINVAL;
-		if (nbytes != sizeof(struct fuse_out_header))
+		if (nbytes != sizeof(struct fuse_out_header)) {
+			fuse_put_request(fc, req);
 			goto err_finish;
+		}
 
 		if (oh.error == -ENOSYS)
 			fc->no_interrupt = 1;
 		else if (oh.error == -EAGAIN)
 			queue_interrupt(&fc->iq, req);
+		fuse_put_request(fc, req);
 
 		fuse_copy_finish(cs);
 		return nbytes;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Amir Goldstein <[email protected]>

commit 6cd078702f2f33cb6b19a682de3e9184112f1a46 upstream.

linking a non-copied-up file into a non-copied-up parent results in a nested call to mutex_lock_interruptible(&oi->lock). Fix this by copying up target parent before ovl_nlink_start(), same as done in ovl_rename().

~/unionmount-testsuite$ ./run --ov -s ~/unionmount-testsuite$ ln /mnt/a/foo100 /mnt/a/dir100/

WARNING: possible recursive locking detected
--------------------------------------------
ln/1545 is trying to acquire lock:
00000000bcce7c4c (&ovl_i_lock_key[depth]){+.+.}, at:

     ovl_copy_up_start+0x28/0x7d
 but task is already holding lock:
 0000000026d73d5b (&ovl_i_lock_key[depth]){+.+.}, at:
     ovl_nlink_start+0x3c/0xc1

[SzM: this seems to be a false positive, but doing the copy-up first is harmless and removes the lockdep splat]

---
 fs/overlayfs/dir.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -595,6 +595,11 @@ static int ovl_link(struct dentry *old,
 	if (err)
 		goto out_drop_write;
 
+	err = ovl_copy_up(new->d_parent);
+	if (err)
+		goto out_drop_write;
+
+
 	err = ovl_nlink_start(old, &locked);
 	if (err)
 		goto out_drop_write;

4.14-stable review patch. If anyone has any objections, please let me know.

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

[ Upstream commit d06f8a2f1befb5a3d0aa660ab1c05e9b744456ea ]

Masking/unmasking the CPU UART irq in CP0_Status (and redirecting it to other CPUs) may cause interrupts be lost, especially in multi-package machines (Package-0's UART irq cannot be delivered to others). So make mask_loongson_irq() and unmask_loongson_irq() be no-ops.

The original problem (UART IRQ may deliver to any core) is also because of masking/unmasking the CPU UART irq in CP0_Status. So it is safe to remove all of the stuff.

Patchwork: https://patchwork.linux-mips.org/patch/20433/

---
 arch/mips/loongson64/loongson-3/irq.c | 43 ++-------------------------
 1 file changed, 3 insertions(+), 40 deletions(-)

index cbeb20f9fc95..2e115ab66a00 100644
@@ -102,45 +102,8 @@ static struct irqaction cascade_irqaction = {
 	.name = "cascade",
 };
 
-static inline void mask_loongson_irq(struct irq_data *d)
-{
-	clear_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));
-	irq_disable_hazard();
-
-	/* Workaround: UART IRQ may deliver to any core */
-	if (d->irq == LOONGSON_UART_IRQ) {
-		int cpu = smp_processor_id();
-		int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node;
-		int core_id = cpu_logical_map(cpu) % loongson_sysconf.cores_per_node;
-		u64 intenclr_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_INTENCLR);
-		u64 introuter_lpc_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_LPC);
-
-		*(volatile u32 *)intenclr_addr = 1 << 10;
-		*(volatile u8 *)introuter_lpc_addr = 0x10 + (1<<core_id);
-	}
-}
-
-static inline void unmask_loongson_irq(struct irq_data *d)
-{
-	/* Workaround: UART IRQ may deliver to any core */
-	if (d->irq == LOONGSON_UART_IRQ) {
-		int cpu = smp_processor_id();
-		int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node;
-		int core_id = cpu_logical_map(cpu) % loongson_sysconf.cores_per_node;
-		u64 intenset_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_INTENSET);
-		u64 introuter_lpc_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_LPC);
-
-		*(volatile u32 *)intenset_addr = 1 << 10;
-		*(volatile u8 *)introuter_lpc_addr = 0x10 + (1<<core_id);
-	}
-
-	set_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));
-	irq_enable_hazard();
-}
+static inline void mask_loongson_irq(struct irq_data *d) { }
+static inline void unmask_loongson_irq(struct irq_data *d) { }
 
  /* For MIPS IRQs which shared by all cores */
 static struct irq_chip loongson_irq_chip = {

@@ -183,7 +146,7 @@ void __init mach_init_irq(void)
 	chip->irq_set_affinity = plat_set_irq_affinity;
 
 	irq_set_chip_and_handler(LOONGSON_UART_IRQ,
-			&loongson_irq_chip, handle_level_irq);
+			&loongson_irq_chip, handle_percpu_irq);
 
 	/* setup HT1 irq */
 	setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction);

2.17.1

4.14-stable review patch. If anyone has any objections, please let me know.

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

[ Upstream commit 360fe725f8849aaddc53475fef5d4a0c439b05ae ]

After commit e509bd7da149dc349160 ("genirq: Allow migration of chained interrupts by installing default action") Loongson-3 fails at here:

setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction);

This is because both chained_action and cascade_irqaction don't have IRQF_SHARED flag. This will cause Loongson-3 resume fails because HPET timer interrupt can't be delivered during S3. So we set the irqchip of the chained irq to loongson_irq_chip which doesn't disable the chained irq in CP0.Status.

Patchwork: https://patchwork.linux-mips.org/patch/20434/

---
 arch/mips/include/asm/mach-loongson64/irq.h |  2 +-
 arch/mips/loongson64/loongson-3/irq.c       | 13 +++----------
 2 files changed, 4 insertions(+), 11 deletions(-)

index 3644b68c0ccc..be9f727a9328 100644
@@ -10,7 +10,7 @@
 #define MIPS_CPU_IRQ_BASE 56
 
 #define LOONGSON_UART_IRQ   (MIPS_CPU_IRQ_BASE + 2) /* UART */
-#define LOONGSON_HT1_IRQ    (MIPS_CPU_IRQ_BASE + 3) /* HT1 */
+#define LOONGSON_BRIDGE_IRQ (MIPS_CPU_IRQ_BASE + 3) /* CASCADE */
 #define LOONGSON_TIMER_IRQ  (MIPS_CPU_IRQ_BASE + 7) /* CPU Timer */
 
 #define LOONGSON_HT1_CFG_BASE		loongson_sysconf.ht_control_base

index 2e115ab66a00..5605061f5f98 100644
@@ -96,12 +96,6 @@ void mach_irq_dispatch(unsigned int pending)
 	}
 }
 
-static struct irqaction cascade_irqaction = {
-	.handler = no_action,
-	.flags = IRQF_NO_SUSPEND,
-	.name = "cascade",
-};
-
 static inline void mask_loongson_irq(struct irq_data *d) { }
 static inline void unmask_loongson_irq(struct irq_data *d) { }
 

@@ -147,11 +141,10 @@ void __init mach_init_irq(void)
 
 	irq_set_chip_and_handler(LOONGSON_UART_IRQ,
 			&loongson_irq_chip, handle_percpu_irq);
+	irq_set_chip_and_handler(LOONGSON_BRIDGE_IRQ,
+			&loongson_irq_chip, handle_percpu_irq);
 
-	/* setup HT1 irq */
-	setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction);
-
-	set_c0_status(STATUSF_IP2 | STATUSF_IP6);
+	set_c0_status(STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP6);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

2.17.1

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Enric Balletbo i Serra <[email protected]>

commit 665636b2940d0897c4130253467f5e8c42eea392 upstream.

Fixes the signedness bug returning '(-22)' on the return type by removing the sanity checker in rockchip_ddrclk_get_parent(). The function should return and unsigned value only and it's safe to remove the sanity checker as the core functions that call get_parent like clk_core_get_parent_by_index already ensures the validity of the clk index returned (index >= core->num_parents).

---
 drivers/clk/rockchip/clk-ddr.c |    4 ----
 1 file changed, 4 deletions(-)

@@ -80,16 +80,12 @@ static long rockchip_ddrclk_sip_round_ra
 static u8 rockchip_ddrclk_get_parent(struct clk_hw *hw)
 {
 	struct rockchip_ddrclk *ddrclk = to_rockchip_ddrclk_hw(hw);
-	int num_parents = clk_hw_get_num_parents(hw);
 	u32 val;
 
 	val = clk_readl(ddrclk->reg_base +
 			ddrclk->mux_offset) >> ddrclk->mux_shift;
 	val &= GENMASK(ddrclk->mux_width - 1, 0);
 
-	if (val >= num_parents)
-		return -EINVAL;
-
 	return val;
 }
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Chris Packham <[email protected]>

commit 00c5a926af12a9f0236928dab3dc9faf621406a1 upstream.

The correct fieldbit value for the NAND PLL reload trigger is 27.

---
 drivers/clk/mvebu/clk-corediv.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -72,7 +72,7 @@ static const struct clk_corediv_desc mve
 };
 
 static const struct clk_corediv_desc mv98dx3236_corediv_desc[] = {
-	{ .mask = 0x0f, .offset = 6, .fieldbit = 26 }, /* NAND clock */
+	{ .mask = 0x0f, .offset = 6, .fieldbit = 27 }, /* NAND clock */
 };
 
 #define to_corediv_clk(p) container_of(p, struct clk_corediv, hw)

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lubomir Rintel <[email protected]>

commit 786fa584eda86d6598db3b87c61dc81f68808d11 upstream.

When the "xclk" clock was added, it was made mandatory. This broke the driver on an OLPC plaform which doesn't know such clock. Make it optional.

Tested on a OLPC XO-1 laptop.

