lkml.org 
[lkml]   [2021]   [Dec]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
SubjectRe: Linux 4.14.257
Date
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt
index f64060908d5a..35f469c4f675 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-37xx-pinctrl.txt
@@ -43,26 +43,26 @@ group emmc_nb

group pwm0
- pin 11 (GPIO1-11)
- - functions pwm, gpio
+ - functions pwm, led, gpio

group pwm1
- pin 12
- - functions pwm, gpio
+ - functions pwm, led, gpio

group pwm2
- pin 13
- - functions pwm, gpio
+ - functions pwm, led, gpio

group pwm3
- pin 14
- - functions pwm, gpio
+ - functions pwm, led, gpio

group pmic1
- - pin 17
+ - pin 7
- functions pmic, gpio

group pmic0
- - pin 16
+ - pin 6
- functions pmic, gpio

group i2c2
@@ -112,17 +112,25 @@ group usb2_drvvbus1
- functions drvbus, gpio

group sdio_sb
- - pins 60-64
+ - pins 60-65
- functions sdio, gpio

group rgmii
- - pins 42-55
+ - pins 42-53
- functions mii, gpio

group pcie1
- - pins 39-40
+ - pins 39
+ - functions pcie, gpio
+
+group pcie1_clkreq
+ - pins 40
- functions pcie, gpio

+group smi
+ - pins 54-55
+ - functions smi, gpio
+
group ptp
- pins 56-58
- functions ptp, gpio
diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index 056898685d40..fc531c29a2e8 100644
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -30,8 +30,7 @@ conn_reuse_mode - INTEGER

0: disable any special handling on port reuse. The new
connection will be delivered to the same real server that was
- servicing the previous connection. This will effectively
- disable expire_nodest_conn.
+ servicing the previous connection.

bit 1: enable rescheduling of new connections when it is safe.
That is, whenever expire_nodest_conn and for TCP sockets, when
diff --git a/Makefile b/Makefile
index dd00bb6d79ef..99110c39fdc1 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 14
-SUBLEVEL = 256
+SUBLEVEL = 257
EXTRAVERSION =
NAME = Petit Gorille

diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 165fd1c1461a..c3b6ba4db8e3 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -246,6 +246,8 @@

gpio-controller;
#gpio-cells = <2>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
};

pcie0: pcie@12000 {
@@ -365,7 +367,7 @@
i2c0: i2c@18009000 {
compatible = "brcm,iproc-i2c";
reg = <0x18009000 0x50>;
- interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
clock-frequency = <100000>;
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index d5562f9ce600..fd9717e9fee3 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -280,6 +280,14 @@ tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr
tlb_add_flush(tlb, addr);
}

+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+ unsigned long size)
+{
+ tlb_add_flush(tlb, address);
+ tlb_add_flush(tlb, address + size - PMD_SIZE);
+}
+
#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
#define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp)
diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h
index 65e1817d8afe..692a287a8712 100644
--- a/arch/arm/mach-socfpga/core.h
+++ b/arch/arm/mach-socfpga/core.h
@@ -48,7 +48,7 @@ extern void __iomem *sdr_ctl_base_addr;
u32 socfpga_sdram_self_refresh(u32 sdr_base);
extern unsigned int socfpga_sdram_self_refresh_sz;

-extern char secondary_trampoline, secondary_trampoline_end;
+extern char secondary_trampoline[], secondary_trampoline_end[];

extern unsigned long socfpga_cpu1start_addr;

diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c
index 0ee76772b507..a272999ce04b 100644
--- a/arch/arm/mach-socfpga/platsmp.c
+++ b/arch/arm/mach-socfpga/platsmp.c
@@ -31,14 +31,14 @@

static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
{
- int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+ int trampoline_size = secondary_trampoline_end - secondary_trampoline;

if (socfpga_cpu1start_addr) {
/* This will put CPU #1 into reset. */
writel(RSTMGR_MPUMODRST_CPU1,
rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST);

- memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+ memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);

writel(__pa_symbol(secondary_startup),
sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff));
@@ -56,12 +56,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)

static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle)
{
- int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+ int trampoline_size = secondary_trampoline_end - secondary_trampoline;

if (socfpga_cpu1start_addr) {
writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr +
SOCFPGA_A10_RSTMGR_MODMPURST);
- memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+ memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);

writel(__pa_symbol(secondary_startup),
sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff));
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-db.dts b/arch/arm64/boot/dts/marvell/armada-3720-db.dts
index 9df0f06ce607..0a0e9e19e879 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-db.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-db.dts
@@ -155,6 +155,9 @@

/* CON15(V2.0)/CON17(V1.4) : PCIe / CON15(V2.0)/CON12(V1.4) :mini-PCIe */
&pcie0 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pcie_reset_pins &pcie_clkreq_pins>;
+ reset-gpios = <&gpiosb 3 GPIO_ACTIVE_LOW>;
status = "okay";
};

diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts
index 13c0ec053ada..89c7385390f4 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts
@@ -82,6 +82,9 @@

/* J9 */
&pcie0 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pcie_reset_pins &pcie_clkreq_pins>;
+ reset-gpios = <&gpiosb 3 GPIO_ACTIVE_LOW>;
status = "okay";
};

diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index 257bfa811fe8..b369356e7419 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -239,6 +239,15 @@
function = "mii";
};

+ pcie_reset_pins: pcie-reset-pins {
+ groups = "pcie1";
+ function = "gpio";
+ };
+
+ pcie_clkreq_pins: pcie-clkreq-pins {
+ groups = "pcie1_clkreq";
+ function = "pcie";
+ };
};

eth0: ethernet@30000 {
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 44f0ac0df308..26d49489498b 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -269,6 +269,16 @@ __tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long addre
tlb->end_addr = address + PAGE_SIZE;
}

+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+ unsigned long size)
+{
+ if (tlb->start_addr > address)
+ tlb->start_addr = address;
+ if (tlb->end_addr < address + size)
+ tlb->end_addr = address + size;
+}
+
#define tlb_migrate_finish(mm) platform_tlb_migrate_finish(mm)

#define tlb_start_vma(tlb, vma) do { } while (0)
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 85afd6b4297b..45a5801ff467 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2990,7 +2990,7 @@ config HAVE_LATENCYTOP_SUPPORT
config PGTABLE_LEVELS
int
default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48
- default 3 if 64BIT && !PAGE_SIZE_64KB
+ default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48)
default 2

source "init/Kconfig"
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 01946ebaff72..154ea9a7b8c7 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -17,7 +17,12 @@
# Mike Shaver, Helge Deller and Martin K. Petersen
#

+ifdef CONFIG_PARISC_SELF_EXTRACT
+boot := arch/parisc/boot
+KBUILD_IMAGE := $(boot)/bzImage
+else
KBUILD_IMAGE := vmlinuz
+endif

KBUILD_DEFCONFIG := default_defconfig

diff --git a/arch/parisc/install.sh b/arch/parisc/install.sh
index 6f68784fea25..a8c49815f58c 100644
--- a/arch/parisc/install.sh
+++ b/arch/parisc/install.sh
@@ -39,6 +39,7 @@ verify "$3"
if [ -n "${INSTALLKERNEL}" ]; then
if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
+ if [ -x /usr/sbin/${INSTALLKERNEL} ]; then exec /usr/sbin/${INSTALLKERNEL} "$@"; fi
fi

# Default install
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 42a873226a04..af84b81686d1 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -245,27 +245,13 @@ void __init time_init(void)
static int __init init_cr16_clocksource(void)
{
/*
- * The cr16 interval timers are not syncronized across CPUs on
- * different sockets, so mark them unstable and lower rating on
- * multi-socket SMP systems.
+ * The cr16 interval timers are not syncronized across CPUs, even if
+ * they share the same socket.
*/
if (num_online_cpus() > 1 && !running_on_qemu) {
- int cpu;
- unsigned long cpu0_loc;
- cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
-
- for_each_online_cpu(cpu) {
- if (cpu == 0)
- continue;
- if ((cpu0_loc != 0) &&
- (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc))
- continue;
-
- clocksource_cr16.name = "cr16_unstable";
- clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
- clocksource_cr16.rating = 0;
- break;
- }
+ clocksource_cr16.name = "cr16_unstable";
+ clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
+ clocksource_cr16.rating = 0;
}

/* XXX: We may want to mark sched_clock stable here if cr16 clocks are
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 457b7ba0fbb6..c216a24ddff8 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -116,6 +116,20 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
return tlb_remove_page(tlb, page);
}

+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+ unsigned long address, unsigned long size)
+{
+ /*
+ * the range might exceed the original range that was provided to
+ * tlb_gather_mmu(), so we need to update it despite the fact it is
+ * usually not updated.
+ */
+ if (tlb->start > address)
+ tlb->start = address;
+ if (tlb->end < address + size)
+ tlb->end = address + size;
+}
+
/*
* pte_free_tlb frees a pte table and clears the CRSTE for the
* page table from the tlb.
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index ceaee215e243..e9ef093eb676 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -706,9 +706,6 @@ static void __init setup_memory(void)
storage_key_init_range(reg->base, reg->base + reg->size);
}
psw_set_key(PAGE_DEFAULT_KEY);
-
- /* Only cosmetics */
- memblock_enforce_memory_limit(memblock_end_of_DRAM());
}

/*
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index ae677f814bc0..aa6b9487c8bb 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -896,6 +896,7 @@ EXPORT_SYMBOL(get_guest_storage_key);
int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
unsigned long *oldpte, unsigned long *oldpgste)
{
+ struct vm_area_struct *vma;
unsigned long pgstev;
spinlock_t *ptl;
pgste_t pgste;
@@ -905,6 +906,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
WARN_ON_ONCE(orc > ESSA_MAX);
if (unlikely(orc > ESSA_MAX))
return -EINVAL;
+
+ vma = find_vma(mm, hva);
+ if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+ return -EFAULT;
ptep = get_locked_pte(mm, hva, &ptl);
if (unlikely(!ptep))
return -EFAULT;
@@ -997,10 +1002,14 @@ EXPORT_SYMBOL(pgste_perform_essa);
int set_pgste_bits(struct mm_struct *mm, unsigned long hva,
unsigned long bits, unsigned long value)
{
+ struct vm_area_struct *vma;
spinlock_t *ptl;
pgste_t new;
pte_t *ptep;

+ vma = find_vma(mm, hva);
+ if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+ return -EFAULT;
ptep = get_locked_pte(mm, hva, &ptl);
if (unlikely(!ptep))
return -EFAULT;
@@ -1025,9 +1034,13 @@ EXPORT_SYMBOL(set_pgste_bits);
*/
int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep)
{
+ struct vm_area_struct *vma;
spinlock_t *ptl;
pte_t *ptep;

+ vma = find_vma(mm, hva);
+ if (!vma || hva < vma->vm_start || is_vm_hugetlb_page(vma))
+ return -EFAULT;
ptep = get_locked_pte(mm, hva, &ptl);
if (unlikely(!ptep))
return -EFAULT;
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 77abe192fb43..adcb0bfe238e 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -127,6 +127,16 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
return tlb_remove_page(tlb, page);
}

+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+ unsigned long size)
+{
+ if (tlb->start > address)
+ tlb->start = address;
+ if (tlb->end < address + size)
+ tlb->end = address + size;
+}
+
#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
unsigned int page_size)
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index dce6db147f24..02e61f6abfca 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -130,6 +130,18 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
return tlb_remove_page(tlb, page);
}

+static inline void
+tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+ unsigned long size)
+{
+ tlb->need_flush = 1;
+
+ if (tlb->start > address)
+ tlb->start = address;
+ if (tlb->end < address + size)
+ tlb->end = address + size;
+}
+
/**
* tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
*
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index ed84d3917a59..76740c8c000c 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -57,6 +57,7 @@ static void __init setup_real_mode(void)
#ifdef CONFIG_X86_64
u64 *trampoline_pgd;
u64 efer;
+ int i;
#endif

base = (unsigned char *)real_mode_header;
@@ -114,8 +115,17 @@ static void __init setup_real_mode(void)
trampoline_header->flags |= TH_FLAGS_SME_ACTIVE;

trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
+
+ /* Map the real mode stub as virtual == physical */
trampoline_pgd[0] = trampoline_pgd_entry.pgd;
- trampoline_pgd[511] = init_top_pgt[511].pgd;
+
+ /*
+ * Include the entirety of the kernel mapping into the trampoline
+ * PGD. This way, all mappings present in the normal kernel page
+ * tables are usable while running on trampoline_pgd.
+ */
+ for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++)
+ trampoline_pgd[i] = init_top_pgt[i].pgd;
#endif
}

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index c5fd7908fc91..63bf8a7d477b 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2894,7 +2894,7 @@ static void binder_transaction(struct binder_proc *proc,
t->from = thread;
else
t->from = NULL;
- t->sender_euid = proc->cred->euid;
+ t->sender_euid = task_euid(proc->tsk);
t->to_proc = target_proc;
t->to_thread = target_thread;
t->code = tr->code;
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 5a94659064b4..66dd209ed70e 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1406,6 +1406,14 @@ static int sata_fsl_init_controller(struct ata_host *host)
return 0;
}

+static void sata_fsl_host_stop(struct ata_host *host)
+{
+ struct sata_fsl_host_priv *host_priv = host->private_data;
+
+ iounmap(host_priv->hcr_base);
+ kfree(host_priv);
+}
+
/*
* scsi mid-layer and libata interface structures
*/
@@ -1438,6 +1446,8 @@ static struct ata_port_operations sata_fsl_ops = {
.port_start = sata_fsl_port_start,
.port_stop = sata_fsl_port_stop,

+ .host_stop = sata_fsl_host_stop,
+
.pmp_attach = sata_fsl_pmp_attach,
.pmp_detach = sata_fsl_pmp_detach,
};
@@ -1492,9 +1502,9 @@ static int sata_fsl_probe(struct platform_device *ofdev)
host_priv->ssr_base = ssr_base;
host_priv->csr_base = csr_base;

- irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
- if (!irq) {
- dev_err(&ofdev->dev, "invalid irq from platform\n");
+ irq = platform_get_irq(ofdev, 0);
+ if (irq < 0) {
+ retval = irq;
goto error_exit_with_cleanup;
}
host_priv->irq = irq;
@@ -1569,10 +1579,6 @@ static int sata_fsl_remove(struct platform_device *ofdev)

ata_host_detach(host);

- irq_dispose_mapping(host_priv->irq);
- iounmap(host_priv->hcr_base);
- kfree(host_priv);
-
return 0;
}

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 7ba58c39146f..878eb9ba06b2 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -78,6 +78,7 @@ enum blkif_state {
BLKIF_STATE_DISCONNECTED,
BLKIF_STATE_CONNECTED,
BLKIF_STATE_SUSPENDED,
+ BLKIF_STATE_ERROR,
};

struct grant {
@@ -87,6 +88,7 @@ struct grant {
};

enum blk_req_status {
+ REQ_PROCESSING,
REQ_WAITING,
REQ_DONE,
REQ_ERROR,
@@ -534,10 +536,10 @@ static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo,

id = get_id_from_freelist(rinfo);
rinfo->shadow[id].request = req;
- rinfo->shadow[id].status = REQ_WAITING;
+ rinfo->shadow[id].status = REQ_PROCESSING;
rinfo->shadow[id].associated_id = NO_ASSOCIATED_ID;

- (*ring_req)->u.rw.id = id;
+ rinfo->shadow[id].req.u.rw.id = id;

return id;
}
@@ -545,11 +547,12 @@ static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo,
static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_info *rinfo)
{
struct blkfront_info *info = rinfo->dev_info;
- struct blkif_request *ring_req;
+ struct blkif_request *ring_req, *final_ring_req;
unsigned long id;

/* Fill out a communications ring structure. */
- id = blkif_ring_get_request(rinfo, req, &ring_req);
+ id = blkif_ring_get_request(rinfo, req, &final_ring_req);
+ ring_req = &rinfo->shadow[id].req;

ring_req->operation = BLKIF_OP_DISCARD;
ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
@@ -560,8 +563,9 @@ static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_inf
else
ring_req->u.discard.flag = 0;

- /* Keep a private copy so we can reissue requests when recovering. */
- rinfo->shadow[id].req = *ring_req;
+ /* Copy the request to the ring page. */
+ *final_ring_req = *ring_req;
+ rinfo->shadow[id].status = REQ_WAITING;

return 0;
}
@@ -694,6 +698,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
{
struct blkfront_info *info = rinfo->dev_info;
struct blkif_request *ring_req, *extra_ring_req = NULL;
+ struct blkif_request *final_ring_req, *final_extra_ring_req = NULL;
unsigned long id, extra_id = NO_ASSOCIATED_ID;
bool require_extra_req = false;
int i;
@@ -738,7 +743,8 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
}

/* Fill out a communications ring structure. */
- id = blkif_ring_get_request(rinfo, req, &ring_req);
+ id = blkif_ring_get_request(rinfo, req, &final_ring_req);
+ ring_req = &rinfo->shadow[id].req;

num_sg = blk_rq_map_sg(req->q, req, rinfo->shadow[id].sg);
num_grant = 0;
@@ -789,7 +795,9 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
ring_req->u.rw.nr_segments = num_grant;
if (unlikely(require_extra_req)) {
extra_id = blkif_ring_get_request(rinfo, req,
- &extra_ring_req);
+ &final_extra_ring_req);
+ extra_ring_req = &rinfo->shadow[extra_id].req;
+
/*
* Only the first request contains the scatter-gather
* list.
@@ -831,10 +839,13 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
if (setup.segments)
kunmap_atomic(setup.segments);