---
 drivers/media/i2c/ov7670.c |   30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

@@ -1612,23 +1612,29 @@ static int ov7670_probe(struct i2c_clien
 			info->pclk_hb_disable = true;
 	}
 
-	info->clk = devm_clk_get(&client->dev, "xclk");
-	if (IS_ERR(info->clk))
-		return PTR_ERR(info->clk);
-	ret = clk_prepare_enable(info->clk);
-	if (ret)
-		return ret;
+	info->clk = devm_clk_get(&client->dev, "xclk"); /* optional */
+	if (IS_ERR(info->clk)) {
+		ret = PTR_ERR(info->clk);
+		if (ret == -ENOENT)
+			info->clk = NULL;
+		else
+			return ret;
+	}
+	if (info->clk) {
+		ret = clk_prepare_enable(info->clk);
+		if (ret)
+			return ret;
+		info->clock_speed = clk_get_rate(info->clk) / 1000000;
+		if (info->clock_speed < 10 || info->clock_speed > 48) {
+			ret = -EINVAL;
+			goto clk_disable;
+		}
+	}
 
 	ret = ov7670_init_gpio(client, info);
 	if (ret)
 		goto clk_disable;
 
-	info->clock_speed = clk_get_rate(info->clk) / 1000000;
-	if (info->clock_speed < 10 || info->clock_speed > 48) {
-		ret = -EINVAL;
-		goto clk_disable;
-	}
-
 	/* Make sure it's an ov7670 */
 	ret = ov7670_detect(sd);
 	if (ret) {

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Ilya Dryomov <[email protected]>

commit 94e6992bb560be8bffb47f287194adf070b57695 upstream.

If the read is large enough, we end up spinning in the messenger:

libceph: osd0 192.168.122.1:6801 io error
libceph: osd0 192.168.122.1:6801 io error
libceph: osd0 192.168.122.1:6801 io error

This is a receive side limit, so only reads were affected.

---
 include/linux/ceph/libceph.h |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

@@ -81,7 +81,13 @@ struct ceph_options {
 
 #define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
-#define CEPH_MSG_MAX_DATA_LEN	(16*1024*1024)
+
+/*
+ * Handle the largest possible rbd object in one message.
+ * There is no limit on the size of cephfs objects, but it has to obey
+ * rsize and wsize mount options anyway.
+ */
+#define CEPH_MSG_MAX_DATA_LEN	(32*1024*1024)
 
 #define CEPH_AUTH_NAME_DEFAULT   "guest"
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Mikulas Patocka <[email protected]>

commit 3c6c6a7878d00a3ac997a779c5b9861ff25dfcc8 upstream.

The code for manual bit triple is not endian-clean. It builds the variable "hostdword" using byte accesses, therefore we must read the variable with "le32_to_cpu".

The patch also enables (hardware or software) bit triple only if the image is monochrome (image->depth). If we want to blit full-color image, we shouldn't use the triple code.

---
 drivers/video/fbdev/aty/mach64_accel.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -345,7 +345,7 @@ void atyfb_imageblit(struct fb_info *inf
 		 * since Rage 3D IIc we have DP_HOST_TRIPLE_EN bit
 		 * this hwaccelerated triple has an issue with not aligned data
 		 */
-		if (M64_HAS(HW_TRIPLE) && image->width % 8 == 0)
+		if (image->depth == 1 && M64_HAS(HW_TRIPLE) && image->width % 8 == 0)
 			pix_width |= DP_HOST_TRIPLE_EN;
 	}
 

@@ -382,7 +382,7 @@ void atyfb_imageblit(struct fb_info *inf
 	src_bytes = (((image->width * image->depth) + 7) / 8) * image->height;
 
 	/* manual triple each pixel */
-	if (info->var.bits_per_pixel == 24 && !(pix_width & DP_HOST_TRIPLE_EN)) {
+	if (image->depth == 1 && info->var.bits_per_pixel == 24 && !(pix_width & DP_HOST_TRIPLE_EN)) {
 		int inbit, outbit, mult24, byte_id_in_dword, width;
 		u8 *pbitmapin = (u8*)image->data, *pbitmapout;
 		u32 hostdword;

@@ -415,7 +415,7 @@ void atyfb_imageblit(struct fb_info *inf
 				}
 			}
 			wait_for_fifo(1, par);
-			aty_st_le32(HOST_DATA0, hostdword, par);
+			aty_st_le32(HOST_DATA0, le32_to_cpu(hostdword), par);
 		}
 	} else {
 		u32 *pbitmap, dwords = (src_bytes + 3) / 4;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Mikulas Patocka <[email protected]>

commit c09bcc91bb94ed91f1391bffcbe294963d605732 upstream.

Reading the registers without waiting for engine idle returns unpredictable values. These unpredictable values result in display corruption - if atyfb_imageblit reads the content of DP_PIX_WIDTH with the bit DP_HOST_TRIPLE_EN set (from previous invocation), the driver would never ever clear the bit, resulting in display corruption.

We don't want to wait for idle because it would degrade performance, so this patch modifies the driver so that it never reads accelerator registers.

HOST_CNTL doesn't have to be read, we can just write it with HOST_BYTE_ALIGN because no other part of the driver cares if HOST_BYTE_ALIGN is set.

DP_PIX_WIDTH is written in the functions atyfb_copyarea and atyfb_fillrect with the default value and in atyfb_imageblit with the value set according to the source image data.

---
 drivers/video/fbdev/aty/mach64_accel.c |   22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

@@ -127,7 +127,7 @@ void aty_init_engine(struct atyfb_par *p
 
 	/* set host attributes */
 	wait_for_fifo(13, par);
-	aty_st_le32(HOST_CNTL, 0, par);
+	aty_st_le32(HOST_CNTL, HOST_BYTE_ALIGN, par);
 
 	/* set pattern attributes */
 	aty_st_le32(PAT_REG0, 0, par);

@@ -233,7 +233,8 @@ void atyfb_copyarea(struct fb_info *info
 		rotation = rotation24bpp(dx, direction);
 	}
 
-	wait_for_fifo(4, par);
+	wait_for_fifo(5, par);
+	aty_st_le32(DP_PIX_WIDTH, par->crtc.dp_pix_width, par);
 	aty_st_le32(DP_SRC, FRGD_SRC_BLIT, par);
 	aty_st_le32(SRC_Y_X, (sx << 16) | sy, par);
 	aty_st_le32(SRC_HEIGHT1_WIDTH1, (width << 16) | area->height, par);

@@ -269,7 +270,8 @@ void atyfb_fillrect(struct fb_info *info
 		rotation = rotation24bpp(dx, DST_X_LEFT_TO_RIGHT);
 	}
 
-	wait_for_fifo(3, par);
+	wait_for_fifo(4, par);
+	aty_st_le32(DP_PIX_WIDTH, par->crtc.dp_pix_width, par);
 	aty_st_le32(DP_FRGD_CLR, color, par);
 	aty_st_le32(DP_SRC,
 		    BKGD_SRC_BKGD_CLR | FRGD_SRC_FRGD_CLR | MONO_SRC_ONE,

@@ -284,7 +286,7 @@ void atyfb_imageblit(struct fb_info *inf
 {
 	struct atyfb_par *par = (struct atyfb_par *) info->par;
 	u32 src_bytes, dx = image->dx, dy = image->dy, width = image->width;
-	u32 pix_width_save, pix_width, host_cntl, rotation = 0, src, mix;
+	u32 pix_width, rotation = 0, src, mix;
 
 	if (par->asleep)
 		return;

@@ -296,8 +298,7 @@ void atyfb_imageblit(struct fb_info *inf
 		return;
 	}
 
-	pix_width = pix_width_save = aty_ld_le32(DP_PIX_WIDTH, par);
-	host_cntl = aty_ld_le32(HOST_CNTL, par) | HOST_BYTE_ALIGN;
+	pix_width = par->crtc.dp_pix_width;
 
 	switch (image->depth) {
 	case 1:

@@ -370,12 +371,11 @@ void atyfb_imageblit(struct fb_info *inf
 		mix = FRGD_MIX_D_XOR_S | BKGD_MIX_D;
 	}
 
-	wait_for_fifo(6, par);
-	aty_st_le32(DP_WRITE_MASK, 0xFFFFFFFF, par);
+	wait_for_fifo(5, par);
 	aty_st_le32(DP_PIX_WIDTH, pix_width, par);
 	aty_st_le32(DP_MIX, mix, par);
 	aty_st_le32(DP_SRC, src, par);
-	aty_st_le32(HOST_CNTL, host_cntl, par);
+	aty_st_le32(HOST_CNTL, HOST_BYTE_ALIGN, par);
 	aty_st_le32(DST_CNTL, DST_Y_TOP_TO_BOTTOM | DST_X_LEFT_TO_RIGHT | rotation, par);
 
 	draw_rect(dx, dy, width, image->height, par);

@@ -424,8 +424,4 @@ void atyfb_imageblit(struct fb_info *inf
 			aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
 		}
 	}
-
-	/* restore pix_width */
-	wait_for_fifo(1, par);
-	aty_st_le32(DP_PIX_WIDTH, pix_width_save, par);
 }

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Gustavo A. R. Silva <[email protected]>

commit e9a2310fb689151166df7fd9971093362d34bd79 upstream.

There is a potential execution path in which function platform_get_resource() returns NULL. If this happens, we will end up having a NULL pointer dereference.

Fix this by replacing devm_ioremap with devm_ioremap_resource, which has the NULL check and the memory region request.

This code was detected with the help of Coccinelle.

---
 drivers/clk/hisilicon/reset.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -109,9 +109,8 @@ struct hisi_reset_controller *hisi_reset
 		return NULL;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rstc->membase = devm_ioremap(&pdev->dev,
-				res->start, resource_size(res));
-	if (!rstc->membase)
+	rstc->membase = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(rstc->membase))
 		return NULL;
 
 	spin_lock_init(&rstc->lock);

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Ming Lei <[email protected]>

commit 8dc765d438f1e42b3e8227b3b09fad7d73f4ec9a upstream.

c2856ae2f315d ("blk-mq: quiesce queue before freeing queue") has already fixed this race, however the implied synchronize_rcu() in blk_mq_quiesce_queue() can slow down LUN probe a lot, so caused performance regression.

Then 1311326cf4755c7 ("blk-mq: avoid to synchronize rcu inside blk_cleanup_queue()") tried to quiesce queue for avoiding unnecessary synchronize_rcu()
only when queue initialization is done, because it is usual to see lots of inexistent LUNs which need to be probed.

However, turns out it isn't safe to quiesce queue only when queue initialization is done. Because when one SCSI command is completed, the user of sending command can be waken up immediately, then the scsi device may be removed, meantime the run queue in scsi_end_request() is still in-progress, so kernel panic can be caused.

In Red Hat QE lab, there are several reports about this kind of kernel panic triggered during kernel booting.

This patch tries to address the issue by grabing one queue usage counter during freeing one request and the following run queue.

---
 block/blk-core.c        |    5 ++---
 drivers/scsi/scsi_lib.c |    8 ++++++++
 2 files changed, 10 insertions(+), 3 deletions(-)

@@ -671,9 +671,8 @@ void blk_cleanup_queue(struct request_qu
 	 * dispatch may still be in-progress since we dispatch requests
 	 * from more than one contexts.
 	 *
-	 * No need to quiesce queue if it isn't initialized yet since
-	 * blk_freeze_queue() should be enough for cases of passthrough
-	 * request.
+	 * We rely on driver to deal with the race in case that queue
+	 * initialization isn't done.
 	 */
 	if (q->mq_ops && blk_queue_init_done(q))
 		blk_mq_quiesce_queue(q);

@@ -683,6 +683,12 @@ static bool scsi_end_request(struct requ
 		 */
 		scsi_mq_uninit_cmd(cmd);
 
+		/*
+		 * queue is still alive, so grab the ref for preventing it
+		 * from being cleaned up during running queue.
+		 */
+		percpu_ref_get(&q->q_usage_counter);
+
 		__blk_mq_end_request(req, error);
 
 		if (scsi_target(sdev)->single_lun ||

@@ -690,6 +696,8 @@ static bool scsi_end_request(struct requ
 			kblockd_schedule_work(&sdev->requeue_work);
 		else
 			blk_mq_run_hw_queues(q, true);
+
+		percpu_ref_put(&q->q_usage_counter);
 	} else {
 		unsigned long flags;
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Changwei Ge <[email protected]>

commit 29aa30167a0a2e6045a0d6d2e89d8168132333d5 upstream.

Somehow, file system metadata was corrupted, which causes ocfs2_check_dir_entry() to fail in function ocfs2_dir_foreach_blk_el().

According to the original design intention, if above happens we should skip the problematic block and continue to retrieve dir entry. But there is obviouse misuse of brelse around related code.

After failure of ocfs2_check_dir_entry(), current code just moves to next position and uses the problematic buffer head again and again during which the problematic buffer head is released for multiple times. I suppose, this a serious issue which is long-lived in ocfs2. This may cause other file systems which is also used in a the same host insane.

So we should also consider about bakcporting this patch into linux -stable.

---
 fs/ocfs2/dir.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -1896,8 +1896,7 @@ static int ocfs2_dir_foreach_blk_el(stru
 				/* On error, skip the f_pos to the
 				   next block. */
 				ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
-				brelse(bh);
-				continue;
+				break;
 			}
 			if (le64_to_cpu(de->inode)) {
 				unsigned char d_type = DT_UNKNOWN;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Andrea Arcangeli <[email protected]>

commit ac5b2c18911ffe95c08d69273917f90212cf5659 upstream.

THP allocation might be really disruptive when allocated on NUMA system with the local node full or hard to reclaim. Stefan has posted an allocation stall report on 4.12 based SLES kernel which suggests the same issue:

kvm: page allocation stalls for 194572ms, order:9, mode:0x4740ca(__GFP_HIGHMEM|__GFP_IO|__GFP_FS|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE|__GFP_MOVABLE|__GFP_DIRECT_RECLAIM), nodemask=(null) kvm cpuset=/ mems_allowed=0-1

  CPU: 10 PID: 84752 Comm: kvm Tainted: G        W 4.12.0+98-ph <a href="/view.php?id=1" title="[geschlossen] Integration Ramdisk" class="resolved">0000001</a> SLE15 (unreleased)
  Hardware name: Supermicro SYS-1029P-WTRT/X11DDW-NT, BIOS 2.0 12/05/2017
  Call Trace:
   dump_stack+0x5c/0x84
   warn_alloc+0xe0/0x180
   __alloc_pages_slowpath+0x820/0xc90
   __alloc_pages_nodemask+0x1cc/0x210
   alloc_pages_vma+0x1e5/0x280
   do_huge_pmd_wp_page+0x83f/0xf00
   __handle_mm_fault+0x93d/0x1060
   handle_mm_fault+0xc6/0x1b0
   __do_page_fault+0x230/0x430
   do_page_fault+0x2a/0x70
   page_fault+0x7b/0x80
   [...]
  Mem-Info:
  active_anon:126315487 inactive_anon:1612476 isolated_anon:5
   active_file:60183 inactive_file:245285 isolated_file:0
   unevictable:15657 dirty:286 writeback:1 unstable:0
   slab_reclaimable:75543 slab_unreclaimable:2509111
   mapped:81814 shmem:31764 pagetables:370616 bounce:0
   free:32294031 free_pcp:6233 free_cma:0
  Node 0 active_anon:254680388kB inactive_anon:1112760kB active_file:240648kB inactive_file:981168kB unevictable:13368kB isolated(anon):0kB isolated(file):0kB mapped:280240kB dirty:1144kB writeback:0kB shmem:95832kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 81225728kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
  Node 1 active_anon:250583072kB inactive_anon:5337144kB active_file:84kB inactive_file:0kB unevictable:49260kB isolated(anon):20kB isolated(file):0kB mapped:47016kB dirty:0kB writeback:4kB shmem:31224kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 31897600kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no

The defrag mode is "madvise" and from the above report it is clear that the THP has been allocated for MADV_HUGEPAGA vma.

Andrea has identified that the main source of the problem is __GFP_THISNODE usage:

: The problem is that direct compaction combined with the NUMA : __GFP_THISNODE logic in mempolicy.c is telling reclaim to swap very : hard the local node, instead of failing the allocation if there's no : THP available in the local node.
:
: Such logic was ok until __GFP_THISNODE was added to the THP allocation : path even with MPOL_DEFAULT.
:
: The idea behind the __GFP_THISNODE addition, is that it is better to : provide local memory in PAGE_SIZE units than to use remote NUMA THP : backed memory. That largely depends on the remote latency though, on : threadrippers for example the overhead is relatively low in my : experience.
:
: The combination of __GFP_THISNODE and __GFP_DIRECT_RECLAIM results in : extremely slow qemu startup with vfio, if the VM is larger than the : size of one host NUMA node. This is because it will try very hard to : unsuccessfully swapout get_user_pages pinned pages as result of the : __GFP_THISNODE being set, instead of falling back to PAGE_SIZE : allocations and instead of trying to allocate THP on other nodes (it : would be even worse without vfio type1 GUP pins of course, except it'd : be swapping heavily instead).

Fix this by removing __GFP_THISNODE for THP requests which are requesting the direct reclaim. This effectivelly reverts 5265047ac301 on the grounds that the zone/node reclaim was known to be disruptive due to premature reclaim when there was memory free. While it made sense at the time for HPC workloads without NUMA awareness on rare machines, it was ultimately harmful in the majority of cases. The existing behaviour is similar, if not as widespare as it applies to a corner case but crucially, it cannot be tuned around like zone_reclaim_mode can. The default behaviour should always be to cause the least harm for the common case.

If there are specialised use cases out there that want zone_reclaim_mode in specific cases, then it can be built on top. Longterm we should consider a memory policy which allows for the node reclaim like behavior for the specific memory ranges which would allow a

[1] http://lkml.kernel.org/r/[email protected]

Mel said:

: Both patches look correct to me but I'm responding to this one because : it's the fix. The change makes sense and moves further away from the : severe stalling behaviour we used to see with both THP and zone reclaim : mode.
:
: I put together a basic experiment with usemem configured to reference a : buffer multiple times that is 80% the size of main memory on a 2-socket : box with symmetric node sizes and defrag set to "always". The defrag : setting is not the default but it would be functionally similar to : accessing a buffer with madvise(MADV_HUGEPAGE). Usemem is configured to : reference the buffer multiple times and while it's not an interesting : workload, it would be expected to complete reasonably quickly as it fits : within memory. The results were;
:
: usemem
: vanilla noreclaim-v1

: Amean     Elapsd-1       42.78 (   0.00%)       26.87 (  37.18%)
: Amean     Elapsd-3       27.55 (   0.00%)        7.44 (  73.00%)
: Amean     Elapsd-4        5.72 (   0.00%)        5.69 (   0.45%)

:
: This shows the elapsed time in seconds for 1 thread, 3 threads and 4 : threads referencing buffers 80% the size of memory. With the patches : applied, it's 37.18% faster for the single thread and 73% faster with two : threads. Note that 4 threads showing little difference does not indicate : the problem is related to thread counts. It's simply the case that 4 : threads gets spread so their workload mostly fits in one node. :
: The overall view from /proc/vmstats is more startling
:
: 4.19.0-rc1 4.19.0-rc1
: vanillanoreclaim-v1r1
: Minor Faults 35593425 708164
: Major Faults 484088 36

: Swap Ins                    3772837           0
: Swap Outs                   3932295           0
:
: Massive amounts of swap in/out without the patch
:
: Direct pages scanned        6013214           0
: Kswapd pages scanned              0           0
: Kswapd pages reclaimed            0           0
: Direct pages reclaimed      4033009           0

:
: Lots of reclaim activity without the patch
:
: Kswapd efficiency 100% 100%
: Kswapd velocity 0.000 0.000
: Direct efficiency 67% 100%
: Direct velocity 11191.956 0.000
:
: Mostly from direct reclaim context as you'd expect without the patch. :
: Page writes by reclaim 3932314.000 0.000

: Page writes file                 19           0
: Page writes anon            3932295           0
: Page reclaim immediate        42336           0

:
: Writes from reclaim context is never good but the patch eliminates it. :
: We should never have default behaviour to thrash the system for such a : basic workload. If zone reclaim mode behaviour is ever desired but on a : single task instead of a global basis then the sensible option is to build : a mempolicy that enforces that behaviour.

This was a severe regression compared to previous kernels that made important workloads unusable and it starts when __GFP_THISNODE was added to THP allocations under MADV_HUGEPAGE. It is not a significant risk to go to the previous behavior before __GFP_THISNODE was added, it worked like that for years.

This was simply an optimization to some lucky workloads that can fit in a single node, but it ended up breaking the VM for others that can't possibly fit in a single node, so going back is safe.