- /* Keep a private copy so we can reissue requests when recovering. */
- rinfo->shadow[id].req = *ring_req;
- if (unlikely(require_extra_req))
- rinfo->shadow[extra_id].req = *extra_ring_req;
+ /* Copy request(s) to the ring page. */
+ *final_ring_req = *ring_req;
+ rinfo->shadow[id].status = REQ_WAITING;
+ if (unlikely(require_extra_req)) {
+ *final_extra_ring_req = *extra_ring_req;
+ rinfo->shadow[extra_id].status = REQ_WAITING;
+ }

if (new_persistent_gnts)
gnttab_free_grant_references(setup.gref_head);
@@ -1408,8 +1419,8 @@ static enum blk_req_status blkif_rsp_to_req_status(int rsp)
static int blkif_get_final_status(enum blk_req_status s1,
enum blk_req_status s2)
{
- BUG_ON(s1 == REQ_WAITING);
- BUG_ON(s2 == REQ_WAITING);
+ BUG_ON(s1 < REQ_DONE);
+ BUG_ON(s2 < REQ_DONE);

if (s1 == REQ_ERROR || s2 == REQ_ERROR)
return BLKIF_RSP_ERROR;
@@ -1442,7 +1453,7 @@ static bool blkif_completion(unsigned long *id,
s->status = blkif_rsp_to_req_status(bret->status);

/* Wait the second response if not yet here. */
- if (s2->status == REQ_WAITING)
+ if (s2->status < REQ_DONE)
return 0;

bret->status = blkif_get_final_status(s->status,
@@ -1550,7 +1561,7 @@ static bool blkif_completion(unsigned long *id,
static irqreturn_t blkif_interrupt(int irq, void *dev_id)
{
struct request *req;
- struct blkif_response *bret;
+ struct blkif_response bret;
RING_IDX i, rp;
unsigned long flags;
struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
@@ -1561,54 +1572,76 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)

spin_lock_irqsave(&rinfo->ring_lock, flags);
again:
- rp = rinfo->ring.sring->rsp_prod;
- rmb(); /* Ensure we see queued responses up to 'rp'. */
+ rp = READ_ONCE(rinfo->ring.sring->rsp_prod);
+ virt_rmb(); /* Ensure we see queued responses up to 'rp'. */
+ if (RING_RESPONSE_PROD_OVERFLOW(&rinfo->ring, rp)) {
+ pr_alert("%s: illegal number of responses %u\n",
+ info->gd->disk_name, rp - rinfo->ring.rsp_cons);
+ goto err;
+ }

for (i = rinfo->ring.rsp_cons; i != rp; i++) {
unsigned long id;
+ unsigned int op;
+
+ RING_COPY_RESPONSE(&rinfo->ring, i, &bret);
+ id = bret.id;

- bret = RING_GET_RESPONSE(&rinfo->ring, i);
- id = bret->id;
/*
* The backend has messed up and given us an id that we would
* never have given to it (we stamp it up to BLK_RING_SIZE -
* look in get_id_from_freelist.
*/
if (id >= BLK_RING_SIZE(info)) {
- WARN(1, "%s: response to %s has incorrect id (%ld)\n",
- info->gd->disk_name, op_name(bret->operation), id);
- /* We can't safely get the 'struct request' as
- * the id is busted. */
- continue;
+ pr_alert("%s: response has incorrect id (%ld)\n",
+ info->gd->disk_name, id);
+ goto err;
}
+ if (rinfo->shadow[id].status != REQ_WAITING) {
+ pr_alert("%s: response references no pending request\n",
+ info->gd->disk_name);
+ goto err;
+ }
+
+ rinfo->shadow[id].status = REQ_PROCESSING;
req = rinfo->shadow[id].request;

- if (bret->operation != BLKIF_OP_DISCARD) {
+ op = rinfo->shadow[id].req.operation;
+ if (op == BLKIF_OP_INDIRECT)
+ op = rinfo->shadow[id].req.u.indirect.indirect_op;
+ if (bret.operation != op) {
+ pr_alert("%s: response has wrong operation (%u instead of %u)\n",
+ info->gd->disk_name, bret.operation, op);
+ goto err;
+ }
+
+ if (bret.operation != BLKIF_OP_DISCARD) {
/*
* We may need to wait for an extra response if the
* I/O request is split in 2
*/
- if (!blkif_completion(&id, rinfo, bret))
+ if (!blkif_completion(&id, rinfo, &bret))
continue;
}

if (add_id_to_freelist(rinfo, id)) {
WARN(1, "%s: response to %s (id %ld) couldn't be recycled!\n",
- info->gd->disk_name, op_name(bret->operation), id);
+ info->gd->disk_name, op_name(bret.operation), id);
continue;
}

- if (bret->status == BLKIF_RSP_OKAY)
+ if (bret.status == BLKIF_RSP_OKAY)
blkif_req(req)->error = BLK_STS_OK;
else
blkif_req(req)->error = BLK_STS_IOERR;

- switch (bret->operation) {
+ switch (bret.operation) {
case BLKIF_OP_DISCARD:
- if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
+ if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
struct request_queue *rq = info->rq;
- printk(KERN_WARNING "blkfront: %s: %s op failed\n",
- info->gd->disk_name, op_name(bret->operation));
+
+ pr_warn_ratelimited("blkfront: %s: %s op failed\n",
+ info->gd->disk_name, op_name(bret.operation));
blkif_req(req)->error = BLK_STS_NOTSUPP;
info->feature_discard = 0;
info->feature_secdiscard = 0;
@@ -1618,15 +1651,15 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
break;
case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
- if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
- printk(KERN_WARNING "blkfront: %s: %s op failed\n",
- info->gd->disk_name, op_name(bret->operation));
+ if (unlikely(bret.status == BLKIF_RSP_EOPNOTSUPP)) {
+ pr_warn_ratelimited("blkfront: %s: %s op failed\n",
+ info->gd->disk_name, op_name(bret.operation));
blkif_req(req)->error = BLK_STS_NOTSUPP;
}
- if (unlikely(bret->status == BLKIF_RSP_ERROR &&
+ if (unlikely(bret.status == BLKIF_RSP_ERROR &&
rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
- printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
- info->gd->disk_name, op_name(bret->operation));
+ pr_warn_ratelimited("blkfront: %s: empty %s op failed\n",
+ info->gd->disk_name, op_name(bret.operation));
blkif_req(req)->error = BLK_STS_NOTSUPP;
}
if (unlikely(blkif_req(req)->error)) {
@@ -1639,9 +1672,10 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
/* fall through */
case BLKIF_OP_READ:
case BLKIF_OP_WRITE:
- if (unlikely(bret->status != BLKIF_RSP_OKAY))
- dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
- "request: %x\n", bret->status);
+ if (unlikely(bret.status != BLKIF_RSP_OKAY))
+ dev_dbg_ratelimited(&info->xbdev->dev,
+ "Bad return from blkdev data request: %#x\n",
+ bret.status);

break;
default:
@@ -1666,6 +1700,14 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
spin_unlock_irqrestore(&rinfo->ring_lock, flags);

return IRQ_HANDLED;
+
+ err:
+ info->connected = BLKIF_STATE_ERROR;
+
+ spin_unlock_irqrestore(&rinfo->ring_lock, flags);
+
+ pr_alert("%s disabled for further use\n", info->gd->disk_name);
+ return IRQ_HANDLED;
}


diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index eff0a8ece8bc..85abba74ed98 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -292,7 +292,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)

bo = kzalloc(sizeof(*bo), GFP_KERNEL);
if (!bo)
- return ERR_PTR(-ENOMEM);
+ return NULL;

mutex_lock(&vc4->bo_lock);
bo->label = VC4_BO_TYPE_KERNEL;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index df89f490e552..14373b06e63d 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2433,6 +2433,9 @@ static void wacom_wac_finger_event(struct hid_device *hdev,
struct wacom_features *features = &wacom->wacom_wac.features;

switch (equivalent_usage) {
+ case HID_DG_CONFIDENCE:
+ wacom_wac->hid_data.confidence = value;
+ break;
case HID_GD_X:
wacom_wac->hid_data.x = value;
break;
@@ -2463,7 +2466,8 @@ static void wacom_wac_finger_event(struct hid_device *hdev,


if (usage->usage_index + 1 == field->report_count) {
- if (equivalent_usage == wacom_wac->hid_data.last_slot_field)
+ if (equivalent_usage == wacom_wac->hid_data.last_slot_field &&
+ wacom_wac->hid_data.confidence)
wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input);
}
}
@@ -2476,6 +2480,8 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev,
struct hid_data* hid_data = &wacom_wac->hid_data;
int i;

+ hid_data->confidence = true;
+
for (i = 0; i < report->maxfield; i++) {
struct hid_field *field = report->field[i];
int j;
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index 55b542a6a66b..a61d3543b8e6 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -293,6 +293,7 @@ struct hid_data {
bool inrange_state;
bool invert_state;
bool tipswitch;
+ bool confidence;
int x;
int y;
int pressure;
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index 061b7824f698..2765ca732b95 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -1135,6 +1135,7 @@ void cec_received_msg_ts(struct cec_adapter *adap,
if (abort)
dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT;
msg->flags = dst->flags;
+ msg->sequence = dst->sequence;
/* Remove it from the wait_queue */
list_del_init(&data->list);

diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 8f108a30cba6..09a65f8f6203 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -4703,6 +4703,10 @@ type3_infoblock(struct net_device *dev, u_char count, u_char *p)
lp->ibn = 3;
lp->active = *p++;
if (MOTO_SROM_BUG) lp->active = 0;
+ /* if (MOTO_SROM_BUG) statement indicates lp->active could
+ * be 8 (i.e. the size of array lp->phy) */
+ if (WARN_ON(lp->active >= ARRAY_SIZE(lp->phy)))
+ return -EINVAL;
lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1);
lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1);
lp->phy[lp->active].mc = get_unaligned_le16(p); p += 2;
@@ -4994,19 +4998,23 @@ mii_get_phy(struct net_device *dev)
}
if ((j == limit) && (i < DE4X5_MAX_MII)) {
for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++);
- lp->phy[k].addr = i;
- lp->phy[k].id = id;
- lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */
- lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */
- lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */
- lp->mii_cnt++;
- lp->active++;
- printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
- j = de4x5_debug;
- de4x5_debug |= DEBUG_MII;
- de4x5_dbg_mii(dev, k);
- de4x5_debug = j;
- printk("\n");
+ if (k < DE4X5_MAX_PHY) {
+ lp->phy[k].addr = i;
+ lp->phy[k].id = id;
+ lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */
+ lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */
+ lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */
+ lp->mii_cnt++;
+ lp->active++;
+ printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
+ j = de4x5_debug;
+ de4x5_debug |= DEBUG_MII;
+ de4x5_dbg_mii(dev, k);
+ de4x5_debug = j;
+ printk("\n");
+ } else {
+ goto purgatory;
+ }
}
}
purgatory:
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 408b63faf9a8..c4e56784ed1b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -336,6 +336,10 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
return;

if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) {
+ /* DSAF_MAX_PORT_NUM is 6, but DSAF_GE_NUM is 8.
+ We need check to prevent array overflow */
+ if (port >= DSAF_MAX_PORT_NUM)
+ return;
reg_val_1 = 0x1 << port;
port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off;
/* there is difference between V1 and V2 in register.*/
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 5f8709aa0f4e..70a80e43d833 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2283,9 +2283,14 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
bool carry_xdp_prog)
{
struct bpf_prog *xdp_prog;
- int i, t;
+ int i, t, ret;

- mlx4_en_copy_priv(tmp, priv, prof);
+ ret = mlx4_en_copy_priv(tmp, priv, prof);
+ if (ret) {
+ en_warn(priv, "%s: mlx4_en_copy_priv() failed, return\n",
+ __func__);
+ return ret;
+ }

if (mlx4_en_alloc_resources(tmp)) {
en_warn(priv,
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index 1817deea98a4..aa4fcbc37d94 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -128,7 +128,7 @@ static const struct net_device_ops xtsonic_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
};

-static int __init sonic_probe1(struct net_device *dev)
+static int sonic_probe1(struct net_device *dev)
{
static unsigned version_printed = 0;
unsigned int silicon_revision;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 4994599728dc..3c0862f9b381 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -1078,8 +1078,14 @@ static int qlcnic_83xx_add_rings(struct qlcnic_adapter *adapter)
sds_mbx_size = sizeof(struct qlcnic_sds_mbx);
context_id = recv_ctx->context_id;
num_sds = adapter->drv_sds_rings - QLCNIC_MAX_SDS_RINGS;
- ahw->hw_ops->alloc_mbx_args(&cmd, adapter,
- QLCNIC_CMD_ADD_RCV_RINGS);
+ err = ahw->hw_ops->alloc_mbx_args(&cmd, adapter,
+ QLCNIC_CMD_ADD_RCV_RINGS);
+ if (err) {
+ dev_err(&adapter->pdev->dev,
+ "Failed to alloc mbx args %d\n", err);
+ return err;
+ }
+
cmd.req.arg[1] = 0 | (num_sds << 8) | (context_id << 16);

/* set up status rings, mbx 2-81 */
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 1b30636c8bc7..838b6fe9dfaa 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2052,7 +2052,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
if (dev->domain_data.phyirq > 0)
phydev->irq = dev->domain_data.phyirq;
else
- phydev->irq = 0;
+ phydev->irq = PHY_POLL;
netdev_dbg(dev->net, "phydev->irq = %d\n", phydev->irq);

/* set to AUTOMDIX */
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 6e58ee9f143e..5c7c608e24c9 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -208,6 +208,7 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));

+ memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
ret = vrf_ip6_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
dev->stats.tx_errors++;
@@ -289,6 +290,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
RT_SCOPE_LINK);
}

+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
vrf_dev->stats.tx_errors++;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 89e6a50b53da..ef7dd70a40a1 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -121,21 +121,17 @@ struct netfront_queue {

/*
* {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries
- * are linked from tx_skb_freelist through skb_entry.link.
- *
- * NB. Freelist index entries are always going to be less than
- * PAGE_OFFSET, whereas pointers to skbs will always be equal or
- * greater than PAGE_OFFSET: we use this property to distinguish
- * them.
+ * are linked from tx_skb_freelist through tx_link.
*/
- union skb_entry {
- struct sk_buff *skb;
- unsigned long link;
- } tx_skbs[NET_TX_RING_SIZE];
+ struct sk_buff *tx_skbs[NET_TX_RING_SIZE];
+ unsigned short tx_link[NET_TX_RING_SIZE];
+#define TX_LINK_NONE 0xffff
+#define TX_PENDING 0xfffe
grant_ref_t gref_tx_head;
grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
struct page *grant_tx_page[NET_TX_RING_SIZE];
unsigned tx_skb_freelist;
+ unsigned int tx_pend_queue;

spinlock_t rx_lock ____cacheline_aligned_in_smp;
struct xen_netif_rx_front_ring rx;
@@ -161,6 +157,9 @@ struct netfront_info {
struct netfront_stats __percpu *rx_stats;
struct netfront_stats __percpu *tx_stats;

+ /* Is device behaving sane? */
+ bool broken;
+
atomic_t rx_gso_checksum_fixup;
};

@@ -169,33 +168,25 @@ struct netfront_rx_info {
struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
};

-static void skb_entry_set_link(union skb_entry *list, unsigned short id)
-{
- list->link = id;
-}
-
-static int skb_entry_is_link(const union skb_entry *list)
-{
- BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link));
- return (unsigned long)list->skb < PAGE_OFFSET;
-}
-
/*
* Access macros for acquiring freeing slots in tx_skbs[].
*/

-static void add_id_to_freelist(unsigned *head, union skb_entry *list,
- unsigned short id)
+static void add_id_to_list(unsigned *head, unsigned short *list,
+ unsigned short id)
{
- skb_entry_set_link(&list[id], *head);
+ list[id] = *head;
*head = id;
}

-static unsigned short get_id_from_freelist(unsigned *head,
- union skb_entry *list)
+static unsigned short get_id_from_list(unsigned *head, unsigned short *list)
{
unsigned int id = *head;
- *head = list[id].link;
+
+ if (id != TX_LINK_NONE) {
+ *head = list[id];
+ list[id] = TX_LINK_NONE;
+ }
return id;
}

@@ -353,7 +344,7 @@ static int xennet_open(struct net_device *dev)
unsigned int i = 0;
struct netfront_queue *queue = NULL;

- if (!np->queues)
+ if (!np->queues || np->broken)
return -ENODEV;

for (i = 0; i < num_queues; ++i) {
@@ -381,27 +372,47 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
unsigned short id;
struct sk_buff *skb;
bool more_to_do;
+ const struct device *dev = &queue->info->netdev->dev;

BUG_ON(!netif_carrier_ok(queue->info->netdev));

do {
prod = queue->tx.sring->rsp_prod;
+ if (RING_RESPONSE_PROD_OVERFLOW(&queue->tx, prod)) {
+ dev_alert(dev, "Illegal number of responses %u\n",
+ prod - queue->tx.rsp_cons);
+ goto err;
+ }
rmb(); /* Ensure we see responses up to 'rp'. */

for (cons = queue->tx.rsp_cons; cons != prod; cons++) {
- struct xen_netif_tx_response *txrsp;
+ struct xen_netif_tx_response txrsp;

- txrsp = RING_GET_RESPONSE(&queue->tx, cons);
- if (txrsp->status == XEN_NETIF_RSP_NULL)
+ RING_COPY_RESPONSE(&queue->tx, cons, &txrsp);
+ if (txrsp.status == XEN_NETIF_RSP_NULL)
continue;