---
 mm/mempolicy.c |   32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

@@ -2012,8 +2012,36 @@ alloc_pages_vma(gfp_t gfp, int order, st
 		nmask = policy_nodemask(gfp, pol);
 		if (!nmask || node_isset(hpage_node, *nmask)) {
 			mpol_cond_put(pol);
-			page = __alloc_pages_node(hpage_node,
-						gfp | __GFP_THISNODE, order);
+			/*
+			 * We cannot invoke reclaim if __GFP_THISNODE
+			 * is set. Invoking reclaim with
+			 * __GFP_THISNODE set, would cause THP
+			 * allocations to trigger heavy swapping
+			 * despite there may be tons of free memory
+			 * (including potentially plenty of THP
+			 * already available in the buddy) on all the
+			 * other NUMA nodes.
+			 *
+			 * At most we could invoke compaction when
+			 * __GFP_THISNODE is set (but we would need to
+			 * refrain from invoking reclaim even if
+			 * compaction returned COMPACT_SKIPPED because
+			 * there wasn't not enough memory to succeed
+			 * compaction). For now just avoid
+			 * __GFP_THISNODE instead of limiting the
+			 * allocation path to a strict and single
+			 * compaction invocation.
+			 *
+			 * Supposedly if direct reclaim was enabled by
+			 * the caller, the app prefers THP regardless
+			 * of the node it comes from so this would be
+			 * more desiderable behavior than only
+			 * providing THP originated from the local
+			 * node in such case.
+			 */
+			if (!(gfp & __GFP_DIRECT_RECLAIM))
+				gfp |= __GFP_THISNODE;
+			page = __alloc_pages_node(hpage_node, gfp, order);
 			goto out;
 		}
 	}

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Arnd Bergmann <[email protected]>

commit be2e1c9dcf76886a83fb1c433a316e26d4ca2550 upstream.

I noticed during the creation of another bugfix that the BCH_CONST_PARAMS option that is set by DOCG3 breaks setting variable parameters for any other users of the BCH library code.

The only other user we have today is the MTD_NAND software BCH implementation (most flash controllers use hardware BCH these days and are not affected). I considered removing BCH_CONST_PARAMS entirely because of the inherent conflict, but according to the description in lib/bch.c there is a significant performance benefit in keeping it.

To avoid the immediate problem of the conflict between MTD_NAND_BCH and DOCG3, this only sets the constant parameters if MTD_NAND_BCH is disabled, which should fix the problem for all cases that are affected. This should also work for all stable kernels.

Note that there is only one machine that actually seems to use the DOCG3 driver (arch/arm/mach-pxa/mioa701.c), so most users should have the driver disabled, but it almost certainly shows up if we wanted to test random kernels on machines that use software BCH in MTD.

---
 drivers/mtd/devices/Kconfig |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -206,7 +206,7 @@ comment "Disk-On-Chip Device Drivers"
 config MTD_DOCG3
 	tristate "M-Systems Disk-On-Chip G3"
 	select BCH
-	select BCH_CONST_PARAMS
+	select BCH_CONST_PARAMS if !MTD_NAND_BCH
 	select BITREVERSE
 	---help---
 	  This provides an MTD device driver for the M-Systems DiskOnChip

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Steven Rostedt (VMware) <[email protected]>

commit 15035388439f892017d38b05214d3cda6578af64 upstream.

When running function tracing on a Linux guest running on VMware Workstation, the guest would crash. This is due to tracing of the sched_clock internal call of the VMware vmware_sched_clock(), which causes an infinite recursion within the tracing code (clock calls must not be traced).

Make vmware_sched_clock() not traced by ftrace.

---
 arch/x86/kernel/cpu/vmware.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(
 }
 early_param("no-vmw-sched-clock", setup_vmw_sched_clock);
 
-static unsigned long long vmware_sched_clock(void)
+static unsigned long long notrace vmware_sched_clock(void)
 {
 	unsigned long long ns;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Kelley <[email protected]>

commit 1de72c706488b7be664a601cf3843bd01e327e58 upstream.

Hyper-V emulation of the PIT has a quirk such that the normal PIT shutdown path doesn't work, because clearing the counter register restarts the timer.

Disable the counter clearing on PIT shutdown.

---
 arch/x86/kernel/cpu/mshyperv.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -20,6 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kexec.h>
+#include <linux/i8253.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv.h>

@@ -243,6 +244,16 @@ static void __init ms_hyperv_init_platfo
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 
+	/*
+	 * Hyper-V VMs have a PIT emulation quirk such that zeroing the
+	 * counter register during PIT shutdown restarts the PIT. So it
+	 * continues to interrupt @18.2 HZ. Setting i8253_clear_counter
+	 * to false tells pit_shutdown() not to zero the counter so that
+	 * the PIT really is shutdown. Generation 2 VMs don't have a PIT,
+	 * and setting this value has no effect.
+	 */
+	i8253_clear_counter_on_shutdown = false;
+
 #if IS_ENABLED(CONFIG_HYPERV)
 	/*
 	 * Setup the hook to get control post apic initialization.

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: H. Peter Anvin (Intel) <[email protected]>

commit d0ffb805b729322626639336986bc83fc2e60871 upstream.

Alpha has had c_ispeed and c_ospeed, but still set speeds in c_cflags using arbitrary flags. Because BOTHER is not defined, the general Linux code doesn't allow setting arbitrary baud rates, and because CBAUDEX == 0, we can have an array overrun of the baud_rate[] table in drivers/tty/tty_baudrate.c if (c_cflags & CBAUD) == 037.

Resolve both problems by #defining BOTHER to 037 on Alpha.

However, userspace still needs to know if setting BOTHER is actually safe given legacy kernels (does anyone actually care about that on Alpha anymore?), so enable the TCGETS2/TCSETS*2 ioctls on Alpha, even though they use the same structure. Define struct termios2 just for compatibility; it is the exact same structure as struct termios. In a future patchset, this will be cleaned up so the uapi headers are usable from libc.

---
 arch/alpha/include/asm/termios.h       |    8 +++++++-
 arch/alpha/include/uapi/asm/ioctls.h   |    5 +++++
 arch/alpha/include/uapi/asm/termbits.h |   17 +++++++++++++++++
 3 files changed, 29 insertions(+), 1 deletion(-)

@@ -73,9 +73,15 @@
 })
 
 #define user_termios_to_kernel_termios(k, u) \
-	copy_from_user(k, u, sizeof(struct termios))
+	copy_from_user(k, u, sizeof(struct termios2))
 
 #define kernel_termios_to_user_termios(u, k) \
+	copy_to_user(u, k, sizeof(struct termios2))
+
+#define user_termios_to_kernel_termios_1(k, u) \
+	copy_from_user(k, u, sizeof(struct termios))
+
+#define kernel_termios_to_user_termios_1(u, k) \
 	copy_to_user(u, k, sizeof(struct termios))
 
 #endif	/* _ALPHA_TERMIOS_H */

@@ -32,6 +32,11 @@
 #define TCXONC		_IO('t', 30)
 #define TCFLSH		_IO('t', 31)
 
+#define TCGETS2		_IOR('T', 42, struct termios2)
+#define TCSETS2		_IOW('T', 43, struct termios2)
+#define TCSETSW2	_IOW('T', 44, struct termios2)
+#define TCSETSF2	_IOW('T', 45, struct termios2)
+
 #define TIOCSWINSZ	_IOW('t', 103, struct winsize)
 #define TIOCGWINSZ	_IOR('t', 104, struct winsize)
 #define	TIOCSTART	_IO('t', 110)		/* start output, like ^Q */

@@ -26,6 +26,19 @@ struct termios {
 	speed_t c_ospeed;		/* output speed */
 };
 
+/* Alpha has identical termios and termios2 */
+
+struct termios2 {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_cc[NCCS];		/* control characters */
+	cc_t c_line;			/* line discipline (== c_cc[19]) */
+	speed_t c_ispeed;		/* input speed */
+	speed_t c_ospeed;		/* output speed */
+};
+
 /* Alpha has matching termios and ktermios */
 
 struct ktermios {

@@ -148,6 +161,7 @@ struct ktermios {
 #define B3000000  00034
 #define B3500000  00035
 #define B4000000  00036
+#define BOTHER    00037
 
 #define CSIZE	00001400
 #define   CS5	00000000

@@ -165,6 +179,9 @@ struct ktermios {
 #define CMSPAR	  010000000000		/* mark or space (stick) parity */
 #define CRTSCTS	  020000000000		/* flow control */
 
+#define CIBAUD	07600000
+#define IBSHIFT	16
+
 /* c_lflag bits */
 #define ISIG	0x00000080
 #define ICANON	0x00000100

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lu Fengqi <[email protected]>

commit fcd5e74288f7d36991b1f0fb96b8c57079645e38 upstream.

When running generic/475, we may get the following warning in dmesg:

[ 6902.102154] WARNING: CPU: 3 PID: 18013 at fs/btrfs/extent-tree.c:9776 btrfs_free_block_groups+0x2af/0x3b0 [btrfs]
[ 6902.109160] CPU: 3 PID: 18013 Comm: umount Tainted: G        W  O      4.19.0-rc8+ #8
[ 6902.110971] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
[ 6902.112857] RIP: 0010:btrfs_free_block_groups+0x2af/0x3b0 [btrfs]
[ 6902.118921] RSP: 0018:ffffc9000459bdb0 EFLAGS: 00010286
[ 6902.120315] RAX: ffff880175050bb0 RBX: ffff8801124a8000 RCX: 0000000000170007
[ 6902.121969] RDX: 0000000000000002 RSI: 0000000000170007 RDI: ffffffff8125fb74
[ 6902.123716] RBP: ffff880175055d10 R08: 0000000000000000 R09: 0000000000000000
[ 6902.125417] R10: 0000000000000000 R11: 0000000000000000 R12: ffff880175055d88
[ 6902.127129] R13: ffff880175050bb0 R14: 0000000000000000 R15: dead000000000100
[ 6902.129060] FS:  00007f4507223780(0000) GS:ffff88017ba00000(0000) knlGS:0000000000000000
[ 6902.130996] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 6902.132558] CR2: 00005623599cac78 CR3: 000000014b700001 CR4: 00000000003606e0
[ 6902.134270] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 6902.135981] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 6902.137836] Call Trace:
[ 6902.138939]  close_ctree+0x171/0x330 [btrfs]
[ 6902.140181]  ? kthread_stop+0x146/0x1f0
[ 6902.141277]  generic_shutdown_super+0x6c/0x100
[ 6902.142517]  kill_anon_super+0x14/0x30
[ 6902.143554]  btrfs_kill_super+0x13/0x100 [btrfs]
[ 6902.144790]  deactivate_locked_super+0x2f/0x70
[ 6902.146014]  cleanup_mnt+0x3b/0x70
[ 6902.147020]  task_work_run+0x9e/0xd0
[ 6902.148036]  do_syscall_64+0x470/0x600
[ 6902.149142]  ? trace_hardirqs_off_thunk+0x1a/0x1c
[ 6902.150375]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 6902.151640] RIP: 0033:0x7f45077a6a7b
[ 6902.157324] RSP: 002b:00007ffd589f3e68 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6
[ 6902.159187] RAX: 0000000000000000 RBX: 000055e8eec732b0 RCX: 00007f45077a6a7b
[ 6902.160834] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 000055e8eec73490
[ 6902.162526] RBP: 0000000000000000 R08: 000055e8eec734b0 R09: 00007ffd589f26c0
[ 6902.164141] R10: 0000000000000000 R11: 0000000000000246 R12: 000055e8eec73490
[ 6902.165815] R13: 00007f4507ac61a4 R14: 0000000000000000 R15: 00007ffd589f40d8
[ 6902.167553] irq event stamp: 0
[ 6902.168998] hardirqs last  enabled at (0): [<0000000000000000>]           (null)
[ 6902.170731] hardirqs last disabled at (0): [<ffffffff810cd810>] copy_process.part.55+0x3b0/0x1f00
[ 6902.172773] softirqs last  enabled at (0): [<ffffffff810cd810>] copy_process.part.55+0x3b0/0x1f00
[ 6902.174671] softirqs last disabled at (0): [<0000000000000000>]           (null)
[ 6902.176407] ---[ end trace 463138c2986b275c ]---
[ 6902.177636] BTRFS info (device dm-3): space_info 4 has 273465344 free, is not full
[ 6902.179453] BTRFS info (device dm-3): space_info total=276824064, used=4685824, pinned=18446744073708158976, reserved=0, may_use=0, readonly=65536

In the above line there's "pinned=18446744073708158976" which is an unsigned u64 value of -1392640, an obvious underflow.

When transaction_kthread is running cleanup_transaction(), another fsstress is running btrfs_commit_transaction(). The btrfs_finish_extent_commit() may get the same range as btrfs_destroy_pinned_extent() got, which causes the pinned underflow.

---
 fs/btrfs/disk-io.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

@@ -4428,13 +4428,23 @@ static int btrfs_destroy_pinned_extent(s
 	unpin = pinned_extents;
 again:
 	while (1) {
+		/*
+		 * The btrfs_finish_extent_commit() may get the same range as
+		 * ours between find_first_extent_bit and clear_extent_dirty.
+		 * Hence, hold the unused_bg_unpin_mutex to avoid double unpin
+		 * the same extent range.
+		 */
+		mutex_lock(&fs_info->unused_bg_unpin_mutex);
 		ret = find_first_extent_bit(unpin, 0, &start, &end,
 					    EXTENT_DIRTY, NULL);
-		if (ret)
+		if (ret) {
+			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 			break;
+		}
 
 		clear_extent_dirty(unpin, start, end);
 		btrfs_error_unpin_extent_range(fs_info, start, end);
+		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 		cond_resched();
 	}
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Filipe Manana <[email protected]>

commit 11023d3f5fdf89bba5e1142127701ca6e6014587 upstream.

If we attempt to deduplicate the last block of a file A into the middle of a file B, and file A's size is not a multiple of the block size, we end rounding the deduplication length to 0 bytes, to avoid the data corruption issue fixed by commit de02b9f6bb65 ("Btrfs: fix data corruption when deduplicating between different files"). However a length of zero will cause the insertion of an extent state with a start value greater (by 1) then the end value, leading to a corrupt extent state that will trigger a warning and cause chaos such as an infinite loop during inode eviction. Example trace:

 [96049.833585] ------------[ cut here ]------------
 [96049.833714] WARNING: CPU: 0 PID: 24448 at fs/btrfs/extent_io.c:436 insert_state+0x101/0x120 [btrfs]
 [96049.833767] CPU: 0 PID: 24448 Comm: xfs_io Not tainted 4.19.0-rc7-btrfs-next-39 #1
 [96049.833768] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014
 [96049.833780] RIP: 0010:insert_state+0x101/0x120 [btrfs]
 [96049.833783] RSP: 0018:ffffafd2c3707af0 EFLAGS: 00010282
 [96049.833785] RAX: 0000000000000000 RBX: 000000000004dfff RCX: 0000000000000006
 [96049.833786] RDX: 0000000000000007 RSI: ffff99045c143230 RDI: ffff99047b2168a0
 [96049.833787] RBP: ffff990457851cd0 R08: 0000000000000001 R09: 0000000000000000
 [96049.833787] R10: ffffafd2c3707ab8 R11: 0000000000000000 R12: ffff9903b93b12c8
 [96049.833788] R13: 000000000004e000 R14: ffffafd2c3707b80 R15: ffffafd2c3707b78
 [96049.833790] FS:  00007f5c14e7d700(0000) GS:ffff99047b200000(0000) knlGS:0000000000000000
 [96049.833791] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 [96049.833792] CR2: 00007f5c146abff8 CR3: 0000000115f4c004 CR4: 00000000003606f0
 [96049.833795] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 [96049.833796] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 [96049.833796] Call Trace:
 [96049.833809]  __set_extent_bit+0x46c/0x6a0 [btrfs]
 [96049.833823]  lock_extent_bits+0x6b/0x210 [btrfs]
 [96049.833831]  ? _raw_spin_unlock+0x24/0x30
 [96049.833841]  ? test_range_bit+0xdf/0x130 [btrfs]
 [96049.833853]  lock_extent_range+0x8e/0x150 [btrfs]
 [96049.833864]  btrfs_double_extent_lock+0x78/0xb0 [btrfs]
 [96049.833875]  btrfs_extent_same_range+0x14e/0x550 [btrfs]
 [96049.833885]  ? rcu_read_lock_sched_held+0x3f/0x70
 [96049.833890]  ? __kmalloc_node+0x2b0/0x2f0
 [96049.833899]  ? btrfs_dedupe_file_range+0x19a/0x280 [btrfs]
 [96049.833909]  btrfs_dedupe_file_range+0x270/0x280 [btrfs]
 [96049.833916]  vfs_dedupe_file_range_one+0xd9/0xe0
 [96049.833919]  vfs_dedupe_file_range+0x131/0x1b0
 [96049.833924]  do_vfs_ioctl+0x272/0x6e0
 [96049.833927]  ? __fget+0x113/0x200
 [96049.833931]  ksys_ioctl+0x70/0x80
 [96049.833933]  __x64_sys_ioctl+0x16/0x20
 [96049.833937]  do_syscall_64+0x60/0x1b0
 [96049.833939]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
 [96049.833941] RIP: 0033:0x7f5c1478ddd7
 [96049.833943] RSP: 002b:00007ffe15b196a8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010
 [96049.833945] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5c1478ddd7
 [96049.833946] RDX: 00005625ece322d0 RSI: 00000000c0189436 RDI: 0000000000000004
 [96049.833947] RBP: 0000000000000000 R08: 00007f5c14a46f48 R09: 0000000000000040
 [96049.833948] R10: 0000000000000541 R11: 0000000000000202 R12: 0000000000000000
 [96049.833949] R13: 0000000000000000 R14: 0000000000000004 R15: 00005625ece322d0
 [96049.833954] irq event stamp: 6196
 [96049.833956] hardirqs last  enabled at (6195): [<ffffffff91b00663>] console_unlock+0x503/0x640
 [96049.833958] hardirqs last disabled at (6196): [<ffffffff91a037dd>] trace_hardirqs_off_thunk+0x1a/0x1c
 [96049.833959] softirqs last  enabled at (6114): [<ffffffff92600370>] __do_softirq+0x370/0x421
 [96049.833964] softirqs last disabled at (6095): [<ffffffff91a8dd4d>] irq_exit+0xcd/0xe0
 [96049.833965] ---[ end trace db7b05f01b7fa10c ]---
 [96049.935816] R13: 0000000000000000 R14: 00005562e5259240 R15: 00007ffff092b910
 [96049.935822] irq event stamp: 6584
 [96049.935823] hardirqs last  enabled at (6583): [<ffffffff91b00663>] console_unlock+0x503/0x640
 [96049.935825] hardirqs last disabled at (6584): [<ffffffff91a037dd>] trace_hardirqs_off_thunk+0x1a/0x1c
 [96049.935827] softirqs last  enabled at (6328): [<ffffffff92600370>] __do_softirq+0x370/0x421
 [96049.935828] softirqs last disabled at (6313): [<ffffffff91a8dd4d>] irq_exit+0xcd/0xe0
 [96049.935829] ---[ end trace db7b05f01b7fa123 ]---
 [96049.935840] ------------[ cut here ]------------
 [96049.936065] WARNING: CPU: 1 PID: 24463 at fs/btrfs/extent_io.c:436 insert_state+0x101/0x120 [btrfs]
 [96049.936107] CPU: 1 PID: 24463 Comm: umount Tainted: G        W         4.19.0-rc7-btrfs-next-39 #1
 [96049.936108] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014
 [96049.936117] RIP: 0010:insert_state+0x101/0x120 [btrfs]
 [96049.936119] RSP: 0018:ffffafd2c3637bc0 EFLAGS: 00010282
 [96049.936120] RAX: 0000000000000000 RBX: 000000000004dfff RCX: 0000000000000006
 [96049.936121] RDX: 0000000000000007 RSI: ffff990445cf88e0 RDI: ffff99047b2968a0
 [96049.936122] RBP: ffff990457851cd0 R08: 0000000000000001 R09: 0000000000000000
 [96049.936123] R10: ffffafd2c3637b88 R11: 0000000000000000 R12: ffff9904574301e8
 [96049.936124] R13: 000000000004e000 R14: ffffafd2c3637c50 R15: ffffafd2c3637c48
 [96049.936125] FS:  00007fe4b87e72c0(0000) GS:ffff99047b280000(0000) knlGS:0000000000000000
 [96049.936126] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 [96049.936128] CR2: 00005562e52618d8 CR3: 00000001151c8005 CR4: 00000000003606e0
 [96049.936129] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 [96049.936131] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 [96049.936131] Call Trace:
 [96049.936141]  __set_extent_bit+0x46c/0x6a0 [btrfs]
 [96049.936154]  lock_extent_bits+0x6b/0x210 [btrfs]
 [96049.936167]  btrfs_evict_inode+0x1e1/0x5a0 [btrfs]
 [96049.936172]  evict+0xbf/0x1c0
 [96049.936174]  dispose_list+0x51/0x80
 [96049.936176]  evict_inodes+0x193/0x1c0
 [96049.936180]  generic_shutdown_super+0x3f/0x110
 [96049.936182]  kill_anon_super+0xe/0x30
 [96049.936189]  btrfs_kill_super+0x13/0x100 [btrfs]
 [96049.936191]  deactivate_locked_super+0x3a/0x70
 [96049.936193]  cleanup_mnt+0x3b/0x80
 [96049.936195]  task_work_run+0x93/0xc0
 [96049.936198]  exit_to_usermode_loop+0xfa/0x100
 [96049.936201]  do_syscall_64+0x17f/0x1b0
 [96049.936202]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
 [96049.936204] RIP: 0033:0x7fe4b80cfb37
 [96049.936206] RSP: 002b:00007ffff092b688 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6
 [96049.936207] RAX: 0000000000000000 RBX: 00005562e5259060 RCX: 00007fe4b80cfb37
 [96049.936208] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 00005562e525faa0
 [96049.936209] RBP: 00005562e525faa0 R08: 00005562e525f770 R09: 0000000000000015
 [96049.936210] R10: 00000000000006b4 R11: 0000000000000246 R12: 00007fe4b85d1e64
 [96049.936211] R13: 0000000000000000 R14: 00005562e5259240 R15: 00007ffff092b910
 [96049.936211] R13: 0000000000000000 R14: 00005562e5259240 R15: 00007ffff092b910
 [96049.936216] irq event stamp: 6616
 [96049.936219] hardirqs last  enabled at (6615): [<ffffffff91b00663>] console_unlock+0x503/0x640
 [96049.936219] hardirqs last disabled at (6616): [<ffffffff91a037dd>] trace_hardirqs_off_thunk+0x1a/0x1c
 [96049.936222] softirqs last  enabled at (6328): [<ffffffff92600370>] __do_softirq+0x370/0x421
 [96049.936222] softirqs last disabled at (6313): [<ffffffff91a8dd4d>] irq_exit+0xcd/0xe0
 [96049.936223] ---[ end trace db7b05f01b7fa124 ]---

The second stack trace, from inode eviction, is repeated forever due to the infinite loop during eviction.