- id = txrsp->id;
- skb = queue->tx_skbs[id].skb;
+ id = txrsp.id;
+ if (id >= RING_SIZE(&queue->tx)) {
+ dev_alert(dev,
+ "Response has incorrect id (%u)\n",
+ id);
+ goto err;
+ }
+ if (queue->tx_link[id] != TX_PENDING) {
+ dev_alert(dev,
+ "Response for inactive request\n");
+ goto err;
+ }
+
+ queue->tx_link[id] = TX_LINK_NONE;
+ skb = queue->tx_skbs[id];
+ queue->tx_skbs[id] = NULL;
if (unlikely(gnttab_query_foreign_access(
queue->grant_tx_ref[id]) != 0)) {
- pr_alert("%s: warning -- grant still in use by backend domain\n",
- __func__);
- BUG();
+ dev_alert(dev,
+ "Grant still in use by backend domain\n");
+ goto err;
}
gnttab_end_foreign_access_ref(
queue->grant_tx_ref[id], GNTMAP_readonly);
@@ -409,7 +420,7 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
&queue->gref_tx_head, queue->grant_tx_ref[id]);
queue->grant_tx_ref[id] = GRANT_INVALID_REF;
queue->grant_tx_page[id] = NULL;
- add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id);
+ add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, id);
dev_kfree_skb_irq(skb);
}

@@ -419,13 +430,20 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
} while (more_to_do);

xennet_maybe_wake_tx(queue);
+
+ return;
+
+ err:
+ queue->info->broken = true;
+ dev_alert(dev, "Disabled for further use\n");
}

struct xennet_gnttab_make_txreq {
struct netfront_queue *queue;
struct sk_buff *skb;
struct page *page;
- struct xen_netif_tx_request *tx; /* Last request */
+ struct xen_netif_tx_request *tx; /* Last request on ring page */
+ struct xen_netif_tx_request tx_local; /* Last request local copy*/
unsigned int size;
};

@@ -441,7 +459,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
struct netfront_queue *queue = info->queue;
struct sk_buff *skb = info->skb;

- id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+ id = get_id_from_list(&queue->tx_skb_freelist, queue->tx_link);
tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
@@ -449,34 +467,37 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
gfn, GNTMAP_readonly);

- queue->tx_skbs[id].skb = skb;
+ queue->tx_skbs[id] = skb;
queue->grant_tx_page[id] = page;
queue->grant_tx_ref[id] = ref;

- tx->id = id;
- tx->gref = ref;
- tx->offset = offset;
- tx->size = len;
- tx->flags = 0;
+ info->tx_local.id = id;
+ info->tx_local.gref = ref;
+ info->tx_local.offset = offset;
+ info->tx_local.size = len;
+ info->tx_local.flags = 0;
+
+ *tx = info->tx_local;
+
+ /*
+ * Put the request in the pending queue, it will be set to be pending
+ * when the producer index is about to be raised.
+ */
+ add_id_to_list(&queue->tx_pend_queue, queue->tx_link, id);

info->tx = tx;
- info->size += tx->size;
+ info->size += info->tx_local.size;
}

static struct xen_netif_tx_request *xennet_make_first_txreq(
- struct netfront_queue *queue, struct sk_buff *skb,
- struct page *page, unsigned int offset, unsigned int len)
+ struct xennet_gnttab_make_txreq *info,
+ unsigned int offset, unsigned int len)
{
- struct xennet_gnttab_make_txreq info = {
- .queue = queue,
- .skb = skb,
- .page = page,
- .size = 0,
- };
+ info->size = 0;

- gnttab_for_one_grant(page, offset, len, xennet_tx_setup_grant, &info);
+ gnttab_for_one_grant(info->page, offset, len, xennet_tx_setup_grant, info);

- return info.tx;
+ return info->tx;
}

static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,
@@ -489,35 +510,27 @@ static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,
xennet_tx_setup_grant(gfn, offset, len, data);
}

-static struct xen_netif_tx_request *xennet_make_txreqs(
- struct netfront_queue *queue, struct xen_netif_tx_request *tx,
- struct sk_buff *skb, struct page *page,
+static void xennet_make_txreqs(
+ struct xennet_gnttab_make_txreq *info,
+ struct page *page,
unsigned int offset, unsigned int len)
{
- struct xennet_gnttab_make_txreq info = {
- .queue = queue,
- .skb = skb,
- .tx = tx,
- };
-
/* Skip unused frames from start of page */
page += offset >> PAGE_SHIFT;
offset &= ~PAGE_MASK;

while (len) {
- info.page = page;
- info.size = 0;
+ info->page = page;
+ info->size = 0;

gnttab_foreach_grant_in_range(page, offset, len,
xennet_make_one_txreq,
- &info);
+ info);

page++;
offset = 0;
- len -= info.size;
+ len -= info->size;
}
-
- return info.tx;
}

/*
@@ -564,13 +577,22 @@ static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
return queue_idx;
}

+static void xennet_mark_tx_pending(struct netfront_queue *queue)
+{
+ unsigned int i;
+
+ while ((i = get_id_from_list(&queue->tx_pend_queue, queue->tx_link)) !=
+ TX_LINK_NONE)
+ queue->tx_link[i] = TX_PENDING;
+}
+
#define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)

static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats);
- struct xen_netif_tx_request *tx, *first_tx;
+ struct xen_netif_tx_request *first_tx;
unsigned int i;
int notify;
int slots;
@@ -579,6 +601,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
unsigned int len;
unsigned long flags;
struct netfront_queue *queue = NULL;
+ struct xennet_gnttab_make_txreq info = { };
unsigned int num_queues = dev->real_num_tx_queues;
u16 queue_index;
struct sk_buff *nskb;
@@ -586,6 +609,8 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
/* Drop the packet if no queues are set up */
if (num_queues < 1)
goto drop;
+ if (unlikely(np->broken))
+ goto drop;
/* Determine which queue to transmit this SKB on */
queue_index = skb_get_queue_mapping(skb);
queue = &np->queues[queue_index];
@@ -636,21 +661,24 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
}

/* First request for the linear area. */
- first_tx = tx = xennet_make_first_txreq(queue, skb,
- page, offset, len);
- offset += tx->size;
+ info.queue = queue;
+ info.skb = skb;
+ info.page = page;
+ first_tx = xennet_make_first_txreq(&info, offset, len);
+ offset += info.tx_local.size;
if (offset == PAGE_SIZE) {
page++;
offset = 0;
}
- len -= tx->size;
+ len -= info.tx_local.size;

if (skb->ip_summed == CHECKSUM_PARTIAL)
/* local packet? */
- tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
+ first_tx->flags |= XEN_NETTXF_csum_blank |
+ XEN_NETTXF_data_validated;
else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
/* remote but checksummed. */
- tx->flags |= XEN_NETTXF_data_validated;
+ first_tx->flags |= XEN_NETTXF_data_validated;

/* Optional extra info after the first request. */
if (skb_shinfo(skb)->gso_size) {
@@ -659,7 +687,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
gso = (struct xen_netif_extra_info *)
RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);

- tx->flags |= XEN_NETTXF_extra_info;
+ first_tx->flags |= XEN_NETTXF_extra_info;

gso->u.gso.size = skb_shinfo(skb)->gso_size;
gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ?
@@ -673,19 +701,21 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
}

/* Requests for the rest of the linear area. */
- tx = xennet_make_txreqs(queue, tx, skb, page, offset, len);
+ xennet_make_txreqs(&info, page, offset, len);

/* Requests for all the frags. */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
- tx = xennet_make_txreqs(queue, tx, skb,
- skb_frag_page(frag), frag->page_offset,
+ xennet_make_txreqs(&info, skb_frag_page(frag),
+ frag->page_offset,
skb_frag_size(frag));
}

/* First request has the packet length. */
first_tx->size = skb->len;

+ xennet_mark_tx_pending(queue);
+
RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
if (notify)
notify_remote_via_irq(queue->tx_irq);
@@ -743,7 +773,7 @@ static int xennet_get_extras(struct netfront_queue *queue,
RING_IDX rp)

{
- struct xen_netif_extra_info *extra;
+ struct xen_netif_extra_info extra;
struct device *dev = &queue->info->netdev->dev;
RING_IDX cons = queue->rx.rsp_cons;
int err = 0;
@@ -759,24 +789,22 @@ static int xennet_get_extras(struct netfront_queue *queue,
break;
}

- extra = (struct xen_netif_extra_info *)
- RING_GET_RESPONSE(&queue->rx, ++cons);
+ RING_COPY_RESPONSE(&queue->rx, ++cons, &extra);

- if (unlikely(!extra->type ||
- extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
+ if (unlikely(!extra.type ||
+ extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
if (net_ratelimit())
dev_warn(dev, "Invalid extra type: %d\n",
- extra->type);
+ extra.type);
err = -EINVAL;
} else {
- memcpy(&extras[extra->type - 1], extra,
- sizeof(*extra));
+ extras[extra.type - 1] = extra;
}

skb = xennet_get_rx_skb(queue, cons);
ref = xennet_get_rx_ref(queue, cons);
xennet_move_rx_slot(queue, skb, ref);
- } while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE);
+ } while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);

queue->rx.rsp_cons = cons;
return err;
@@ -786,7 +814,7 @@ static int xennet_get_responses(struct netfront_queue *queue,
struct netfront_rx_info *rinfo, RING_IDX rp,
struct sk_buff_head *list)
{
- struct xen_netif_rx_response *rx = &rinfo->rx;
+ struct xen_netif_rx_response *rx = &rinfo->rx, rx_local;
struct xen_netif_extra_info *extras = rinfo->extras;
struct device *dev = &queue->info->netdev->dev;
RING_IDX cons = queue->rx.rsp_cons;
@@ -844,7 +872,8 @@ static int xennet_get_responses(struct netfront_queue *queue,
break;
}

- rx = RING_GET_RESPONSE(&queue->rx, cons + slots);
+ RING_COPY_RESPONSE(&queue->rx, cons + slots, &rx_local);
+ rx = &rx_local;
skb = xennet_get_rx_skb(queue, cons + slots);
ref = xennet_get_rx_ref(queue, cons + slots);
slots++;
@@ -899,10 +928,11 @@ static int xennet_fill_frags(struct netfront_queue *queue,
struct sk_buff *nskb;

while ((nskb = __skb_dequeue(list))) {
- struct xen_netif_rx_response *rx =
- RING_GET_RESPONSE(&queue->rx, ++cons);
+ struct xen_netif_rx_response rx;
skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];

+ RING_COPY_RESPONSE(&queue->rx, ++cons, &rx);
+
if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;

@@ -917,7 +947,7 @@ static int xennet_fill_frags(struct netfront_queue *queue,

skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
skb_frag_page(nfrag),
- rx->offset, rx->status, PAGE_SIZE);
+ rx.offset, rx.status, PAGE_SIZE);

skb_shinfo(nskb)->nr_frags = 0;
kfree_skb(nskb);
@@ -1010,12 +1040,19 @@ static int xennet_poll(struct napi_struct *napi, int budget)
skb_queue_head_init(&tmpq);

rp = queue->rx.sring->rsp_prod;
+ if (RING_RESPONSE_PROD_OVERFLOW(&queue->rx, rp)) {
+ dev_alert(&dev->dev, "Illegal number of responses %u\n",
+ rp - queue->rx.rsp_cons);
+ queue->info->broken = true;
+ spin_unlock(&queue->rx_lock);
+ return 0;
+ }
rmb(); /* Ensure we see queued responses up to 'rp'. */

i = queue->rx.rsp_cons;
work_done = 0;
while ((i != rp) && (work_done < budget)) {
- memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx));
+ RING_COPY_RESPONSE(&queue->rx, i, rx);
memset(extras, 0, sizeof(rinfo.extras));

err = xennet_get_responses(queue, &rinfo, rp, &tmpq);
@@ -1137,17 +1174,18 @@ static void xennet_release_tx_bufs(struct netfront_queue *queue)

for (i = 0; i < NET_TX_RING_SIZE; i++) {
/* Skip over entries which are actually freelist references */
- if (skb_entry_is_link(&queue->tx_skbs[i]))
+ if (!queue->tx_skbs[i])
continue;

- skb = queue->tx_skbs[i].skb;
+ skb = queue->tx_skbs[i];
+ queue->tx_skbs[i] = NULL;
get_page(queue->grant_tx_page[i]);
gnttab_end_foreign_access(queue->grant_tx_ref[i],
GNTMAP_readonly,
(unsigned long)page_address(queue->grant_tx_page[i]));
queue->grant_tx_page[i] = NULL;
queue->grant_tx_ref[i] = GRANT_INVALID_REF;
- add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i);
+ add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, i);
dev_kfree_skb_irq(skb);
}
}
@@ -1227,6 +1265,9 @@ static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
struct netfront_queue *queue = dev_id;
unsigned long flags;

+ if (queue->info->broken)
+ return IRQ_HANDLED;
+
spin_lock_irqsave(&queue->tx_lock, flags);
xennet_tx_buf_gc(queue);
spin_unlock_irqrestore(&queue->tx_lock, flags);
@@ -1239,6 +1280,9 @@ static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
struct netfront_queue *queue = dev_id;
struct net_device *dev = queue->info->netdev;

+ if (queue->info->broken)
+ return IRQ_HANDLED;
+
if (likely(netif_carrier_ok(dev) &&
RING_HAS_UNCONSUMED_RESPONSES(&queue->rx)))
napi_schedule(&queue->napi);
@@ -1260,6 +1304,10 @@ static void xennet_poll_controller(struct net_device *dev)
struct netfront_info *info = netdev_priv(dev);
unsigned int num_queues = dev->real_num_tx_queues;
unsigned int i;
+
+ if (info->broken)
+ return;
+
for (i = 0; i < num_queues; ++i)
xennet_interrupt(0, &info->queues[i]);
}
@@ -1630,13 +1678,15 @@ static int xennet_init_queue(struct netfront_queue *queue)
snprintf(queue->name, sizeof(queue->name), "vif%s-q%u",
devid, queue->id);

- /* Initialise tx_skbs as a free chain containing every entry. */
+ /* Initialise tx_skb_freelist as a free chain containing every entry. */
queue->tx_skb_freelist = 0;
+ queue->tx_pend_queue = TX_LINK_NONE;
for (i = 0; i < NET_TX_RING_SIZE; i++) {
- skb_entry_set_link(&queue->tx_skbs[i], i+1);
+ queue->tx_link[i] = i + 1;
queue->grant_tx_ref[i] = GRANT_INVALID_REF;
queue->grant_tx_page[i] = NULL;
}
+ queue->tx_link[NET_TX_RING_SIZE - 1] = TX_LINK_NONE;

/* Clear out rx_skbs */
for (i = 0; i < NET_RX_RING_SIZE; i++) {
@@ -1841,6 +1891,9 @@ static int talk_to_netback(struct xenbus_device *dev,
if (info->queues)
xennet_destroy_queues(info);

+ /* For the case of a reconnect reset the "broken" indicator. */
+ info->broken = false;
+
err = xennet_create_queues(info, &num_queues);
if (err < 0) {
xenbus_dev_fatal(dev, err, "creating queues");
diff --git a/drivers/pci/host/pci-aardvark.c b/drivers/pci/host/pci-aardvark.c
index a572b2fb7af8..9ae544e113dc 100644
--- a/drivers/pci/host/pci-aardvark.c
+++ b/drivers/pci/host/pci-aardvark.c
@@ -12,6 +12,7 @@
*/

#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
@@ -20,6 +21,7 @@
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/of_address.h>
+#include <linux/of_gpio.h>
#include <linux/of_pci.h>

/* PCIe core registers */
@@ -27,16 +29,7 @@
#define PCIE_CORE_CMD_IO_ACCESS_EN BIT(0)
#define PCIE_CORE_CMD_MEM_ACCESS_EN BIT(1)
#define PCIE_CORE_CMD_MEM_IO_REQ_EN BIT(2)
-#define PCIE_CORE_DEV_CTRL_STATS_REG 0xc8
-#define PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE (0 << 4)
-#define PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT 5
-#define PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE (0 << 11)
-#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT 12
-#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ 0x2
-#define PCIE_CORE_LINK_CTRL_STAT_REG 0xd0
-#define PCIE_CORE_LINK_L0S_ENTRY BIT(0)
-#define PCIE_CORE_LINK_TRAINING BIT(5)
-#define PCIE_CORE_LINK_WIDTH_SHIFT 20
+#define PCIE_CORE_PCIEXP_CAP 0xc0
#define PCIE_CORE_ERR_CAPCTL_REG 0x118
#define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX BIT(5)
#define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN BIT(6)
@@ -117,29 +110,92 @@
/* PCIe window configuration */
#define OB_WIN_BASE_ADDR 0x4c00
#define OB_WIN_BLOCK_SIZE 0x20
+#define OB_WIN_COUNT 8
#define OB_WIN_REG_ADDR(win, offset) (OB_WIN_BASE_ADDR + \
OB_WIN_BLOCK_SIZE * (win) + \
(offset))
#define OB_WIN_MATCH_LS(win) OB_WIN_REG_ADDR(win, 0x00)
+#define OB_WIN_ENABLE BIT(0)
#define OB_WIN_MATCH_MS(win) OB_WIN_REG_ADDR(win, 0x04)
#define OB_WIN_REMAP_LS(win) OB_WIN_REG_ADDR(win, 0x08)
#define OB_WIN_REMAP_MS(win) OB_WIN_REG_ADDR(win, 0x0c)
#define OB_WIN_MASK_LS(win) OB_WIN_REG_ADDR(win, 0x10)
#define OB_WIN_MASK_MS(win) OB_WIN_REG_ADDR(win, 0x14)
#define OB_WIN_ACTIONS(win) OB_WIN_REG_ADDR(win, 0x18)
-
-/* PCIe window types */
-#define OB_PCIE_MEM 0x0
-#define OB_PCIE_IO 0x4
+#define OB_WIN_DEFAULT_ACTIONS (OB_WIN_ACTIONS(OB_WIN_COUNT-1) + 0x4)
+#define OB_WIN_FUNC_NUM_MASK GENMASK(31, 24)
+#define OB_WIN_FUNC_NUM_SHIFT 24
+#define OB_WIN_FUNC_NUM_ENABLE BIT(23)
+#define OB_WIN_BUS_NUM_BITS_MASK GENMASK(22, 20)
+#define OB_WIN_BUS_NUM_BITS_SHIFT 20
+#define OB_WIN_MSG_CODE_ENABLE BIT(22)
+#define OB_WIN_MSG_CODE_MASK GENMASK(21, 14)
+#define OB_WIN_MSG_CODE_SHIFT 14
+#define OB_WIN_MSG_PAYLOAD_LEN BIT(12)
+#define OB_WIN_ATTR_ENABLE BIT(11)
+#define OB_WIN_ATTR_TC_MASK GENMASK(10, 8)
+#define OB_WIN_ATTR_TC_SHIFT 8
+#define OB_WIN_ATTR_RELAXED BIT(7)
+#define OB_WIN_ATTR_NOSNOOP BIT(6)
+#define OB_WIN_ATTR_POISON BIT(5)
+#define OB_WIN_ATTR_IDO BIT(4)
+#define OB_WIN_TYPE_MASK GENMASK(3, 0)
+#define OB_WIN_TYPE_SHIFT 0
+#define OB_WIN_TYPE_MEM 0x0
+#define OB_WIN_TYPE_IO 0x4
+#define OB_WIN_TYPE_CONFIG_TYPE0 0x8
+#define OB_WIN_TYPE_CONFIG_TYPE1 0x9
+#define OB_WIN_TYPE_MSG 0xc

/* LMI registers base address and register offsets */
#define LMI_BASE_ADDR 0x6000
#define CFG_REG (LMI_BASE_ADDR + 0x0)
#define LTSSM_SHIFT 24
#define LTSSM_MASK 0x3f
-#define LTSSM_L0 0x10
#define RC_BAR_CONFIG 0x300

+/* LTSSM values in CFG_REG */
+enum {
+ LTSSM_DETECT_QUIET = 0x0,
+ LTSSM_DETECT_ACTIVE = 0x1,
+ LTSSM_POLLING_ACTIVE = 0x2,
+ LTSSM_POLLING_COMPLIANCE = 0x3,
+ LTSSM_POLLING_CONFIGURATION = 0x4,
+ LTSSM_CONFIG_LINKWIDTH_START = 0x5,
+ LTSSM_CONFIG_LINKWIDTH_ACCEPT = 0x6,
+ LTSSM_CONFIG_LANENUM_ACCEPT = 0x7,
+ LTSSM_CONFIG_LANENUM_WAIT = 0x8,
+ LTSSM_CONFIG_COMPLETE = 0x9,
+ LTSSM_CONFIG_IDLE = 0xa,
+ LTSSM_RECOVERY_RCVR_LOCK = 0xb,
+ LTSSM_RECOVERY_SPEED = 0xc,
+ LTSSM_RECOVERY_RCVR_CFG = 0xd,
+ LTSSM_RECOVERY_IDLE = 0xe,
+ LTSSM_L0 = 0x10,
+ LTSSM_RX_L0S_ENTRY = 0x11,
+ LTSSM_RX_L0S_IDLE = 0x12,
+ LTSSM_RX_L0S_FTS = 0x13,
+ LTSSM_TX_L0S_ENTRY = 0x14,
+ LTSSM_TX_L0S_IDLE = 0x15,
+ LTSSM_TX_L0S_FTS = 0x16,
+ LTSSM_L1_ENTRY = 0x17,
+ LTSSM_L1_IDLE = 0x18,
+ LTSSM_L2_IDLE = 0x19,
+ LTSSM_L2_TRANSMIT_WAKE = 0x1a,
+ LTSSM_DISABLED = 0x20,
+ LTSSM_LOOPBACK_ENTRY_MASTER = 0x21,
+ LTSSM_LOOPBACK_ACTIVE_MASTER = 0x22,
+ LTSSM_LOOPBACK_EXIT_MASTER = 0x23,
+ LTSSM_LOOPBACK_ENTRY_SLAVE = 0x24,
+ LTSSM_LOOPBACK_ACTIVE_SLAVE = 0x25,
+ LTSSM_LOOPBACK_EXIT_SLAVE = 0x26,
+ LTSSM_HOT_RESET = 0x27,
+ LTSSM_RECOVERY_EQUALIZATION_PHASE0 = 0x28,
+ LTSSM_RECOVERY_EQUALIZATION_PHASE1 = 0x29,
+ LTSSM_RECOVERY_EQUALIZATION_PHASE2 = 0x2a,
+ LTSSM_RECOVERY_EQUALIZATION_PHASE3 = 0x2b,
+};
+
/* PCIe core controller registers */
#define CTRL_CORE_BASE_ADDR 0x18000
#define CTRL_CONFIG_REG (CTRL_CORE_BASE_ADDR + 0x0)
@@ -200,6 +256,13 @@ struct advk_pcie {
struct platform_device *pdev;
void __iomem *base;
struct list_head resources;
+ struct {
+ phys_addr_t match;
+ phys_addr_t remap;
+ phys_addr_t mask;
+ u32 actions;
+ } wins[OB_WIN_COUNT];
+ u8 wins_count;
struct irq_domain *irq_domain;
struct irq_chip irq_chip;
raw_spinlock_t irq_lock;
@@ -212,6 +275,8 @@ struct advk_pcie {
struct mutex msi_used_lock;
u16 msi_msg;
int root_bus_nr;
+ int link_gen;
+ struct gpio_desc *reset_gpio;
};

static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg)
@@ -224,52 +289,155 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg)
return readl(pcie->base + reg);
}

-static int advk_pcie_link_up(struct advk_pcie *pcie)
+static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie)
{
- u32 val, ltssm_state;
+ u32 val;
+ u8 ltssm_state;

val = advk_readl(pcie, CFG_REG);
ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK;
- return ltssm_state >= LTSSM_L0;
+ return ltssm_state;
+}
+
+static inline bool advk_pcie_link_up(struct advk_pcie *pcie)
+{
+ /* check if LTSSM is in normal operation - some L* state */
+ u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+ return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED;
+}
+
+static inline bool advk_pcie_link_training(struct advk_pcie *pcie)
+{
+ /*
+ * According to PCIe Base specification 3.0, Table 4-14: Link
+ * Status Mapped to the LTSSM is Link Training mapped to LTSSM
+ * Configuration and Recovery states.
+ */
+ u8 ltssm_state = advk_pcie_ltssm_state(pcie);
+ return ((ltssm_state >= LTSSM_CONFIG_LINKWIDTH_START &&
+ ltssm_state < LTSSM_L0) ||
+ (ltssm_state >= LTSSM_RECOVERY_EQUALIZATION_PHASE0 &&
+ ltssm_state <= LTSSM_RECOVERY_EQUALIZATION_PHASE3));
}

static int advk_pcie_wait_for_link(struct advk_pcie *pcie)
{
- struct device *dev = &pcie->pdev->dev;
int retries;

/* check if the link is up or not */
for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) {
- if (advk_pcie_link_up(pcie)) {
- dev_info(dev, "link up\n");
+ if (advk_pcie_link_up(pcie))
return 0;
- }

usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
}

- dev_err(dev, "link never came up\n");
return -ETIMEDOUT;
}

+static void advk_pcie_issue_perst(struct advk_pcie *pcie)
+{
+ if (!pcie->reset_gpio)
+ return;
+
+ /* 10ms delay is needed for some cards */
+ dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n");
+ gpiod_set_value_cansleep(pcie->reset_gpio, 1);
+ usleep_range(10000, 11000);
+ gpiod_set_value_cansleep(pcie->reset_gpio, 0);
+}
+
+static void advk_pcie_train_link(struct advk_pcie *pcie)
+{
+ struct device *dev = &pcie->pdev->dev;
+ u32 reg;
+ int ret;
+
+ /*
+ * Setup PCIe rev / gen compliance based on device tree property
+ * 'max-link-speed' which also forces maximal link speed.
+ */
+ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+ reg &= ~PCIE_GEN_SEL_MSK;
+ if (pcie->link_gen == 3)
+ reg |= SPEED_GEN_3;
+ else if (pcie->link_gen == 2)
+ reg |= SPEED_GEN_2;
+ else
+ reg |= SPEED_GEN_1;
+ advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+ /*
+ * Set maximal link speed value also into PCIe Link Control 2 register.
+ * Armada 3700 Functional Specification says that default value is based
+ * on SPEED_GEN but tests showed that default value is always 8.0 GT/s.
+ */
+ reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+ reg &= ~PCI_EXP_LNKCTL2_TLS;
+ if (pcie->link_gen == 3)
+ reg |= PCI_EXP_LNKCTL2_TLS_8_0GT;
+ else if (pcie->link_gen == 2)
+ reg |= PCI_EXP_LNKCTL2_TLS_5_0GT;
+ else
+ reg |= PCI_EXP_LNKCTL2_TLS_2_5GT;
+ advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2);
+
+ /* Enable link training after selecting PCIe generation */
+ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
+ reg |= LINK_TRAINING_EN;
+ advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
+
+ /*
+ * Reset PCIe card via PERST# signal. Some cards are not detected
+ * during link training when they are in some non-initial state.
+ */
+ advk_pcie_issue_perst(pcie);
+
+ /*
+ * PERST# signal could have been asserted by pinctrl subsystem before
+ * probe() callback has been called or issued explicitly by reset gpio
+ * function advk_pcie_issue_perst(), making the endpoint going into
+ * fundamental reset. As required by PCI Express spec (PCI Express
+ * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1
+ * Conventional Reset) a delay for at least 100ms after such a reset
+ * before sending a Configuration Request to the device is needed.
+ * So wait until PCIe link is up. Function advk_pcie_wait_for_link()
+ * waits for link at least 900ms.
+ */
+ ret = advk_pcie_wait_for_link(pcie);
+ if (ret < 0)
+ dev_err(dev, "link never came up\n");
+ else
+ dev_info(dev, "link up\n");
+}
+
/*
* Set PCIe address window register which could be used for memory
* mapping.
*/
-static void advk_pcie_set_ob_win(struct advk_pcie *pcie,
- u32 win_num, u32 match_ms,
- u32 match_ls, u32 mask_ms,
- u32 mask_ls, u32 remap_ms,
- u32 remap_ls, u32 action)
+static void advk_pcie_set_ob_win(struct advk_pcie *pcie, u8 win_num,
+ phys_addr_t match, phys_addr_t remap,
+ phys_addr_t mask, u32 actions)
{
- advk_writel(pcie, match_ls, OB_WIN_MATCH_LS(win_num));
- advk_writel(pcie, match_ms, OB_WIN_MATCH_MS(win_num));
- advk_writel(pcie, mask_ms, OB_WIN_MASK_MS(win_num));
- advk_writel(pcie, mask_ls, OB_WIN_MASK_LS(win_num));
- advk_writel(pcie, remap_ms, OB_WIN_REMAP_MS(win_num));
- advk_writel(pcie, remap_ls, OB_WIN_REMAP_LS(win_num));
- advk_writel(pcie, action, OB_WIN_ACTIONS(win_num));
- advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num));
+ advk_writel(pcie, OB_WIN_ENABLE |
+ lower_32_bits(match), OB_WIN_MATCH_LS(win_num));
+ advk_writel(pcie, upper_32_bits(match), OB_WIN_MATCH_MS(win_num));
+ advk_writel(pcie, lower_32_bits(remap), OB_WIN_REMAP_LS(win_num));
+ advk_writel(pcie, upper_32_bits(remap), OB_WIN_REMAP_MS(win_num));
+ advk_writel(pcie, lower_32_bits(mask), OB_WIN_MASK_LS(win_num));
+ advk_writel(pcie, upper_32_bits(mask), OB_WIN_MASK_MS(win_num));
+ advk_writel(pcie, actions, OB_WIN_ACTIONS(win_num));
+}
+
+static void advk_pcie_disable_ob_win(struct advk_pcie *pcie, u8 win_num)
+{
+ advk_writel(pcie, 0, OB_WIN_MATCH_LS(win_num));
+ advk_writel(pcie, 0, OB_WIN_MATCH_MS(win_num));
+ advk_writel(pcie, 0, OB_WIN_REMAP_LS(win_num));
+ advk_writel(pcie, 0, OB_WIN_REMAP_MS(win_num));
+ advk_writel(pcie, 0, OB_WIN_MASK_LS(win_num));
+ advk_writel(pcie, 0, OB_WIN_MASK_MS(win_num));
+ advk_writel(pcie, 0, OB_WIN_ACTIONS(win_num));
}

static void advk_pcie_setup_hw(struct advk_pcie *pcie)
@@ -277,10 +445,6 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
u32 reg;
int i;

- /* Point PCIe unit MBUS decode windows to DRAM space */
- for (i = 0; i < 8; i++)
- advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0);
-
/* Set to Direct mode */
reg = advk_readl(pcie, CTRL_CONFIG_REG);
reg &= ~(CTRL_MODE_MASK << CTRL_MODE_SHIFT);
@@ -299,36 +463,27 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV;
advk_writel(pcie, reg, PCIE_CORE_ERR_CAPCTL_REG);

- /* Set PCIe Device Control and Status 1 PF0 register */
- reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE |
- (7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) |
- PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE |
- (PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ <<
- PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT);
- advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG);
+ /* Set PCIe Device Control register */
+ reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);
+ reg &= ~PCI_EXP_DEVCTL_RELAX_EN;
+ reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN;
+ reg &= ~PCI_EXP_DEVCTL_PAYLOAD;
+ reg &= ~PCI_EXP_DEVCTL_READRQ;
+ reg |= PCI_EXP_DEVCTL_PAYLOAD_512B;
+ reg |= PCI_EXP_DEVCTL_READRQ_512B;
+ advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL);

/* Program PCIe Control 2 to disable strict ordering */
reg = PCIE_CORE_CTRL2_RESERVED |
PCIE_CORE_CTRL2_TD_ENABLE;
advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);

- /* Set GEN2 */
- reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
- reg &= ~PCIE_GEN_SEL_MSK;
- reg |= SPEED_GEN_2;
- advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
/* Set lane X1 */
reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
reg &= ~LANE_CNT_MSK;
reg |= LANE_COUNT_1;
advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);

- /* Enable link training */
- reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG);
- reg |= LINK_TRAINING_EN;
- advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
-
/* Enable MSI */
reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
reg |= PCIE_CORE_CTRL2_MSI_ENABLE;
@@ -353,21 +508,52 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK);
advk_writel(pcie, reg, HOST_CTRL_INT_MASK_REG);

+ /*
+ * Enable AXI address window location generation:
+ * When it is enabled, the default outbound window
+ * configurations (Default User Field: 0xD0074CFC)
+ * are used to transparent address translation for
+ * the outbound transactions. Thus, PCIe address
+ * windows are not required for transparent memory
+ * access when default outbound window configuration
+ * is set for memory access.
+ */
reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
reg |= PCIE_CORE_CTRL2_OB_WIN_ENABLE;
advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG);

- /* Bypass the address window mapping for PIO */
+ /*
+ * Set memory access in Default User Field so it
+ * is not required to configure PCIe address for
+ * transparent memory access.
+ */
+ advk_writel(pcie, OB_WIN_TYPE_MEM, OB_WIN_DEFAULT_ACTIONS);
+
+ /*
+ * Bypass the address window mapping for PIO:
+ * Since PIO access already contains all required
+ * info over AXI interface by PIO registers, the
+ * address window is not required.
+ */
reg = advk_readl(pcie, PIO_CTRL);
reg |= PIO_CTRL_ADDR_WIN_DISABLE;
advk_writel(pcie, reg, PIO_CTRL);

- /* Start link training */
- reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG);
- reg |= PCIE_CORE_LINK_TRAINING;
- advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG);
+ /*
+ * Configure PCIe address windows for non-memory or
+ * non-transparent access as by default PCIe uses
+ * transparent memory access.
+ */
+ for (i = 0; i < pcie->wins_count; i++)
+ advk_pcie_set_ob_win(pcie, i,
+ pcie->wins[i].match, pcie->wins[i].remap,
+ pcie->wins[i].mask, pcie->wins[i].actions);

- advk_pcie_wait_for_link(pcie);
+ /* Disable remaining PCIe outbound windows */
+ for (i = pcie->wins_count; i < OB_WIN_COUNT; i++)
+ advk_pcie_disable_ob_win(pcie, i);
+
+ advk_pcie_train_link(pcie);

reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
reg |= PCIE_CORE_CMD_MEM_ACCESS_EN |
@@ -502,6 +688,22 @@ static bool advk_pcie_pio_is_running(struct advk_pcie *pcie)
return false;
}

+static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
+ int devfn)
+{
+ if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+ return false;
+
+ /*
+ * If the link goes down after we check for link-up, nothing bad
+ * happens but the config access times out.
+ */
+ if (bus->number != pcie->root_bus_nr && !advk_pcie_link_up(pcie))
+ return false;
+
+ return true;
+}
+
static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
int where, int size, u32 *val)
{
@@ -509,7 +711,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
u32 reg;
int ret;

- if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) {
+ if (!advk_pcie_valid_device(pcie, bus, devfn)) {
*val = 0xffffffff;
return PCIBIOS_DEVICE_NOT_FOUND;
}
@@ -541,8 +743,10 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
advk_writel(pcie, 1, PIO_START);

ret = advk_pcie_wait_pio(pcie);
- if (ret < 0)
+ if (ret < 0) {
+ *val = 0xffffffff;
return PCIBIOS_SET_FAILED;
+ }

/* Check PIO status and get the read result */
ret = advk_pcie_check_pio_status(pcie, val);
@@ -568,7 +772,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
int offset;
int ret;