This is the same type of problem fixed way back in 2015 by commit 113e8283869b ("Btrfs: fix inode eviction infinite loop after extent_same ioctl") and commit ccccf3d67294 ("Btrfs: fix inode eviction infinite loop after cloning into it").

So fix this by returning immediately if the deduplication range length gets rounded down to 0 bytes, as there is nothing that needs to be done in such case.

Example reproducer:

 $ mkfs.btrfs -f /dev/sdb
 $ mount /dev/sdb /mnt

 $ xfs_io -f -c "pwrite -S 0xe6 0 100" /mnt/foo
 $ xfs_io -f -c "pwrite -S 0xe6 0 1M" /mnt/bar

# Unmount the filesystem and mount it again so that we start without any

 # extent state records when we ask for the deduplication.
 $ umount /mnt
 $ mount /dev/sdb /mnt

 $ xfs_io -c "dedupe /mnt/foo 0 500K 100" /mnt/bar

# This unmount triggers the infinite loop.

 $ umount /mnt

A test case for fstests will follow soon.

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

@@ -3178,6 +3178,8 @@ static int btrfs_extent_same(struct inod
 			const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize;
 
 			len = round_down(i_size_read(src), sz) - loff;
+			if (len == 0)
+				return 0;
 			olen = len;
 		}
 	}

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Kelley <[email protected]>

commit 35b69a420bfb56b7b74cb635ea903db05e357bec upstream.

Add support for platforms where pit_shutdown() doesn't work because of a quirk in the PIT emulation. On these platforms setting the counter register to zero causes the PIT to start running again, negating the shutdown.

Provide a global variable that controls whether the counter register is zero'ed, which platform specific code can override.

---
 drivers/clocksource/i8253.c |   14 ++++++++++++--
 include/linux/i8253.h       |    1 +
 2 files changed, 13 insertions(+), 2 deletions(-)

@@ -20,6 +20,13 @@
 DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
+/*
+ * Handle PIT quirk in pit_shutdown() where zeroing the counter register
+ * restarts the PIT, negating the shutdown. On platforms with the quirk,
+ * platform specific code can set this to false.
+ */
+bool i8253_clear_counter_on_shutdown __ro_after_init = true;
+
 #ifdef CONFIG_CLKSRC_I8253
 /*
  * Since the PIT overflows every tick, its not very useful

@@ -109,8 +116,11 @@ static int pit_shutdown(struct clock_eve
 	raw_spin_lock(&i8253_lock);
 
 	outb_p(0x30, PIT_MODE);
-	outb_p(0, PIT_CH0);
-	outb_p(0, PIT_CH0);
+
+	if (i8253_clear_counter_on_shutdown) {
+		outb_p(0, PIT_CH0);
+		outb_p(0, PIT_CH0);
+	}
 
 	raw_spin_unlock(&i8253_lock);
 	return 0;

@@ -21,6 +21,7 @@
 #define PIT_LATCH	((PIT_TICK_RATE + HZ/2) / HZ)
 
 extern raw_spinlock_t i8253_lock;
+extern bool i8253_clear_counter_on_shutdown;
 extern struct clock_event_device i8253_clockevent;
 extern void clockevent_i8253_init(bool oneshot);
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Vasily Averin <[email protected]>

commit 9e4028935cca3f9ef9b6a90df9da6f1f94853536 upstream.

Currently bh is set to NULL only during first iteration of for cycle, then this pointer is not cleared after end of using.
Therefore rollback after errors can lead to extra brelse(bh) call, decrements bh counter and later trigger an unexpected warning in __brelse()

Patch moves brelse() calls in body of cycle to exclude requirement of brelse() call in rollback.

---
 fs/ext4/resize.c |    8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

@@ -592,7 +592,6 @@ handle_bb:
 		bh = bclean(handle, sb, block);
 		if (IS_ERR(bh)) {
 			err = PTR_ERR(bh);
-			bh = NULL;
 			goto out;
 		}
 		overhead = ext4_group_overhead_blocks(sb, group);

@@ -604,9 +603,9 @@ handle_bb:
 		ext4_mark_bitmap_end(group_data[i].blocks_count,
 				     sb->s_blocksize * 8, bh->b_data);
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (err)
 			goto out;
-		brelse(bh);
 
 handle_ib:
 		if (bg_flags[i] & EXT4_BG_INODE_UNINIT)

@@ -621,18 +620,16 @@ handle_ib:
 		bh = bclean(handle, sb, block);
 		if (IS_ERR(bh)) {
 			err = PTR_ERR(bh);
-			bh = NULL;
 			goto out;
 		}
 
 		ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
 				     sb->s_blocksize * 8, bh->b_data);
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (err)
 			goto out;
-		brelse(bh);
 	}
-	bh = NULL;
 
 	/* Mark group tables in block bitmap */
 	for (j = 0; j < GROUP_TABLE_COUNT; j++) {

@@ -663,7 +660,6 @@ handle_ib:
 	}
 
 out:
-	brelse(bh);
 	err2 = ext4_journal_stop(handle);
 	if (err2 && !err)
 		err = err2;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Theodore Ts'o <[email protected]>

commit 4f32c38b4662312dd3c5f113d8bdd459887fb773 upstream.

---
 fs/ext4/resize.c |    1 +
 1 file changed, 1 insertion(+)

@@ -846,6 +846,7 @@ static int add_new_gdb(handle_t *handle,
 	err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
 	if (unlikely(err)) {
 		ext4_std_error(sb, err);
+		iloc.bh = NULL;
 		goto exit_inode;
 	}
 	brelse(dind);

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Theodore Ts'o <[email protected]>

commit 9e463084cdb22e0b56b2dfbc50461020409a5fd3 upstream.

---
 fs/ext4/super.c |   16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

@@ -4012,6 +4012,14 @@ static int ext4_fill_super(struct super_
 	sbi->s_groups_count = blocks_count;
 	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
 			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
+	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
+	    le32_to_cpu(es->s_inodes_count)) {
+		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
+			 le32_to_cpu(es->s_inodes_count),
+			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
+		ret = -EINVAL;
+		goto failed_mount;
+	}
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
 	if (ext4_has_feature_meta_bg(sb)) {

@@ -4031,14 +4039,6 @@ static int ext4_fill_super(struct super_
 		ret = -ENOMEM;
 		goto failed_mount;
 	}
-	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
-	    le32_to_cpu(es->s_inodes_count)) {
-		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
-			 le32_to_cpu(es->s_inodes_count),
-			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
-		ret = -EINVAL;
-		goto failed_mount;
-	}
 
 	bgl_lock_init(sbi->s_blockgroup_lock);
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Vasily Averin <[email protected]>

commit 45ae932d246f721e6584430017176cbcadfde610 upstream.

bs.bh was taken in previous ext4_xattr_block_find() call, it should be released before re-using

---
 fs/ext4/xattr.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -2404,6 +2404,8 @@ retry_inode:
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 		} else if (error == -ENOSPC) {
 			if (EXT4_I(inode)->i_file_acl && !bs.s.base) {
+				brelse(bs.bh);
+				bs.bh = NULL;
 				error = ext4_xattr_block_find(inode, &i, &bs);
 				if (error)
 					goto cleanup;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Vasily Averin <[email protected]>

commit 53692ec074d00589c2cf1d6d17ca76ad0adce6ec upstream.

---
 fs/ext4/xattr.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

@@ -2707,7 +2707,6 @@ int ext4_expand_extra_isize_ea(struct in
 			       struct ext4_inode *raw_inode, handle_t *handle)
 {
 	struct ext4_xattr_ibody_header *header;
-	struct buffer_head *bh;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	static unsigned int mnt_count;
 	size_t min_offs;

@@ -2748,13 +2747,17 @@ retry:
 	 * EA block can hold new_extra_isize bytes.
 	 */
 	if (EXT4_I(inode)->i_file_acl) {
+		struct buffer_head *bh;
+
 		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
 		error = -EIO;
 		if (!bh)
 			goto cleanup;
 		error = ext4_xattr_check_block(inode, bh);
-		if (error)
+		if (error) {
+			brelse(bh);
 			goto cleanup;
+		}
 		base = BHDR(bh);
 		end = bh->b_data + bh->b_size;
 		min_offs = end - base;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Christophe Leroy <[email protected]>

commit dded2e159208a9edc21dd5c5f583afa28d378d39 upstream.

On a powerpc 8xx, 'btc' fails as follows:

Entering kdb (current=0x(ptrval), pid 282) due to Keyboard Entry kdb> btc
btc: cpu status: Currently on cpu 0
Available cpus: 0
kdb_getarea: Bad address 0x0

when booting the kernel with 'debug_boot_weak_hash', it fails as well

Entering kdb (current=0xba99ad80, pid 284) due to Keyboard Entry kdb> btc
btc: cpu status: Currently on cpu 0
Available cpus: 0
kdb_getarea: Bad address 0xba99ad80

On other platforms, Oopses have been observed too, see
https://github.com/linuxppc/linux/issues/139

This is due to btc calling 'btt' with %p pointer as an argument.

This patch replaces %p by %px to get the real pointer value as expected by 'btt'

---
 kernel/debug/kdb/kdb_bt.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -179,14 +179,14 @@ kdb_bt(int argc, const char **argv)
 				kdb_printf("no process for cpu %ld\n", cpu);
 				return 0;
 			}
-			sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+			sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
 			kdb_parse(buf);
 			return 0;
 		}
 		kdb_printf("btc: cpu status: ");
 		kdb_parse("cpu\n");
 		for_each_online_cpu(cpu) {
-			sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+			sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
 			kdb_parse(buf);
 			touch_nmi_watchdog();
 		}

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lukas Czerner <[email protected]>

commit ebacb81273599555a7a19f7754a1451206a5fc4f upstream.

In async IO blocking case the additional reference to the io is taken for it to survive fuse_aio_complete(). In non blocking case this additional reference is not needed, however we still reference io to figure out whether to wait for completion or not. This is wrong and will lead to use-after-free. Fix it by storing blocking information in separate variable.

This was spotted by KASAN when running generic/208 fstest.

---
 fs/fuse/file.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -2912,10 +2912,12 @@ fuse_direct_IO(struct kiocb *iocb, struc
 	}
 
 	if (io->async) {
+		bool blocking = io->blocking;
+
 		fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
 
 		/* we have a non-extending, async request, so return */
-		if (!io->blocking)
+		if (!blocking)
 			return -EIOCBQUEUED;
 
 		wait_for_completion(&wait);

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Mike Kravetz <[email protected]>

commit 5e41540c8a0f0e98c337dda8b391e5dda0cde7cf upstream.

This bug has been experienced several times by the Oracle DB team. The BUG is in remove_inode_hugepages() as follows:

/*
* If page is mapped, it was faulted in after being
* unmapped in caller. Unmap (again) now after taking
* the fault mutex. The mutex will prevent faults
* until we finish removing the page.
*
* This race can only happen in the hole punch case.
* Getting here in a truncate operation is a bug. */
if (unlikely(page_mapped(page))) {
BUG_ON(truncate_op);

In this case, the elevated map count is not the result of a race. Rather it was incorrectly incremented as the result of a bug in the huge pmd sharing code. Consider the following:

- Process A maps a hugetlbfs file of sufficient size and alignment (PUD_SIZE) that a pmd page could be shared.

- Process B maps the same hugetlbfs file with the same size and alignment such that a pmd page is shared.

- Process B then calls mprotect() to change protections for the mapping with the shared pmd. As a result, the pmd is 'unshared'.

- Process B then calls mprotect() again to chage protections for the mapping back to their original value. pmd remains unshared.

- Process B then forks and process C is created. During the fork process, we do dup_mm -> dup_mmap -> copy_page_range to copy page tables. Copying page tables for hugetlb mappings is done in the routine copy_hugetlb_page_range.

In copy_hugetlb_page_range(), the destination pte is obtained by:

	dst_pte = huge_pte_alloc(dst, addr, sz);

If pmd sharing is possible, the returned pointer will be to a pte in an existing page table. In the situation above, process C could share with either process A or process B. Since process A is first in the list, the returned pte is a pointer to a pte in process A's page table.

However, the check for pmd sharing in copy_hugetlb_page_range is:

	/* If the pagetables are shared don't copy or take references */
	if (dst_pte == src_pte)
		continue;

Since process C is sharing with process A instead of process B, the above test fails. The code in copy_hugetlb_page_range which follows assumes dst_pte points to a huge_pte_none pte. It copies the pte entry from src_pte to dst_pte and increments this map count of the associated page. This is how we end up with an elevated map count.

To solve, check the dst_pte entry for huge_pte_none. If !none, this implies PMD sharing so do not copy.

---
 mm/hugetlb.c |   23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

@@ -3211,7 +3211,7 @@ static int is_hugetlb_entry_hwpoisoned(p
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
 {
-	pte_t *src_pte, *dst_pte, entry;
+	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;

@@ -3239,15 +3239,30 @@ int copy_hugetlb_page_range(struct mm_st
 			break;
 		}
 
-		/* If the pagetables are shared don't copy or take references */
-		if (dst_pte == src_pte)
+		/*
+		 * If the pagetables are shared don't copy or take references.
+		 * dst_pte == src_pte is the common case of src/dest sharing.
+		 *
+		 * However, src could have 'unshared' and dst shares with
+		 * another vma.  If dst_pte !none, this implies sharing.
+		 * Check here before taking page table lock, and once again
+		 * after taking the lock below.
+		 */
+		dst_entry = huge_ptep_get(dst_pte);
+		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry))
 			continue;
 
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		entry = huge_ptep_get(src_pte);
-		if (huge_pte_none(entry)) { /* skip none entry */
+		dst_entry = huge_ptep_get(dst_pte);
+		if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
+			/*
+			 * Skip if src entry none.  Also, skip in the
+			 * unlikely case dst entry !none as this implies
+			 * sharing with another vma.
+			 */
 			;
 		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
 				    is_hugetlb_entry_hwpoisoned(entry))) {

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Ard Biesheuvel <[email protected]>

commit 72a58a63a164b4e9d2d914e65caeb551846883f1 upstream.

Commit:

24d7c494ce46 ("efi/arm-stub: Round up FDT allocation to mapping size")

increased the allocation size for the FDT image created by the stub to a fixed value of 2 MB, to simplify the former code that made several attempts with increasing values for the size. This is reasonable given that the allocation is of type EFI_LOADER_DATA, which is released to the kernel unless it is explicitly memblock_reserve()d by the early boot code.

However, this allocation size leaked into the 'size' field of the FDT header metadata, and so the entire allocation remains occupied by the device tree binary, even if most of it is not used to store device tree information.

So call fdt_pack() to shrink the FDT data structure to its minimum size after populating all the fields, so that the remaining memory is no longer wasted.

---
 drivers/firmware/efi/libstub/fdt.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -158,6 +158,10 @@ static efi_status_t update_fdt(efi_syste
 			return efi_status;
 		}
 	}
+
+	/* shrink the FDT back to its minimum size */
+	fdt_pack(fdt);
+
 	return EFI_SUCCESS;
 
 fdt_set_fail:

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lyude Paul <[email protected]>

commit e96550956fbcd090629c0e2b5b8cded2eded2adf upstream.

With the exception of modesets which would switch the DPMS state of a connector from on to off, we want to make sure that we disallow all modesets which would result in enabling a new monitor or a new mode configuration on a monitor if the connector for the display in question is no longer registered. This allows us to stop userspace from trying to enable new displays on connectors for an MST topology that were just removed from the system, without preventing userspace from disabling DPMS on those connectors.

Changes since v5:
- Fix typo in comment, nothing else

---
 drivers/gpu/drm/drm_atomic_helper.c |   21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

@@ -306,6 +306,26 @@ update_connector_routing(struct drm_atom
 		return 0;
 	}
 
+	crtc_state = drm_atomic_get_new_crtc_state(state,
+						   new_connector_state->crtc);
+	/*
+	 * For compatibility with legacy users, we want to make sure that
+	 * we allow DPMS On->Off modesets on unregistered connectors. Modesets
+	 * which would result in anything else must be considered invalid, to
+	 * avoid turning on new displays on dead connectors.
+	 *
+	 * Since the connector can be unregistered at any point during an
+	 * atomic check or commit, this is racy. But that's OK: all we care
+	 * about is ensuring that userspace can't do anything but shut off the
+	 * display on a connector that was destroyed after its been notified,
+	 * not before.
+	 */
+	if (!READ_ONCE(connector->registered) && crtc_state->active) {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] is not registered\n",
+				 connector->base.id, connector->name);
+		return -EINVAL;
+	}
+
 	funcs = connector->helper_private;
 
 	if (funcs->atomic_best_encoder)

@@ -350,7 +370,6 @@ update_connector_routing(struct drm_atom
 
 	set_best_encoder(state, new_connector_state, new_encoder);
 
-	crtc_state = drm_atomic_get_new_crtc_state(state, new_connector_state->crtc);
 	crtc_state->connectors_changed = true;
 
 	DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] using [ENCODER:%d:%s] on [CRTC:%d:%s]\n",

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lyude Paul <[email protected]>

commit c02ba4ef16eefe663fdefcccaa57fad32d5481bf upstream.

Since we need to be able to allow DPMS on->off prop changes after an MST port has disappeared from the system, we need to be able to make sure we can compute a config for the resulting atomic commit. Currently this is impossible when the port has disappeared, since the VCPI slot searching we try to do in intel_dp_mst_compute_config() will fail with -EINVAL.

Since the only commits we want to allow on no-longer-present MST ports are ones that shut off display hardware, we already know that no VCPI allocations are needed. So, hardcode the VCPI slot count to 0 when intel_dp_mst_compute_config() is called on an MST port that's gone.

Changes since V4:
- Don't use mst_port_gone at all, just check whether or not the drm connector is registered - Daniel Vetter

---
 drivers/gpu/drm/i915/intel_dp_mst.c |   24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

@@ -37,11 +37,11 @@ static bool intel_dp_mst_compute_config(
 	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	struct intel_connector *connector =
-		to_intel_connector(conn_state->connector);
+	struct drm_connector *connector = conn_state->connector;
+	void *port = to_intel_connector(connector)->port;
 	struct drm_atomic_state *state = pipe_config->base.state;
 	int bpp;
-	int lane_count, slots;
+	int lane_count, slots = 0;
 	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
 	int mst_pbn;
 	bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,

@@ -66,17 +66,23 @@ static bool intel_dp_mst_compute_config(
 
 	pipe_config->port_clock = intel_dp_max_link_rate(intel_dp);
 
-	if (drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, connector->port))
+	if (drm_dp_mst_port_has_audio(&intel_dp->mst_mgr, port))
 		pipe_config->has_audio = true;
 
 	mst_pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock, bpp);
 	pipe_config->pbn = mst_pbn;
 
-	slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr,
-					      connector->port, mst_pbn);
-	if (slots < 0) {
-		DRM_DEBUG_KMS("failed finding vcpi slots:%d\n", slots);
-		return false;
+	/* Zombie connectors can't have VCPI slots */
+	if (READ_ONCE(connector->registered)) {
+		slots = drm_dp_atomic_find_vcpi_slots(state,
+						      &intel_dp->mst_mgr,
+						      port,
+						      mst_pbn);
+		if (slots < 0) {
+			DRM_DEBUG_KMS("failed finding vcpi slots:%d\n",
+				      slots);
+			return false;
+		}
 	}
 
 	intel_link_compute_m_n(bpp, lane_count,

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Clint Taylor <[email protected]>

commit 6503493145cba4413ecd3d4d153faeef4a1e9b85 upstream.