- if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+ if (!advk_pcie_valid_device(pcie, bus, devfn))
return PCIBIOS_DEVICE_NOT_FOUND;

if (where % size)
@@ -789,6 +993,7 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie)
struct device_node *node = dev->of_node;
struct device_node *pcie_intc_node;
struct irq_chip *irq_chip;
+ int ret = 0;

raw_spin_lock_init(&pcie->irq_lock);

@@ -803,8 +1008,8 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie)
irq_chip->name = devm_kasprintf(dev, GFP_KERNEL, "%s-irq",
dev_name(dev));
if (!irq_chip->name) {
- of_node_put(pcie_intc_node);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_put_node;
}

irq_chip->irq_mask = advk_pcie_irq_mask;
@@ -816,11 +1021,13 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie)
&advk_pcie_irq_domain_ops, pcie);
if (!pcie->irq_domain) {
dev_err(dev, "Failed to get a INTx IRQ domain\n");
- of_node_put(pcie_intc_node);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_put_node;
}

- return 0;
+out_put_node:
+ of_node_put(pcie_intc_node);
+ return ret;
}

static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie)
@@ -926,13 +1133,7 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)

switch (resource_type(res)) {
case IORESOURCE_IO:
- advk_pcie_set_ob_win(pcie, 1,
- upper_32_bits(res->start),
- lower_32_bits(res->start),
- 0, 0xF8000000, 0,
- lower_32_bits(res->start),
- OB_PCIE_IO);
- err = pci_remap_iospace(res, iobase);
+ err = devm_pci_remap_iospace(dev, res, iobase);
if (err) {
dev_warn(dev, "error %d: failed to map resource %pR\n",
err, res);
@@ -940,12 +1141,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
}
break;
case IORESOURCE_MEM:
- advk_pcie_set_ob_win(pcie, 0,
- upper_32_bits(res->start),
- lower_32_bits(res->start),
- 0x0, 0xF8000000, 0,
- lower_32_bits(res->start),
- (2 << 20) | OB_PCIE_MEM);
res_valid |= !(res->flags & IORESOURCE_PREFETCH);
break;
case IORESOURCE_BUS:
@@ -974,6 +1169,7 @@ static int advk_pcie_probe(struct platform_device *pdev)
struct resource *res;
struct pci_bus *bus, *child;
struct pci_host_bridge *bridge;
+ struct resource_entry *entry;
int ret, irq;

bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie));
@@ -1003,6 +1199,103 @@ static int advk_pcie_probe(struct platform_device *pdev)
return ret;
}

+ resource_list_for_each_entry(entry, &pcie->resources) {
+ resource_size_t start = entry->res->start;
+ resource_size_t size = resource_size(entry->res);
+ unsigned long type = resource_type(entry->res);
+ u64 win_size;
+
+ /*
+ * Aardvark hardware allows to configure also PCIe window
+ * for config type 0 and type 1 mapping, but driver uses
+ * only PIO for issuing configuration transfers which does
+ * not use PCIe window configuration.
+ */
+ if (type != IORESOURCE_MEM && type != IORESOURCE_MEM_64 &&
+ type != IORESOURCE_IO)
+ continue;
+
+ /*
+ * Skip transparent memory resources. Default outbound access
+ * configuration is set to transparent memory access so it
+ * does not need window configuration.
+ */
+ if ((type == IORESOURCE_MEM || type == IORESOURCE_MEM_64) &&
+ entry->offset == 0)
+ continue;
+
+ /*
+ * The n-th PCIe window is configured by tuple (match, remap, mask)
+ * and an access to address A uses this window if A matches the
+ * match with given mask.
+ * So every PCIe window size must be a power of two and every start
+ * address must be aligned to window size. Minimal size is 64 KiB
+ * because lower 16 bits of mask must be zero. Remapped address
+ * may have set only bits from the mask.
+ */
+ while (pcie->wins_count < OB_WIN_COUNT && size > 0) {
+ /* Calculate the largest aligned window size */
+ win_size = (1ULL << (fls64(size)-1)) |
+ (start ? (1ULL << __ffs64(start)) : 0);
+ win_size = 1ULL << __ffs64(win_size);
+ if (win_size < 0x10000)
+ break;
+
+ dev_dbg(dev,
+ "Configuring PCIe window %d: [0x%llx-0x%llx] as %lu\n",
+ pcie->wins_count, (unsigned long long)start,
+ (unsigned long long)start + win_size, type);
+
+ if (type == IORESOURCE_IO) {
+ pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_IO;
+ pcie->wins[pcie->wins_count].match = pci_pio_to_address(start);
+ } else {
+ pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_MEM;
+ pcie->wins[pcie->wins_count].match = start;
+ }
+ pcie->wins[pcie->wins_count].remap = start - entry->offset;
+ pcie->wins[pcie->wins_count].mask = ~(win_size - 1);
+
+ if (pcie->wins[pcie->wins_count].remap & (win_size - 1))
+ break;
+
+ start += win_size;
+ size -= win_size;
+ pcie->wins_count++;
+ }
+
+ if (size > 0) {
+ dev_err(&pcie->pdev->dev,
+ "Invalid PCIe region [0x%llx-0x%llx]\n",
+ (unsigned long long)entry->res->start,
+ (unsigned long long)entry->res->end + 1);
+ return -EINVAL;
+ }
+ }
+
+ pcie->reset_gpio = devm_fwnode_get_index_gpiod_from_child(dev, "reset",
+ 0,
+ dev_fwnode(dev),
+ GPIOD_OUT_LOW,
+ "pcie1-reset");
+ ret = PTR_ERR_OR_ZERO(pcie->reset_gpio);
+ if (ret) {
+ if (ret == -ENOENT) {
+ pcie->reset_gpio = NULL;
+ } else {
+ if (ret != -EPROBE_DEFER)
+ dev_err(dev, "Failed to get reset-gpio: %i\n",
+ ret);
+ return ret;
+ }
+ }
+
+ ret = of_pci_get_max_link_speed(dev->of_node);
+ if (ret <= 0 || ret > 3)
+ pcie->link_gen = 3;
+ else
+ pcie->link_gen = ret;
+
advk_pcie_setup_hw(pcie);

ret = advk_pcie_init_irq_domain(pcie);
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
index 262f591ad8a6..9f7d917458c7 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -153,12 +153,16 @@ static struct armada_37xx_pin_group armada_37xx_nb_groups[] = {
PIN_GRP_GPIO("jtag", 20, 5, BIT(0), "jtag"),
PIN_GRP_GPIO("sdio0", 8, 3, BIT(1), "sdio"),
PIN_GRP_GPIO("emmc_nb", 27, 9, BIT(2), "emmc"),
- PIN_GRP_GPIO("pwm0", 11, 1, BIT(3), "pwm"),
- PIN_GRP_GPIO("pwm1", 12, 1, BIT(4), "pwm"),
- PIN_GRP_GPIO("pwm2", 13, 1, BIT(5), "pwm"),
- PIN_GRP_GPIO("pwm3", 14, 1, BIT(6), "pwm"),
- PIN_GRP_GPIO("pmic1", 17, 1, BIT(7), "pmic"),
- PIN_GRP_GPIO("pmic0", 16, 1, BIT(8), "pmic"),
+ PIN_GRP_GPIO_3("pwm0", 11, 1, BIT(3) | BIT(20), 0, BIT(20), BIT(3),
+ "pwm", "led"),
+ PIN_GRP_GPIO_3("pwm1", 12, 1, BIT(4) | BIT(21), 0, BIT(21), BIT(4),
+ "pwm", "led"),
+ PIN_GRP_GPIO_3("pwm2", 13, 1, BIT(5) | BIT(22), 0, BIT(22), BIT(5),
+ "pwm", "led"),
+ PIN_GRP_GPIO_3("pwm3", 14, 1, BIT(6) | BIT(23), 0, BIT(23), BIT(6),
+ "pwm", "led"),
+ PIN_GRP_GPIO("pmic1", 7, 1, BIT(7), "pmic"),
+ PIN_GRP_GPIO("pmic0", 6, 1, BIT(8), "pmic"),
PIN_GRP_GPIO("i2c2", 2, 2, BIT(9), "i2c"),
PIN_GRP_GPIO("i2c1", 0, 2, BIT(10), "i2c"),
PIN_GRP_GPIO("spi_cs1", 17, 1, BIT(12), "spi"),
@@ -170,11 +174,6 @@ static struct armada_37xx_pin_group armada_37xx_nb_groups[] = {
PIN_GRP_EXTRA("uart2", 9, 2, BIT(1) | BIT(13) | BIT(14) | BIT(19),
BIT(1) | BIT(13) | BIT(14), BIT(1) | BIT(19),
18, 2, "gpio", "uart"),
- PIN_GRP_GPIO_2("led0_od", 11, 1, BIT(20), BIT(20), 0, "led"),
- PIN_GRP_GPIO_2("led1_od", 12, 1, BIT(21), BIT(21), 0, "led"),
- PIN_GRP_GPIO_2("led2_od", 13, 1, BIT(22), BIT(22), 0, "led"),
- PIN_GRP_GPIO_2("led3_od", 14, 1, BIT(23), BIT(23), 0, "led"),
-
};

static struct armada_37xx_pin_group armada_37xx_sb_groups[] = {
@@ -182,8 +181,11 @@ static struct armada_37xx_pin_group armada_37xx_sb_groups[] = {
PIN_GRP_GPIO("usb2_drvvbus1", 1, 1, BIT(1), "drvbus"),
PIN_GRP_GPIO("sdio_sb", 24, 6, BIT(2), "sdio"),
PIN_GRP_GPIO("rgmii", 6, 12, BIT(3), "mii"),
- PIN_GRP_GPIO("pcie1", 3, 2, BIT(4), "pcie"),
- PIN_GRP_GPIO("ptp", 20, 3, BIT(5), "ptp"),
+ PIN_GRP_GPIO("smi", 18, 2, BIT(4), "smi"),
+ PIN_GRP_GPIO("pcie1", 3, 1, BIT(5), "pcie"),
+ PIN_GRP_GPIO("pcie1_clkreq", 4, 1, BIT(9), "pcie"),
+ PIN_GRP_GPIO("pcie1_wakeup", 5, 1, BIT(10), "pcie"),
+ PIN_GRP_GPIO("ptp", 20, 3, BIT(11) | BIT(12) | BIT(13), "ptp"),
PIN_GRP("ptp_clk", 21, 1, BIT(6), "ptp", "mii"),
PIN_GRP("ptp_trig", 22, 1, BIT(7), "ptp", "mii"),
PIN_GRP_GPIO_3("mii_col", 23, 1, BIT(8) | BIT(14), 0, BIT(8), BIT(14),
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 9d836d779d47..05b3e0f724fc 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -1180,15 +1180,6 @@ static int tpacpi_rfk_update_swstate(const struct tpacpi_rfk *tp_rfk)
return status;
}

-/* Query FW and update rfkill sw state for all rfkill switches */
-static void tpacpi_rfk_update_swstate_all(void)
-{
- unsigned int i;
-
- for (i = 0; i < TPACPI_RFK_SW_MAX; i++)
- tpacpi_rfk_update_swstate(tpacpi_rfkill_switches[i]);
-}
-
/*
* Sync the HW-blocking state of all rfkill switches,
* do notice it causes the rfkill core to schedule uevents
@@ -3025,9 +3016,6 @@ static void tpacpi_send_radiosw_update(void)
if (wlsw == TPACPI_RFK_RADIO_OFF)
tpacpi_rfk_update_hwblock_state(true);

- /* Sync sw blocking state */
- tpacpi_rfk_update_swstate_all();
-
/* Sync hw blocking state last if it is hw-unblocked */
if (wlsw == TPACPI_RFK_RADIO_ON)
tpacpi_rfk_update_hwblock_state(false);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 332ea3af69ec..79c5a193308f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2955,7 +2955,7 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)

shost_for_each_device(sdev, ioc->shost) {
sas_device_priv_data = sdev->hostdata;
- if (!sas_device_priv_data)
+ if (!sas_device_priv_data || !sas_device_priv_data->sas_target)
continue;
if (sas_device_priv_data->sas_target->sas_address
!= sas_address)
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index d276d84c0f7a..26c6f1b28801 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1892,12 +1892,12 @@ static void session_recovery_timedout(struct work_struct *work)
}
spin_unlock_irqrestore(&session->lock, flags);

- if (session->transport->session_recovery_timedout)
- session->transport->session_recovery_timedout(session);
-
ISCSI_DBG_TRANS_SESSION(session, "Unblocking SCSI target\n");
scsi_target_unblock(&session->dev, SDEV_TRANSPORT_OFFLINE);
ISCSI_DBG_TRANS_SESSION(session, "Completed unblocking SCSI target\n");
+
+ if (session->transport->session_recovery_timedout)
+ session->transport->session_recovery_timedout(session);
}

static void __iscsi_unblock_session(struct work_struct *work)
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index 811cada301ac..e1ede9fd4920 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -2582,13 +2582,14 @@ static void _rtl92e_pci_disconnect(struct pci_dev *pdev)
free_irq(dev->irq, dev);
priv->irq = 0;
}
- free_rtllib(dev);

if (dev->mem_start != 0) {
iounmap((void __iomem *)dev->mem_start);
release_mem_region(pci_resource_start(pdev, 1),
pci_resource_len(pdev, 1));
}
+
+ free_rtllib(dev);
} else {
priv = rtllib_priv(dev);
}
diff --git a/drivers/staging/typec/tcpm.c b/drivers/staging/typec/tcpm.c
index 686037a498c1..4fff829b00aa 100644
--- a/drivers/staging/typec/tcpm.c
+++ b/drivers/staging/typec/tcpm.c
@@ -2386,11 +2386,7 @@ static void run_state_machine(struct tcpm_port *port)
tcpm_try_src(port) ? SRC_TRY
: SNK_ATTACHED,
0);
- else
- /* Wait for VBUS, but not forever */
- tcpm_set_state(port, PORT_RESET, PD_T_PS_SOURCE_ON);
break;
-
case SRC_TRY:
port->try_src_count++;
tcpm_set_cc(port, tcpm_rp_cc(port));
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 94820f25a15f..8374b8078b7d 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -457,6 +457,8 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
{
struct thermal_instance *pos;
tz->temperature = THERMAL_TEMP_INVALID;
+ tz->prev_low_trip = -INT_MAX;
+ tz->prev_high_trip = INT_MAX;
list_for_each_entry(pos, &tz->thermal_instances, tz_node)
pos->initialized = false;
}
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 5e87e4866bcb..858c7b4b197c 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -99,7 +99,11 @@ static int __write_console(struct xencons_info *xencons,
cons = intf->out_cons;
prod = intf->out_prod;
mb(); /* update queue values before going on */
- BUG_ON((prod - cons) > sizeof(intf->out));
+
+ if ((prod - cons) > sizeof(intf->out)) {
+ pr_err_once("xencons: Illegal ring page indices");
+ return -EINVAL;
+ }

while ((sent < len) && ((prod - cons) < sizeof(intf->out)))
intf->out[MASK_XENCONS_IDX(prod++, intf->out)] = data[sent++];
@@ -127,7 +131,10 @@ static int domU_write_console(uint32_t vtermno, const char *data, int len)
*/
while (len) {
int sent = __write_console(cons, data, len);
-
+
+ if (sent < 0)
+ return sent;
+
data += sent;
len -= sent;

@@ -151,7 +158,11 @@ static int domU_read_console(uint32_t vtermno, char *buf, int len)
cons = intf->in_cons;
prod = intf->in_prod;
mb(); /* get pointers before reading ring */
- BUG_ON((prod - cons) > sizeof(intf->in));
+
+ if ((prod - cons) > sizeof(intf->in)) {
+ pr_err_once("xencons: Illegal ring page indices");
+ return -EINVAL;
+ }

while (cons != prod && recv < len)
buf[recv++] = intf->in[MASK_XENCONS_IDX(cons++, intf->in)];
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 49bdd0f8d06a..dcf84d5020c6 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2790,6 +2790,7 @@ MODULE_DEVICE_TABLE(of, sbsa_uart_of_match);

static const struct acpi_device_id sbsa_uart_acpi_match[] = {
{ "ARMH0011", 0 },
+ { "ARMHB000", 0 },
{},
};
MODULE_DEVICE_TABLE(acpi, sbsa_uart_acpi_match);
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 77a1f00fe843..7848e9455950 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -611,6 +611,9 @@ static void msm_start_rx_dma(struct msm_port *msm_port)
u32 val;
int ret;

+ if (IS_ENABLED(CONFIG_CONSOLE_POLL))
+ return;
+
if (!dma->chan)
return;

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 599d8a4f124a..16ce187390d8 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1541,6 +1541,7 @@ static void uart_tty_port_shutdown(struct tty_port *port)
{
struct uart_state *state = container_of(port, struct uart_state, port);
struct uart_port *uport = uart_port_check(state);
+ char *buf;

/*
* At this point, we stop accepting input. To do this, we
@@ -1562,8 +1563,18 @@ static void uart_tty_port_shutdown(struct tty_port *port)
*/
tty_port_set_suspended(port, 0);

- uart_change_pm(state, UART_PM_STATE_OFF);
+ /*
+ * Free the transmit buffer.
+ */
+ spin_lock_irq(&uport->lock);
+ buf = state->xmit.buf;
+ state->xmit.buf = NULL;
+ spin_unlock_irq(&uport->lock);

+ if (buf)
+ free_page((unsigned long)buf);
+
+ uart_change_pm(state, UART_PM_STATE_OFF);
}

static void uart_wait_until_sent(struct tty_struct *tty, int timeout)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 6c555a50646a..56a0bd05aa2c 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4472,8 +4472,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
if (oldspeed == USB_SPEED_LOW)
delay = HUB_LONG_RESET_TIME;

- mutex_lock(hcd->address0_mutex);
-
/* Reset the device; full speed may morph to high speed */
/* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */
retval = hub_port_reset(hub, port1, udev, delay, false);
@@ -4772,7 +4770,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
hub_port_disable(hub, port1, 0);
update_devnum(udev, devnum); /* for disconnect processing */
}
- mutex_unlock(hcd->address0_mutex);
return retval;
}

@@ -4862,6 +4859,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
struct usb_port *port_dev = hub->ports[port1 - 1];
struct usb_device *udev = port_dev->child;
static int unreliable_port = -1;
+ bool retry_locked;

/* Disconnect any existing devices under this port */
if (udev) {
@@ -4917,7 +4915,11 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
unit_load = 100;

status = 0;
+
for (i = 0; i < SET_CONFIG_TRIES; i++) {
+ usb_lock_port(port_dev);
+ mutex_lock(hcd->address0_mutex);
+ retry_locked = true;

/* reallocate for each attempt, since references
* to the previous one can escape in various ways
@@ -4926,6 +4928,8 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
if (!udev) {
dev_err(&port_dev->dev,
"couldn't allocate usb_device\n");
+ mutex_unlock(hcd->address0_mutex);
+ usb_unlock_port(port_dev);
goto done;
}

@@ -4947,12 +4951,14 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
}

/* reset (non-USB 3.0 devices) and get descriptor */
- usb_lock_port(port_dev);
status = hub_port_init(hub, udev, port1, i);
- usb_unlock_port(port_dev);
if (status < 0)
goto loop;

+ mutex_unlock(hcd->address0_mutex);
+ usb_unlock_port(port_dev);
+ retry_locked = false;
+
if (udev->quirks & USB_QUIRK_DELAY_INIT)
msleep(2000);

@@ -5045,6 +5051,10 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
usb_ep0_reinit(udev);
release_devnum(udev);
hub_free_dev(udev);
+ if (retry_locked) {
+ mutex_unlock(hcd->address0_mutex);
+ usb_unlock_port(port_dev);
+ }
usb_put_dev(udev);
if ((status == -ENOTCONN) || (status == -ENOTSUPP))
break;
@@ -5608,6 +5618,8 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
bos = udev->bos;
udev->bos = NULL;

+ mutex_lock(hcd->address0_mutex);
+
for (i = 0; i < SET_CONFIG_TRIES; ++i) {

/* ep0 maxpacket size may change; let the HCD know about it.
@@ -5617,6 +5629,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
if (ret >= 0 || ret == -ENOTCONN || ret == -ENODEV)
break;
}
+ mutex_unlock(hcd->address0_mutex);

if (ret < 0)
goto re_enumerate;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index d0c12de1c6d0..681d5bb99d99 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -350,7 +350,9 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
/* Must be called with xhci->lock held, releases and aquires lock back */
static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
{
- u32 temp_32;
+ struct xhci_segment *new_seg = xhci->cmd_ring->deq_seg;
+ union xhci_trb *new_deq = xhci->cmd_ring->dequeue;
+ u64 crcr;
int ret;

xhci_dbg(xhci, "Abort command ring\n");
@@ -359,13 +361,18 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)

/*
* The control bits like command stop, abort are located in lower
- * dword of the command ring control register. Limit the write
- * to the lower dword to avoid corrupting the command ring pointer
- * in case if the command ring is stopped by the time upper dword
- * is written.
+ * dword of the command ring control register.
+ * Some controllers require all 64 bits to be written to abort the ring.
+ * Make sure the upper dword is valid, pointing to the next command,
+ * avoiding corrupting the command ring pointer in case the command ring
+ * is stopped by the time the upper dword is written.
*/
- temp_32 = readl(&xhci->op_regs->cmd_ring);
- writel(temp_32 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
+ next_trb(xhci, NULL, &new_seg, &new_deq);
+ if (trb_is_link(new_deq))
+ next_trb(xhci, NULL, &new_seg, &new_deq);
+
+ crcr = xhci_trb_virt_to_dma(new_seg, new_deq);
+ xhci_write_64(xhci, crcr | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);

/* Section 4.6.1.2 of xHCI 1.0 spec says software should also time the
* completion of the Command Abort operation. If CRR is not negated in 5
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index f50de529445d..4e2a9852147b 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1270,6 +1270,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = NCTRL(2) },
{ USB_DEVICE(TELIT_VENDOR_ID, 0x9010), /* Telit SBL FN980 flashing device */
.driver_info = NCTRL(0) | ZLP },
+ { USB_DEVICE(TELIT_VENDOR_ID, 0x9200), /* Telit LE910S1 flashing device */
+ .driver_info = NCTRL(0) | ZLP },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) },
@@ -2096,6 +2098,9 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */
{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */
{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
+ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */
+ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */
+ .driver_info = RSVD(4) },
{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */
{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */
{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 27f3b471c95b..b43b4942f156 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -490,7 +490,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
virtio_transport_free_pkt(pkt);

len += sizeof(pkt->hdr);
- vhost_add_used(vq, head, len);
+ vhost_add_used(vq, head, 0);
total_len += len;
added = true;
} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index 0dff64299099..e3b5476ddf01 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -365,11 +365,17 @@ static void vgacon_init(struct vc_data *c, int init)
struct uni_pagedir *p;

/*
- * We cannot be loaded as a module, therefore init is always 1,
- * but vgacon_init can be called more than once, and init will
- * not be 1.
+ * We cannot be loaded as a module, therefore init will be 1
+ * if we are the default console, however if we are a fallback
+ * console, for example if fbcon has failed registration, then
+ * init will be 0, so we need to make sure our boot parameters
+ * have been copied to the console structure for vgacon_resize
+ * ultimately called by vc_resize. Any subsequent calls to
+ * vgacon_init init will have init set to 0 too.
*/
c->vc_can_do_color = vga_can_do_color;
+ c->vc_scan_lines = vga_scan_lines;
+ c->vc_font.height = c->vc_cell_height = vga_video_font_height;

/* set dimensions manually if init != 0 since vc_resize() will fail */
if (init) {
@@ -378,8 +384,6 @@ static void vgacon_init(struct vc_data *c, int init)
} else
vc_resize(c, vga_video_num_columns, vga_video_num_lines);

- c->vc_scan_lines = vga_scan_lines;
- c->vc_font.height = c->vc_cell_height = vga_video_font_height;
c->vc_complement_mask = 0x7700;
if (vga_512_chars)
c->vc_hi_font_mask = 0x0800;
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 08f1ccdbe343..27c48c90b2ab 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -838,7 +838,7 @@ static struct notifier_block xenbus_resume_nb = {

static int __init xenbus_init(void)
{
- int err = 0;
+ int err;
uint64_t v = 0;
xen_store_domain_type = XS_UNKNOWN;

@@ -878,6 +878,29 @@ static int __init xenbus_init(void)
err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
if (err)
goto out_error;
+ /*
+ * Uninitialized hvm_params are zero and return no error.
+ * Although it is theoretically possible to have
+ * HVM_PARAM_STORE_PFN set to zero on purpose, in reality it is
+ * not zero when valid. If zero, it means that Xenstore hasn't
+ * been properly initialized. Instead of attempting to map a
+ * wrong guest physical address return error.
+ *
+ * Also recognize all bits set as an invalid value.
+ */
+ if (!v || !~v) {
+ err = -ENOENT;
+ goto out_error;
+ }
+ /* Avoid truncation on 32-bit. */
+#if BITS_PER_LONG == 32
+ if (v > ULONG_MAX) {
+ pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n",
+ __func__, v);
+ err = -EINVAL;
+ goto out_error;
+ }
+#endif
xen_store_gfn = (unsigned long)v;
xen_store_interface =
xen_remap(xen_store_gfn << XEN_PAGE_SHIFT,
@@ -912,8 +935,10 @@ static int __init xenbus_init(void)
*/
proc_create_mount_point("xen");
#endif
+ return 0;

out_error:
+ xen_store_domain_type = XS_UNKNOWN;
return err;
}

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index ace58d6a270b..41ebc613ca4c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3339,11 +3339,23 @@ static void btrfs_end_empty_barrier(struct bio *bio)
*/
static void write_dev_flush(struct btrfs_device *device)
{
- struct request_queue *q = bdev_get_queue(device->bdev);
struct bio *bio = device->flush_bio;

+#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+ /*
+ * When a disk has write caching disabled, we skip submission of a bio
+ * with flush and sync requests before writing the superblock, since
+ * it's not needed. However when the integrity checker is enabled, this
+ * results in reports that there are metadata blocks referred by a
+ * superblock that were not properly flushed. So don't skip the bio
+ * submission only when the integrity checker is enabled for the sake
+ * of simplicity, since this is a debug tool and not meant for use in
+ * non-debug builds.
+ */
+ struct request_queue *q = bdev_get_queue(device->bdev);
if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
return;
+#endif

bio_reset(bio);
bio->bi_end_io = btrfs_end_empty_barrier;
diff --git a/fs/file.c b/fs/file.c
index 97c6f0df39da..f1943da6303b 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -679,7 +679,7 @@ void do_close_on_exec(struct files_struct *files)
spin_unlock(&files->file_lock);
}

-static struct file *__fget(unsigned int fd, fmode_t mask)
+static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs)
{
struct files_struct *files = current->files;
struct file *file;
@@ -694,23 +694,32 @@ static struct file *__fget(unsigned int fd, fmode_t mask)
*/
if (file->f_mode & mask)
file = NULL;
- else if (!get_file_rcu(file))
+ else if (!get_file_rcu_many(file, refs))
goto loop;
+ else if (__fcheck_files(files, fd) != file) {
+ fput_many(file, refs);
+ goto loop;
+ }
}
rcu_read_unlock();

return file;
}

+struct file *fget_many(unsigned int fd, unsigned int refs)
+{
+ return __fget(fd, FMODE_PATH, refs);
+}
+
struct file *fget(unsigned int fd)
{
- return __fget(fd, FMODE_PATH);
+ return __fget(fd, FMODE_PATH, 1);
}
EXPORT_SYMBOL(fget);

struct file *fget_raw(unsigned int fd)
{
- return __fget(fd, 0);
+ return __fget(fd, 0, 1);
}
EXPORT_SYMBOL(fget_raw);

@@ -741,7 +750,7 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
return 0;
return (unsigned long)file;
} else {
- file = __fget(fd, mask);
+ file = __fget(fd, mask, 1);
if (!file)
return 0;
return FDPUT_FPUT | (unsigned long)file;
diff --git a/fs/file_table.c b/fs/file_table.c
index 61517f57f8ef..4ceb4982ffea 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -261,9 +261,9 @@ void flush_delayed_fput(void)

static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);

-void fput(struct file *file)
+void fput_many(struct file *file, unsigned int refs)
{
- if (atomic_long_dec_and_test(&file->f_count)) {
+ if (atomic_long_sub_and_test(refs, &file->f_count)) {
struct task_struct *task = current;

if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
@@ -282,6 +282,11 @@ void fput(struct file *file)
}
}

+void fput(struct file *file)
+{
+ fput_many(file, 1);
+}
+
/*
* synchronous analog of fput(); for kernel threads that might be needed
* in some umount() (and thus can't use flush_delayed_fput() without
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index b6f2a10663a0..db7d746633cf 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -902,6 +902,12 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
if (!(buf->flags & PIPE_BUF_FLAG_LRU))
lru_cache_add_file(newpage);

+ /*
+ * Release while we have extra ref on stolen page. Otherwise
+ * anon_pipe_buf_release() might think the page can be reused.
+ */
+ pipe_buf_release(cs->pipe, buf);
+
err = 0;
spin_lock(&cs->req->waitq.lock);
if (test_bit(FR_ABORTED, &cs->req->flags))
@@ -2046,8 +2052,12 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,

pipe_lock(pipe);
out_free:
- for (idx = 0; idx < nbuf; idx++)
- pipe_buf_release(pipe, &bufs[idx]);
+ for (idx = 0; idx < nbuf; idx++) {
+ struct pipe_buffer *buf = &bufs[idx];
+
+ if (buf->ops)
+ pipe_buf_release(pipe, buf);
+ }
pipe_unlock(pipe);

kfree(bufs);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index a61792f777be..394503c79faf 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -186,8 +186,9 @@ static ssize_t _nfs42_proc_copy(struct file *src,
goto out;
}

- truncate_pagecache_range(dst_inode, pos_dst,
- pos_dst + res->write_res.count);
+ WARN_ON_ONCE(invalidate_inode_pages2_range(dst_inode->i_mapping,
+ pos_dst >> PAGE_SHIFT,
+ (pos_dst + res->write_res.count - 1) >> PAGE_SHIFT));

status = res->write_res.count;
out:
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 5966e1e7b1f5..09c683402f95 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -625,8 +625,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp,
status = decode_clone(xdr);
if (status)
goto out;
- status = decode_getfattr(xdr, res->dst_fattr, res->server);
-
+ decode_getfattr(xdr, res->dst_fattr, res->server);
out:
res->rpc_status = status;
return status;
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index aaa7486b6f0d..0bfd71bec7f2 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -105,14 +105,19 @@ static ssize_t read_from_oldmem(char *buf, size_t count,
nr_bytes = count;

/* If pfn is not ram, return zeros for sparse dump files */
- if (pfn_is_ram(pfn) == 0)
- memset(buf, 0, nr_bytes);
- else {
+ if (pfn_is_ram(pfn) == 0) {
+ tmp = 0;
+ if (!userbuf)
+ memset(buf, 0, nr_bytes);
+ else if (clear_user(buf, nr_bytes))
+ tmp = -EFAULT;
+ } else {
tmp = copy_oldmem_page(pfn, buf, nr_bytes,
offset, userbuf);
- if (tmp < 0)
- return tmp;
}
+ if (tmp < 0)
+ return tmp;
+
*ppos += nr_bytes;
count -= nr_bytes;
buf += nr_bytes;
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index faddde44de8c..5e7e4aaf36c5 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -117,6 +117,8 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb,
void tlb_flush_mmu(struct mmu_gather *tlb);
void arch_tlb_finish_mmu(struct mmu_gather *tlb,
unsigned long start, unsigned long end, bool force);
+void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+ unsigned long size);
extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
int page_size);

diff --git a/include/linux/file.h b/include/linux/file.h
index 279720db984a..d26462b127a3 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -13,6 +13,7 @@
struct file;

extern void fput(struct file *);
+extern void fput_many(struct file *, unsigned int);

struct file_operations;
struct vfsmount;
@@ -41,6 +42,7 @@ static inline void fdput(struct fd fd)
}

extern struct file *fget(unsigned int fd);
+extern struct file *fget_many(unsigned int fd, unsigned int refs);
extern struct file *fget_raw(unsigned int fd);
extern unsigned long __fdget(unsigned int fd);
extern unsigned long __fdget_raw(unsigned int fd);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 309c151decd8..1084f1335c9f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -908,7 +908,9 @@ static inline struct file *get_file(struct file *f)
atomic_long_inc(&f->f_count);
return f;
}
-#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
+#define get_file_rcu_many(x, cnt) \
+ atomic_long_add_unless(&(x)->f_count, (cnt), 0)
+#define get_file_rcu(x) get_file_rcu_many((x), 1)
#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
#define file_count(x) atomic_long_read(&(x)->f_count)

diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 474812abe773..e661765271ea 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -127,6 +127,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
return ns;
}

+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+ if (ns) {
+ if (refcount_inc_not_zero(&ns->count))
+ return ns;
+ }
+
+ return NULL;
+}
+
extern void put_ipc_ns(struct ipc_namespace *ns);
#else
static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
@@ -143,6 +153,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
return ns;
}

+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+ return ns;
+}
+
static inline void put_ipc_ns(struct ipc_namespace *ns)
{
}
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index be7a49f437ea..019444c04f58 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -193,6 +193,8 @@ struct kretprobe {
raw_spinlock_t lock;
};

+#define KRETPROBE_MAX_DATA_SIZE 4096
+
struct kretprobe_instance {
struct hlist_node hlist;
struct kretprobe *rp;
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 11b4fba82950..c3d157a37073 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -122,7 +122,7 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
* Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
* subscriptions and synchronises with wait4(). Also used in procfs. Also
* pins the final release of task.io_context. Also protects ->cpuset and
- * ->cgroup.subsys[]. And ->vfork_done.
+ * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
diff --git a/include/linux/shm.h b/include/linux/shm.h
index 2bbafacfbfc9..3ef303df784e 100644
--- a/include/linux/shm.h
+++ b/include/linux/shm.h
@@ -20,9 +20,18 @@ struct shmid_kernel /* private to the kernel */
pid_t shm_lprid;
struct user_struct *mlock_user;

- /* The task created the shm object. NULL if the task is dead. */
+ /*
+ * The task created the shm object, for
+ * task_lock(shp->shm_creator)
+ */
struct task_struct *shm_creator;
- struct list_head shm_clist; /* list by creator */
+
+ /*
+ * List by creator. task_lock(->shm_creator) required for read/write.
+ * If list_empty(), then the creator is dead already.
+ */
+ struct list_head shm_clist;
+ struct ipc_namespace *ns;
} __randomize_layout;

/* shm_mode upper byte flags */
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index bf21591a9e5e..0cda61855d90 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(const siphash_key_t *key)
}

u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key);
-#endif

u64 siphash_1u64(const u64 a, const siphash_key_t *key);
u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key);
@@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(const __le64 *data, size_t len,
static inline u64 siphash(const void *data, size_t len,
const siphash_key_t *key)
{
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
- if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
+ if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+ !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
return __siphash_unaligned(data, len, key);
-#endif
return ___siphash_aligned(data, len, key);
}

@@ -96,10 +93,8 @@ typedef struct {

u32 __hsiphash_aligned(const void *data, size_t len,
const hsiphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key);
-#endif

u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key);
u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key);
@@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len,
static inline u32 hsiphash(const void *data, size_t len,
const hsiphash_key_t *key)
{
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
- if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
+ if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+ !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
return __hsiphash_unaligned(data, len, key);
-#endif
return ___hsiphash_aligned(data, len, key);
}