HDMI 2.0 594Mhz modes were incorrectly selecting 25.200Mhz Automatic N value mode instead of HDMI specification values.

V2: Fix 88.2 Hz N value

---
 drivers/gpu/drm/i915/intel_audio.c |   17 +++++++++++++++++
 1 file changed, 17 insertions(+)

@@ -134,6 +134,9 @@ static const struct {
 /* HDMI N/CTS table */
 #define TMDS_297M 297000
 #define TMDS_296M 296703
+#define TMDS_594M 594000
+#define TMDS_593M 593407
+
 static const struct {
 	int sample_rate;
 	int clock;

@@ -154,6 +157,20 @@ static const struct {
 	{ 176400, TMDS_297M, 18816, 247500 },
 	{ 192000, TMDS_296M, 23296, 281250 },
 	{ 192000, TMDS_297M, 20480, 247500 },
+	{ 44100, TMDS_593M, 8918, 937500 },
+	{ 44100, TMDS_594M, 9408, 990000 },
+	{ 48000, TMDS_593M, 5824, 562500 },
+	{ 48000, TMDS_594M, 6144, 594000 },
+	{ 32000, TMDS_593M, 5824, 843750 },
+	{ 32000, TMDS_594M, 3072, 445500 },
+	{ 88200, TMDS_593M, 17836, 937500 },
+	{ 88200, TMDS_594M, 18816, 990000 },
+	{ 96000, TMDS_593M, 11648, 562500 },
+	{ 96000, TMDS_594M, 12288, 594000 },
+	{ 176400, TMDS_593M, 35672, 937500 },
+	{ 176400, TMDS_594M, 37632, 990000 },
+	{ 192000, TMDS_593M, 23296, 562500 },
+	{ 192000, TMDS_594M, 24576, 594000 },
 };
 
 /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Chris Wilson <[email protected]>

commit 0a823e8fd4fd67726697854578f3584ee3a49b1d upstream.

Ensure that the writes into the context image are completed prior to the register mmio to trigger execution. Although previously we were assured by the SDM that all writes are flushed before an uncached memory transaction (our mmio write to submit the context to HW for execution), we have empirical evidence to believe that this is not actually the case.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108656
References: https://bugs.freedesktop.org/show_bug.cgi?id=108315
References: https://bugs.freedesktop.org/show_bug.cgi?id=106887

---
 drivers/gpu/drm/i915/intel_lrc.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

@@ -325,7 +325,8 @@ static u64 execlists_update_context(stru
 
 	reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail);
 
-	/* True 32b PPGTT with dynamic page allocation: update PDP
+	/*
+	 * True 32b PPGTT with dynamic page allocation: update PDP
 	 * registers and point the unallocated PDPs to scratch page.
 	 * PML4 is allocated during ppgtt init, so this is not needed
 	 * in 48-bit mode.

@@ -333,6 +334,17 @@ static u64 execlists_update_context(stru
 	if (ppgtt && !i915_vm_is_48bit(&ppgtt->base))
 		execlists_update_context_pdps(ppgtt, reg_state);
 
+	/*
+	 * Make sure the context image is complete before we submit it to HW.
+	 *
+	 * Ostensibly, writes (including the WCB) should be flushed prior to
+	 * an uncached write such as our mmio register access, the empirical
+	 * evidence (esp. on Braswell) suggests that the WC write into memory
+	 * may not be visible to the HW prior to the completion of the UC
+	 * register write and that we may begin execution from the context
+	 * before its image is complete leading to invalid PD chasing.
+	 */
+	wmb();
 	return ce->lrc_desc;
 }
 

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Sergey Senozhatsky <[email protected]>

commit fd5f7cde1b85d4c8e09ca46ce948e008a2377f64 upstream.

This patch, basically, reverts commit 6b97a20d3a79 ("printk:
set may_schedule for some of console_trylock() callers"). That commit was a mistake, it introduced a big dependency on the scheduler, by enabling preemption under console_sem in printk()->console_unlock() path, which is rather too critical. The patch did not significantly reduce the possibilities of printk() lockups, but made it possible to stall printk(), as has been reported by Tetsuo Handa [1].

Another issues is that preemption under console_sem also messes up with Steven Rostedt's hand off scheme, by making it possible to sleep with console_sem both in console_unlock() and in vprintk_emit(), after acquiring the console_sem ownership (anywhere between printk_safe_exit_irqrestore() in console_trylock_spinning() and printk_safe_enter_irqsave() in console_unlock()). This makes hand off less likely and, at the same time, may result in a significant amount of pending logbuf messages. Preempted console_sem owner makes it impossible for other CPUs to emit logbuf messages, but does not make it impossible for other CPUs to append new messages to the logbuf.

Reinstate the old behavior and make printk() non-preemptible. Should any printk() lockup reports arrive they must be handled in a different way.

[1] http://lkml.kernel.org/r/201603022101.CAH73907.OVOOMFHFFtQJSL%20()%20I-love%20!%20SAKURA%20!%20ne%20!%20jp

To: Tetsuo Handa <[email protected]>

---
 kernel/printk/printk.c |   22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

@@ -1763,12 +1763,19 @@ asmlinkage int vprintk_emit(int facility
 	/* If called from the scheduler, we can not call up(). */
 	if (!in_sched) {
 		/*
+		 * Disable preemption to avoid being preempted while holding
+		 * console_sem which would prevent anyone from printing to
+		 * console
+		 */
+		preempt_disable();
+		/*
 		 * Try to acquire and then immediately release the console
 		 * semaphore.  The release will print out buffers and wake up
 		 * /dev/kmsg and syslog() users.
 		 */
 		if (console_trylock())
 			console_unlock();
+		preempt_enable();
 	}
 
 	return printed_len;

@@ -2083,20 +2090,7 @@ int console_trylock(void)
 		return 0;
 	}
 	console_locked = 1;
-	/*
-	 * When PREEMPT_COUNT disabled we can't reliably detect if it's
-	 * safe to schedule (e.g. calling printk while holding a spin_lock),
-	 * because preempt_disable()/preempt_enable() are just barriers there
-	 * and preempt_count() is always 0.
-	 *
-	 * RCU read sections have a separate preemption counter when
-	 * PREEMPT_RCU enabled thus we must take extra care and check
-	 * rcu_preempt_depth(), otherwise RCU read sections modify
-	 * preempt_count().
-	 */
-	console_may_schedule = !oops_in_progress &&
-			preemptible() &&
-			!rcu_preempt_depth();
+	console_may_schedule = 0;
 	return 1;
 }
 EXPORT_SYMBOL(console_trylock);

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Amir Goldstein <[email protected]>

commit babf4770be0adc69e6d2de150f4040f175e24beb upstream.

We hit a BUG on kfree of an ERR_PTR()...

---
 fs/overlayfs/namei.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -368,8 +368,10 @@ int ovl_verify_origin(struct dentry *den
 
 	fh = ovl_encode_fh(origin, is_upper);
 	err = PTR_ERR(fh);
-	if (IS_ERR(fh))
+	if (IS_ERR(fh)) {
+		fh = NULL;
 		goto fail;
+	}
 
 	err = ovl_verify_origin_fh(dentry, fh);
 	if (set && err == -ENODATA)

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Himanshu Madhani <[email protected]>

commit 4c1458df9635c7e3ced155f594d2e7dfd7254e21 upstream.

---
 drivers/scsi/qla2xxx/qla_mbx.c |    5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

@@ -3682,10 +3682,7 @@ qla2x00_set_idma_speed(scsi_qla_host_t *
 	mcp->mb[0] = MBC_PORT_PARAMS;
 	mcp->mb[1] = loop_id;
 	mcp->mb[2] = BIT_0;
-	if (IS_CNA_CAPABLE(vha->hw))
-		mcp->mb[3] = port_speed & (BIT_5|BIT_4|BIT_3|BIT_2|BIT_1|BIT_0);
-	else
-		mcp->mb[3] = port_speed & (BIT_2|BIT_1|BIT_0);
+	mcp->mb[3] = port_speed & (BIT_5|BIT_4|BIT_3|BIT_2|BIT_1|BIT_0);
 	mcp->mb[9] = vha->vp_idx;
 	mcp->out_mb = MBX_9|MBX_3|MBX_2|MBX_1|MBX_0;
 	mcp->in_mb = MBX_3|MBX_1|MBX_0;

4.14-stable review patch. If anyone has any objections, please let me know.

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

From: Quinn Tran <[email protected]>

commit b86ac8fd4b2f6ec2f9ca9194c56eac12d620096f upstream.

This patch improves performance for 16G and above adapter by removing additional call to process_response_queue().

[mkp: typo]

---
 drivers/scsi/qla2xxx/qla_init.c |    2 --
 drivers/scsi/qla2xxx/qla_iocb.c |   17 -----------------
 2 files changed, 19 deletions(-)

@@ -7591,7 +7591,6 @@ qla81xx_nvram_config(scsi_qla_host_t *vh
 	}
 	icb->firmware_options_2 &= cpu_to_le32(
 	    ~(BIT_3 | BIT_2 | BIT_1 | BIT_0));
-	vha->flags.process_response_queue = 0;
 	if (ha->zio_mode != QLA_ZIO_DISABLED) {
 		ha->zio_mode = QLA_ZIO_MODE_6;
 

@@ -7603,7 +7602,6 @@ qla81xx_nvram_config(scsi_qla_host_t *vh
 		icb->firmware_options_2 |= cpu_to_le32(
 		    (uint32_t)ha->zio_mode);
 		icb->interrupt_delay_timer = cpu_to_le16(ha->zio_timer);
-		vha->flags.process_response_queue = 1;
 	}
 
 	 /* enable RIDA Format2 */

@@ -1524,12 +1524,6 @@ qla24xx_start_scsi(srb_t *sp)
 
 	/* Set chip new ring index. */
 	WRT_REG_DWORD(req->req_q_in, req->ring_index);
-	RD_REG_DWORD_RELAXED(&ha->iobase->isp24.hccr);
-
-	/* Manage unprocessed RIO/ZIO commands in response queue. */
-	if (vha->flags.process_response_queue &&
-		rsp->ring_ptr->signature != RESPONSE_PROCESSED)
-		qla24xx_process_response_queue(vha, rsp);
 
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	return QLA_SUCCESS;