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index e67564af6f93..1560ce548add 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -42,6 +42,7 @@ enum nci_flag {
NCI_UP,
NCI_DATA_EXCHANGE,
NCI_DATA_EXCHANGE_TO,
+ NCI_UNREG,
};

/* NCI device states */
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index ddcee128f5d9..145acb8f2509 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -19,6 +19,8 @@
*
*/

+#include <linux/types.h>
+
#define NL802154_GENL_NAME "nl802154"

enum nl802154_commands {
@@ -150,10 +152,9 @@ enum nl802154_attrs {
};

enum nl802154_iftype {
- /* for backwards compatibility TODO */
- NL802154_IFTYPE_UNSPEC = -1,
+ NL802154_IFTYPE_UNSPEC = (~(__u32)0),

- NL802154_IFTYPE_NODE,
+ NL802154_IFTYPE_NODE = 0,
NL802154_IFTYPE_MONITOR,
NL802154_IFTYPE_COORD,

diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index c843929e0c4f..5db024aa00e9 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -654,6 +654,11 @@
#define PCI_EXP_LNKCAP2_SLS_8_0GB 0x00000008 /* Supported Speed 8.0GT/s */
#define PCI_EXP_LNKCAP2_CROSSLINK 0x00000100 /* Crosslink supported */
#define PCI_EXP_LNKCTL2 48 /* Link Control 2 */
+#define PCI_EXP_LNKCTL2_TLS 0x000f
+#define PCI_EXP_LNKCTL2_TLS_2_5GT 0x0001 /* Supported Speed 2.5GT/s */
+#define PCI_EXP_LNKCTL2_TLS_5_0GT 0x0002 /* Supported Speed 5GT/s */
+#define PCI_EXP_LNKCTL2_TLS_8_0GT 0x0003 /* Supported Speed 8GT/s */
+#define PCI_EXP_LNKCTL2_TLS_16_0GT 0x0004 /* Supported Speed 16GT/s */
#define PCI_EXP_LNKSTA2 50 /* Link Status 2 */
#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52 /* v2 endpoints with link end here */
#define PCI_EXP_SLTCAP2 52 /* Slot Capabilities 2 */
diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h
index 3f40501fc60b..b39cdbc522ec 100644
--- a/include/xen/interface/io/ring.h
+++ b/include/xen/interface/io/ring.h
@@ -1,21 +1,53 @@
-/* SPDX-License-Identifier: GPL-2.0 */
/******************************************************************************
* ring.h
*
* Shared producer-consumer ring macros.
*
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
* Tim Deegan and Andrew Warfield November 2004.
*/

#ifndef __XEN_PUBLIC_IO_RING_H__
#define __XEN_PUBLIC_IO_RING_H__

+/*
+ * When #include'ing this header, you need to provide the following
+ * declaration upfront:
+ * - standard integers types (uint8_t, uint16_t, etc)
+ * They are provided by stdint.h of the standard headers.
+ *
+ * In addition, if you intend to use the FLEX macros, you also need to
+ * provide the following, before invoking the FLEX macros:
+ * - size_t
+ * - memcpy
+ * - grant_ref_t
+ * These declarations are provided by string.h of the standard headers,
+ * and grant_table.h from the Xen public headers.
+ */
+
#include <xen/interface/grant_table.h>

typedef unsigned int RING_IDX;

/* Round a 32-bit unsigned constant down to the nearest power of two. */
-#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1))
+#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1))
#define __RD4(_x) (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2 : __RD2(_x))
#define __RD8(_x) (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4 : __RD4(_x))
#define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8 : __RD8(_x))
@@ -27,82 +59,79 @@ typedef unsigned int RING_IDX;
* A ring contains as many entries as will fit, rounded down to the nearest
* power of two (so we can mask with (size-1) to loop around).
*/
-#define __CONST_RING_SIZE(_s, _sz) \
- (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \
- sizeof(((struct _s##_sring *)0)->ring[0])))
-
+#define __CONST_RING_SIZE(_s, _sz) \
+ (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \
+ sizeof(((struct _s##_sring *)0)->ring[0])))
/*
* The same for passing in an actual pointer instead of a name tag.
*/
-#define __RING_SIZE(_s, _sz) \
- (__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0])))
+#define __RING_SIZE(_s, _sz) \
+ (__RD32(((_sz) - (long)(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0])))

/*
* Macros to make the correct C datatypes for a new kind of ring.
*
* To make a new ring datatype, you need to have two message structures,
- * let's say struct request, and struct response already defined.
+ * let's say request_t, and response_t already defined.
*
* In a header where you want the ring datatype declared, you then do:
*
- * DEFINE_RING_TYPES(mytag, struct request, struct response);
+ * DEFINE_RING_TYPES(mytag, request_t, response_t);
*
* These expand out to give you a set of types, as you can see below.
* The most important of these are:
*
- * struct mytag_sring - The shared ring.
- * struct mytag_front_ring - The 'front' half of the ring.
- * struct mytag_back_ring - The 'back' half of the ring.
+ * mytag_sring_t - The shared ring.
+ * mytag_front_ring_t - The 'front' half of the ring.
+ * mytag_back_ring_t - The 'back' half of the ring.
*
* To initialize a ring in your code you need to know the location and size
* of the shared memory area (PAGE_SIZE, for instance). To initialise
* the front half:
*
- * struct mytag_front_ring front_ring;
- * SHARED_RING_INIT((struct mytag_sring *)shared_page);
- * FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page,
- * PAGE_SIZE);
+ * mytag_front_ring_t front_ring;
+ * SHARED_RING_INIT((mytag_sring_t *)shared_page);
+ * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE);
*
* Initializing the back follows similarly (note that only the front
* initializes the shared ring):
*
- * struct mytag_back_ring back_ring;
- * BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page,
- * PAGE_SIZE);
+ * mytag_back_ring_t back_ring;
+ * BACK_RING_INIT(&back_ring, (mytag_sring_t *)shared_page, PAGE_SIZE);
*/

-#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \
- \
-/* Shared ring entry */ \
-union __name##_sring_entry { \
- __req_t req; \
- __rsp_t rsp; \
-}; \
- \
-/* Shared ring page */ \
-struct __name##_sring { \
- RING_IDX req_prod, req_event; \
- RING_IDX rsp_prod, rsp_event; \
- uint8_t pad[48]; \
- union __name##_sring_entry ring[1]; /* variable-length */ \
-}; \
- \
-/* "Front" end's private variables */ \
-struct __name##_front_ring { \
- RING_IDX req_prod_pvt; \
- RING_IDX rsp_cons; \
- unsigned int nr_ents; \
- struct __name##_sring *sring; \
-}; \
- \
-/* "Back" end's private variables */ \
-struct __name##_back_ring { \
- RING_IDX rsp_prod_pvt; \
- RING_IDX req_cons; \
- unsigned int nr_ents; \
- struct __name##_sring *sring; \
-};
-
+#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \
+ \
+/* Shared ring entry */ \
+union __name##_sring_entry { \
+ __req_t req; \
+ __rsp_t rsp; \
+}; \
+ \
+/* Shared ring page */ \
+struct __name##_sring { \
+ RING_IDX req_prod, req_event; \
+ RING_IDX rsp_prod, rsp_event; \
+ uint8_t __pad[48]; \
+ union __name##_sring_entry ring[1]; /* variable-length */ \
+}; \
+ \
+/* "Front" end's private variables */ \
+struct __name##_front_ring { \
+ RING_IDX req_prod_pvt; \
+ RING_IDX rsp_cons; \
+ unsigned int nr_ents; \
+ struct __name##_sring *sring; \
+}; \
+ \
+/* "Back" end's private variables */ \
+struct __name##_back_ring { \
+ RING_IDX rsp_prod_pvt; \
+ RING_IDX req_cons; \
+ unsigned int nr_ents; \
+ struct __name##_sring *sring; \
+}; \
+ \
/*
* Macros for manipulating rings.
*
@@ -119,105 +148,99 @@ struct __name##_back_ring { \
*/

/* Initialising empty rings */
-#define SHARED_RING_INIT(_s) do { \
- (_s)->req_prod = (_s)->rsp_prod = 0; \
- (_s)->req_event = (_s)->rsp_event = 1; \
- memset((_s)->pad, 0, sizeof((_s)->pad)); \
+#define SHARED_RING_INIT(_s) do { \
+ (_s)->req_prod = (_s)->rsp_prod = 0; \
+ (_s)->req_event = (_s)->rsp_event = 1; \
+ (void)memset((_s)->__pad, 0, sizeof((_s)->__pad)); \
} while(0)

-#define FRONT_RING_INIT(_r, _s, __size) do { \
- (_r)->req_prod_pvt = 0; \
- (_r)->rsp_cons = 0; \
- (_r)->nr_ents = __RING_SIZE(_s, __size); \
- (_r)->sring = (_s); \
+#define FRONT_RING_ATTACH(_r, _s, _i, __size) do { \
+ (_r)->req_prod_pvt = (_i); \
+ (_r)->rsp_cons = (_i); \
+ (_r)->nr_ents = __RING_SIZE(_s, __size); \
+ (_r)->sring = (_s); \
} while (0)

-#define BACK_RING_INIT(_r, _s, __size) do { \
- (_r)->rsp_prod_pvt = 0; \
- (_r)->req_cons = 0; \
- (_r)->nr_ents = __RING_SIZE(_s, __size); \
- (_r)->sring = (_s); \
-} while (0)
+#define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size)

-/* Initialize to existing shared indexes -- for recovery */
-#define FRONT_RING_ATTACH(_r, _s, __size) do { \
- (_r)->sring = (_s); \
- (_r)->req_prod_pvt = (_s)->req_prod; \
- (_r)->rsp_cons = (_s)->rsp_prod; \
- (_r)->nr_ents = __RING_SIZE(_s, __size); \
+#define BACK_RING_ATTACH(_r, _s, _i, __size) do { \
+ (_r)->rsp_prod_pvt = (_i); \
+ (_r)->req_cons = (_i); \
+ (_r)->nr_ents = __RING_SIZE(_s, __size); \
+ (_r)->sring = (_s); \
} while (0)

-#define BACK_RING_ATTACH(_r, _s, __size) do { \
- (_r)->sring = (_s); \
- (_r)->rsp_prod_pvt = (_s)->rsp_prod; \
- (_r)->req_cons = (_s)->req_prod; \
- (_r)->nr_ents = __RING_SIZE(_s, __size); \
-} while (0)
+#define BACK_RING_INIT(_r, _s, __size) BACK_RING_ATTACH(_r, _s, 0, __size)

/* How big is this ring? */
-#define RING_SIZE(_r) \
+#define RING_SIZE(_r) \
((_r)->nr_ents)

/* Number of free requests (for use on front side only). */
-#define RING_FREE_REQUESTS(_r) \
+#define RING_FREE_REQUESTS(_r) \
(RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons))

/* Test if there is an empty slot available on the front ring.
* (This is only meaningful from the front. )
*/
-#define RING_FULL(_r) \
+#define RING_FULL(_r) \
(RING_FREE_REQUESTS(_r) == 0)

/* Test if there are outstanding messages to be processed on a ring. */
-#define RING_HAS_UNCONSUMED_RESPONSES(_r) \
+#define RING_HAS_UNCONSUMED_RESPONSES(_r) \
((_r)->sring->rsp_prod - (_r)->rsp_cons)

-#define RING_HAS_UNCONSUMED_REQUESTS(_r) \
- ({ \
- unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \
- unsigned int rsp = RING_SIZE(_r) - \
- ((_r)->req_cons - (_r)->rsp_prod_pvt); \
- req < rsp ? req : rsp; \
- })
+#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \
+ unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \
+ unsigned int rsp = RING_SIZE(_r) - \
+ ((_r)->req_cons - (_r)->rsp_prod_pvt); \
+ req < rsp ? req : rsp; \
+})

/* Direct access to individual ring elements, by index. */
-#define RING_GET_REQUEST(_r, _idx) \
+#define RING_GET_REQUEST(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))

+#define RING_GET_RESPONSE(_r, _idx) \
+ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
+
/*
- * Get a local copy of a request.
+ * Get a local copy of a request/response.
*
- * Use this in preference to RING_GET_REQUEST() so all processing is
+ * Use this in preference to RING_GET_{REQUEST,RESPONSE}() so all processing is
* done on a local copy that cannot be modified by the other end.
*
* Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
- * to be ineffective where _req is a struct which consists of only bitfields.
+ * to be ineffective where dest is a struct which consists of only bitfields.
*/
-#define RING_COPY_REQUEST(_r, _idx, _req) do { \
- /* Use volatile to force the copy into _req. */ \
- *(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx); \
+#define RING_COPY_(type, r, idx, dest) do { \
+ /* Use volatile to force the copy into dest. */ \
+ *(dest) = *(volatile typeof(dest))RING_GET_##type(r, idx); \
} while (0)

-#define RING_GET_RESPONSE(_r, _idx) \
- (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
+#define RING_COPY_REQUEST(r, idx, req) RING_COPY_(REQUEST, r, idx, req)
+#define RING_COPY_RESPONSE(r, idx, rsp) RING_COPY_(RESPONSE, r, idx, rsp)

/* Loop termination condition: Would the specified index overflow the ring? */
-#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \
+#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \
(((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r))

/* Ill-behaved frontend determination: Can there be this many requests? */
-#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \
+#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \
(((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r))

+/* Ill-behaved backend determination: Can there be this many responses? */
+#define RING_RESPONSE_PROD_OVERFLOW(_r, _prod) \
+ (((_prod) - (_r)->rsp_cons) > RING_SIZE(_r))

-#define RING_PUSH_REQUESTS(_r) do { \
- virt_wmb(); /* back sees requests /before/ updated producer index */ \
- (_r)->sring->req_prod = (_r)->req_prod_pvt; \
+#define RING_PUSH_REQUESTS(_r) do { \
+ virt_wmb(); /* back sees requests /before/ updated producer index */\
+ (_r)->sring->req_prod = (_r)->req_prod_pvt; \
} while (0)

-#define RING_PUSH_RESPONSES(_r) do { \
- virt_wmb(); /* front sees responses /before/ updated producer index */ \
- (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \
+#define RING_PUSH_RESPONSES(_r) do { \
+ virt_wmb(); /* front sees resps /before/ updated producer index */ \
+ (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \
} while (0)

/*
@@ -250,40 +273,40 @@ struct __name##_back_ring { \
* field appropriately.
*/

-#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \
- RING_IDX __old = (_r)->sring->req_prod; \
- RING_IDX __new = (_r)->req_prod_pvt; \
- virt_wmb(); /* back sees requests /before/ updated producer index */ \
- (_r)->sring->req_prod = __new; \
- virt_mb(); /* back sees new requests /before/ we check req_event */ \
- (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \
- (RING_IDX)(__new - __old)); \
+#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \
+ RING_IDX __old = (_r)->sring->req_prod; \
+ RING_IDX __new = (_r)->req_prod_pvt; \
+ virt_wmb(); /* back sees requests /before/ updated producer index */\
+ (_r)->sring->req_prod = __new; \
+ virt_mb(); /* back sees new requests /before/ we check req_event */ \
+ (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \
+ (RING_IDX)(__new - __old)); \
} while (0)

-#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \
- RING_IDX __old = (_r)->sring->rsp_prod; \
- RING_IDX __new = (_r)->rsp_prod_pvt; \
- virt_wmb(); /* front sees responses /before/ updated producer index */ \
- (_r)->sring->rsp_prod = __new; \
- virt_mb(); /* front sees new responses /before/ we check rsp_event */ \
- (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \
- (RING_IDX)(__new - __old)); \
+#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \
+ RING_IDX __old = (_r)->sring->rsp_prod; \
+ RING_IDX __new = (_r)->rsp_prod_pvt; \
+ virt_wmb(); /* front sees resps /before/ updated producer index */ \
+ (_r)->sring->rsp_prod = __new; \
+ virt_mb(); /* front sees new resps /before/ we check rsp_event */ \
+ (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \
+ (RING_IDX)(__new - __old)); \
} while (0)

-#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \
- (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \
- if (_work_to_do) break; \
- (_r)->sring->req_event = (_r)->req_cons + 1; \
- virt_mb(); \
- (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \
+#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \
+ (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \
+ if (_work_to_do) break; \
+ (_r)->sring->req_event = (_r)->req_cons + 1; \
+ virt_mb(); \
+ (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \
} while (0)

-#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \
- (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \
- if (_work_to_do) break; \
- (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \
- virt_mb(); \
- (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \
+#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \
+ (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \
+ if (_work_to_do) break; \
+ (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \
+ virt_mb(); \
+ (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \
} while (0)


diff --git a/ipc/shm.c b/ipc/shm.c
index 44cca2529a95..d3cebe4e23e3 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -92,6 +92,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
struct shmid_kernel *shp;

shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+ WARN_ON(ns != shp->ns);

if (shp->shm_nattch) {
shp->shm_perm.mode |= SHM_DEST;
@@ -185,10 +186,43 @@ static void shm_rcu_free(struct rcu_head *head)
kvfree(shp);
}

-static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
+/*
+ * It has to be called with shp locked.
+ * It must be called before ipc_rmid()
+ */
+static inline void shm_clist_rm(struct shmid_kernel *shp)
+{
+ struct task_struct *creator;
+
+ /* ensure that shm_creator does not disappear */
+ rcu_read_lock();
+
+ /*
+ * A concurrent exit_shm may do a list_del_init() as well.
+ * Just do nothing if exit_shm already did the work
+ */
+ if (!list_empty(&shp->shm_clist)) {
+ /*
+ * shp->shm_creator is guaranteed to be valid *only*
+ * if shp->shm_clist is not empty.
+ */
+ creator = shp->shm_creator;
+
+ task_lock(creator);
+ /*
+ * list_del_init() is a nop if the entry was already removed
+ * from the list.
+ */
+ list_del_init(&shp->shm_clist);
+ task_unlock(creator);
+ }
+ rcu_read_unlock();
+}
+
+static inline void shm_rmid(struct shmid_kernel *s)
{
- list_del(&s->shm_clist);
- ipc_rmid(&shm_ids(ns), &s->shm_perm);
+ shm_clist_rm(s);
+ ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
}


@@ -243,7 +277,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
shm_file = shp->shm_file;
shp->shm_file = NULL;
ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
- shm_rmid(ns, shp);
+ shm_rmid(shp);
shm_unlock(shp);
if (!is_file_hugepages(shm_file))
shmem_lock(shm_file, 0, shp->mlock_user);
@@ -264,10 +298,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
*
* 2) sysctl kernel.shm_rmid_forced is set to 1.
*/
-static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+static bool shm_may_destroy(struct shmid_kernel *shp)
{
return (shp->shm_nattch == 0) &&
- (ns->shm_rmid_forced ||
+ (shp->ns->shm_rmid_forced ||
(shp->shm_perm.mode & SHM_DEST));
}

@@ -298,7 +332,7 @@ static void shm_close(struct vm_area_struct *vma)
shp->shm_lprid = task_tgid_vnr(current);
shp->shm_dtim = ktime_get_real_seconds();
shp->shm_nattch--;
- if (shm_may_destroy(ns, shp))
+ if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
@@ -319,10 +353,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
*
* As shp->* are changed under rwsem, it's safe to skip shp locking.
*/
- if (shp->shm_creator != NULL)
+ if (!list_empty(&shp->shm_clist))
return 0;

- if (shm_may_destroy(ns, shp)) {
+ if (shm_may_destroy(shp)) {
shm_lock_by_ptr(shp);
shm_destroy(ns, shp);
}
@@ -340,48 +374,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns)
/* Locking assumes this will only be called with task == current */
void exit_shm(struct task_struct *task)
{
- struct ipc_namespace *ns = task->nsproxy->ipc_ns;
- struct shmid_kernel *shp, *n;
+ for (;;) {
+ struct shmid_kernel *shp;
+ struct ipc_namespace *ns;

- if (list_empty(&task->sysvshm.shm_clist))
- return;
+ task_lock(task);
+
+ if (list_empty(&task->sysvshm.shm_clist)) {
+ task_unlock(task);
+ break;
+ }
+
+ shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
+ shm_clist);

- /*
- * If kernel.shm_rmid_forced is not set then only keep track of
- * which shmids are orphaned, so that a later set of the sysctl
- * can clean them up.
- */
- if (!ns->shm_rmid_forced) {
- down_read(&shm_ids(ns).rwsem);
- list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
- shp->shm_creator = NULL;
/*
- * Only under read lock but we are only called on current
- * so no entry on the list will be shared.
+ * 1) Get pointer to the ipc namespace. It is worth to say
+ * that this pointer is guaranteed to be valid because
+ * shp lifetime is always shorter than namespace lifetime
+ * in which shp lives.
+ * We taken task_lock it means that shp won't be freed.
*/
- list_del(&task->sysvshm.shm_clist);
- up_read(&shm_ids(ns).rwsem);
- return;
- }
+ ns = shp->ns;

- /*
- * Destroy all already created segments, that were not yet mapped,
- * and mark any mapped as orphan to cover the sysctl toggling.
- * Destroy is skipped if shm_may_destroy() returns false.
- */
- down_write(&shm_ids(ns).rwsem);
- list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
- shp->shm_creator = NULL;
+ /*
+ * 2) If kernel.shm_rmid_forced is not set then only keep track of
+ * which shmids are orphaned, so that a later set of the sysctl
+ * can clean them up.
+ */
+ if (!ns->shm_rmid_forced)
+ goto unlink_continue;

- if (shm_may_destroy(ns, shp)) {
- shm_lock_by_ptr(shp);
- shm_destroy(ns, shp);
+ /*
+ * 3) get a reference to the namespace.
+ * The refcount could be already 0. If it is 0, then
+ * the shm objects will be free by free_ipc_work().
+ */
+ ns = get_ipc_ns_not_zero(ns);
+ if (!ns) {
+unlink_continue:
+ list_del_init(&shp->shm_clist);
+ task_unlock(task);
+ continue;
}
- }

- /* Remove the list head from any segments still attached. */
- list_del(&task->sysvshm.shm_clist);
- up_write(&shm_ids(ns).rwsem);
+ /*
+ * 4) get a reference to shp.
+ * This cannot fail: shm_clist_rm() is called before
+ * ipc_rmid(), thus the refcount cannot be 0.
+ */
+ WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
+
+ /*
+ * 5) unlink the shm segment from the list of segments
+ * created by current.
+ * This must be done last. After unlinking,
+ * only the refcounts obtained above prevent IPC_RMID
+ * from destroying the segment or the namespace.
+ */
+ list_del_init(&shp->shm_clist);
+
+ task_unlock(task);
+
+ /*
+ * 6) we have all references
+ * Thus lock & if needed destroy shp.
+ */
+ down_write(&shm_ids(ns).rwsem);
+ shm_lock_by_ptr(shp);
+ /*
+ * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's
+ * safe to call ipc_rcu_putref here
+ */
+ ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
+
+ if (ipc_valid_object(&shp->shm_perm)) {
+ if (shm_may_destroy(shp))
+ shm_destroy(ns, shp);
+ else
+ shm_unlock(shp);
+ } else {
+ /*
+ * Someone else deleted the shp from namespace
+ * idr/kht while we have waited.
+ * Just unlock and continue.
+ */
+ shm_unlock(shp);
+ }
+
+ up_write(&shm_ids(ns).rwsem);
+ put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */
+ }
}

static int shm_fault(struct vm_fault *vmf)
@@ -625,7 +708,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
if (error < 0)
goto no_id;

+ shp->ns = ns;
+
+ task_lock(current);
list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
+ task_unlock(current);

/*
* shmid gets reported as "inode#" in /proc/pid/maps.
@@ -1449,7 +1536,8 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
down_write(&shm_ids(ns).rwsem);
shp = shm_lock(ns, shmid);
shp->shm_nattch--;
- if (shm_may_destroy(ns, shp))
+
+ if (shm_may_destroy(shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
diff --git a/ipc/util.c b/ipc/util.c
index 5a65b0cbae7d..198b4c1c3ad3 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -409,8 +409,8 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
{
if (ipcp->key != IPC_PRIVATE)
- rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
- ipc_kht_params);
+ WARN_ON_ONCE(rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
+ ipc_kht_params));
}

/**
@@ -425,7 +425,7 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
{
int lid = ipcid_to_idx(ipcp->id);

- idr_remove(&ids->ipcs_idr, lid);
+ WARN_ON_ONCE(idr_remove(&ids->ipcs_idr, lid) != ipcp);
ipc_kht_remove(ids, ipcp);
ids->in_use--;
ipcp->deleted = true;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d752c1df8f3f..4f918dd28fb7 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2004,6 +2004,9 @@ int register_kretprobe(struct kretprobe *rp)
}
}

+ if (rp->data_size > KRETPROBE_MAX_DATA_SIZE)
+ return -E2BIG;
+
rp->kp.pre_handler = pre_handler_kretprobe;
rp->kp.post_handler = NULL;
rp->kp.fault_handler = NULL;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 02df69a8ee3c..e68b1c20ad3d 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -668,7 +668,7 @@ static int load_image_and_restore(void)
goto Unlock;

error = swsusp_read(&flags);
- swsusp_close(FMODE_READ);
+ swsusp_close(FMODE_READ | FMODE_EXCL);
if (!error)
hibernation_restore(flags & SF_PLATFORM_MODE);

@@ -865,7 +865,7 @@ static int software_resume(void)
/* The snapshot device should not be opened while we're running */
if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
error = -EBUSY;
- swsusp_close(FMODE_READ);
+ swsusp_close(FMODE_READ | FMODE_EXCL);
goto Unlock;
}

@@ -901,7 +901,7 @@ static int software_resume(void)
pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
return error;
Close_Finish:
- swsusp_close(FMODE_READ);
+ swsusp_close(FMODE_READ | FMODE_EXCL);
goto Finish;
}

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b5a251efd164..365bc02230a9 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1363,14 +1363,26 @@ __event_trigger_test_discard(struct trace_event_file *file,
if (eflags & EVENT_FILE_FL_TRIGGER_COND)
*tt = event_triggers_call(file, entry);

- if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
- (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
- !filter_match_preds(file->filter, entry))) {
- __trace_event_discard_commit(buffer, event);
- return true;
- }
+ if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED |
+ EVENT_FILE_FL_FILTERED |
+ EVENT_FILE_FL_PID_FILTER))))
+ return false;
+
+ if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
+ goto discard;
+
+ if (file->flags & EVENT_FILE_FL_FILTERED &&
+ !filter_match_preds(file->filter, entry))
+ goto discard;
+
+ if ((file->flags & EVENT_FILE_FL_PID_FILTER) &&
+ trace_event_ignore_this_pid(file))
+ goto discard;

return false;
+ discard:
+ __trace_event_discard_commit(buffer, event);
+ return true;
}

/**
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7b4af70d9dfd..1285ef6e2d14 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2254,12 +2254,19 @@ static struct trace_event_file *
trace_create_new_event(struct trace_event_call *call,
struct trace_array *tr)
{
+ struct trace_pid_list *pid_list;
struct trace_event_file *file;

file = kmem_cache_alloc(file_cachep, GFP_TRACE);
if (!file)
return NULL;

+ pid_list = rcu_dereference_protected(tr->filtered_pids,
+ lockdep_is_held(&event_mutex));
+
+ if (pid_list)
+ file->flags |= EVENT_FILE_FL_PID_FILTER;
+
file->event_call = call;
file->tr = tr;
atomic_set(&file->sm_ref, 0);
diff --git a/lib/siphash.c b/lib/siphash.c
index 3ae58b4edad6..e632ee40aac1 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -49,6 +49,7 @@
SIPROUND; \
return (v0 ^ v1) ^ (v2 ^ v3);

+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
@@ -80,8 +81,8 @@ u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
POSTAMBLE
}
EXPORT_SYMBOL(__siphash_aligned);
+#endif

-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
@@ -113,7 +114,6 @@ u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
POSTAMBLE
}
EXPORT_SYMBOL(__siphash_unaligned);
-#endif

/**
* siphash_1u64 - compute 64-bit siphash PRF value of a u64
@@ -250,6 +250,7 @@ EXPORT_SYMBOL(siphash_3u32);
HSIPROUND; \
return (v0 ^ v1) ^ (v2 ^ v3);

+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u64));
@@ -280,8 +281,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_aligned);
+#endif

-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key)
{
@@ -313,7 +314,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif

/**
* hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
@@ -418,6 +418,7 @@ EXPORT_SYMBOL(hsiphash_4u32);
HSIPROUND; \
return v1 ^ v3;

+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
{
const u8 *end = data + len - (len % sizeof(u32));
@@ -438,8 +439,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_aligned);
+#endif

-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
u32 __hsiphash_unaligned(const void *data, size_t len,
const hsiphash_key_t *key)
{
@@ -461,7 +462,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
HPOSTAMBLE
}
EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif

/**
* hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c765fd01f0aa..c6ae9c9e360d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3384,8 +3384,9 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
struct page *page;
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
- const unsigned long mmun_start = start; /* For mmu_notifiers */
- const unsigned long mmun_end = end; /* For mmu_notifiers */
+ unsigned long mmun_start = start; /* For mmu_notifiers */
+ unsigned long mmun_end = end; /* For mmu_notifiers */
+ bool force_flush = false;

WARN_ON(!is_vm_hugetlb_page(vma));
BUG_ON(start & ~huge_page_mask(h));
@@ -3397,6 +3398,11 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
*/
tlb_remove_check_page_size_change(tlb, sz);
tlb_start_vma(tlb, vma);
+
+ /*
+ * If sharing possible, alert mmu notifiers of worst case.
+ */
+ adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end);
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
address = start;
for (; address < end; address += sz) {
@@ -3407,6 +3413,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, &address, ptep)) {
spin_unlock(ptl);
+ tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+ force_flush = true;
continue;
}

@@ -3463,6 +3471,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
}
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
tlb_end_vma(tlb, vma);
+
+ /*
+ * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
+ * could defer the flush until now, since by holding i_mmap_rwsem we
+ * guaranteed that the last refernece would not be dropped. But we must
+ * do the flushing before we return, as otherwise i_mmap_rwsem will be
+ * dropped and the last reference to the shared PMDs page might be
+ * dropped as well.
+ *
+ * In theory we could defer the freeing of the PMD pages as well, but
+ * huge_pmd_unshare() relies on the exact page_count for the PMD page to
+ * detect sharing, so we cannot defer the release of the page either.
+ * Instead, do flush now.
+ */
+ if (force_flush)
+ tlb_flush_mmu(tlb);
}

void __unmap_hugepage_range_final(struct mmu_gather *tlb,
@@ -3489,12 +3513,23 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
{
struct mm_struct *mm;
struct mmu_gather tlb;
+ unsigned long tlb_start = start;
+ unsigned long tlb_end = end;
+
+ /*
+ * If shared PMDs were possibly used within this vma range, adjust
+ * start/end for worst case tlb flushing.
+ * Note that we can not be sure if PMDs are shared until we try to
+ * unmap pages. However, we want to make sure TLB flushing covers
+ * the largest possible range.
+ */
+ adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end);

mm = vma->vm_mm;

- tlb_gather_mmu(&tlb, mm, start, end);
+ tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end);
__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
- tlb_finish_mmu(&tlb, start, end);
+ tlb_finish_mmu(&tlb, tlb_start, tlb_end);
}

/*
@@ -4389,11 +4424,21 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
pte_t pte;
struct hstate *h = hstate_vma(vma);
unsigned long pages = 0;
+ unsigned long f_start = start;
+ unsigned long f_end = end;
+ bool shared_pmd = false;
+
+ /*
+ * In the case of shared PMDs, the area to flush could be beyond
+ * start/end. Set f_start/f_end to cover the maximum possible
+ * range if PMD sharing is possible.
+ */
+ adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end);

BUG_ON(address >= end);
- flush_cache_range(vma, address, end);
+ flush_cache_range(vma, f_start, f_end);

- mmu_notifier_invalidate_range_start(mm, start, end);
+ mmu_notifier_invalidate_range_start(mm, f_start, f_end);
i_mmap_lock_write(vma->vm_file->f_mapping);
for (; address < end; address += huge_page_size(h)) {
spinlock_t *ptl;
@@ -4404,6 +4449,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
if (huge_pmd_unshare(mm, &address, ptep)) {
pages++;
spin_unlock(ptl);
+ shared_pmd = true;
continue;
}
pte = huge_ptep_get(ptep);
@@ -4439,12 +4485,18 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
* Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
* may have cleared our pud entry and done put_page on the page table:
* once we release i_mmap_rwsem, another task can do the final put_page
- * and that page table be reused and filled with junk.
+ * and that page table be reused and filled with junk. If we actually
+ * did unshare a page of pmds, flush the range corresponding to the pud.
*/
- flush_hugetlb_tlb_range(vma, start, end);
- mmu_notifier_invalidate_range(mm, start, end);
+ if (shared_pmd) {
+ flush_hugetlb_tlb_range(vma, f_start, f_end);
+ mmu_notifier_invalidate_range(mm, f_start, f_end);
+ } else {
+ flush_hugetlb_tlb_range(vma, start, end);
+ mmu_notifier_invalidate_range(mm, start, end);
+ }
i_mmap_unlock_write(vma->vm_file->f_mapping);
- mmu_notifier_invalidate_range_end(mm, start, end);
+ mmu_notifier_invalidate_range_end(mm, f_start, f_end);

return pages << h->order;
}
diff --git a/mm/memory.c b/mm/memory.c
index c4f142d1ff98..b001670c9615 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -335,6 +335,16 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
return false;
}

+void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address,
+ unsigned long size)
+{
+ if (tlb->page_size != 0 && tlb->page_size != PMD_SIZE)
+ tlb_flush_mmu(tlb);
+
+ tlb->page_size = PMD_SIZE;
+ tlb->start = min(tlb->start, address);
+ tlb->end = max(tlb->end, address + size);
+}
#endif /* HAVE_GENERIC_MMU_GATHER */

#ifdef CONFIG_HAVE_RCU_TABLE_FREE
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d4d53aea2c60..d9bb3ae78560 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2324,7 +2324,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
free:
kfree(t);
out:
- return -ENOBUFS;
+ return -ENOMEM;
}

static void __devinet_sysctl_unregister(struct net *net,
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 8b5ba0a5cd38..93530bd33247 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -340,8 +340,6 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
return;

if (tcp_in_slow_start(tp)) {
- if (hystart && after(ack, ca->end_seq))
- bictcp_hystart_reset(sk);
acked = tcp_slow_start(tp, acked);
if (!acked)
return;
@@ -383,6 +381,9 @@ static void hystart_update(struct sock *sk, u32 delay)
if (ca->found & hystart_detect)
return;

+ if (after(tp->snd_una, ca->end_seq))
+ bictcp_hystart_reset(sk);
+
if (hystart_detect & HYSTART_ACK_TRAIN) {
u32 now = bictcp_clock();

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a903d0ce7e70..f906fe2acedd 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -175,7 +175,7 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
if (skb_dst(skb)->xfrm) {
- IPCB(skb)->flags |= IPSKB_REROUTED;
+ IP6CB(skb)->flags |= IP6SKB_REROUTED;
return dst_output(net, sk, skb);
}
#endif
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 00ede709db2e..f078e8506e25 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1407,22 +1407,52 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head)
kfree(mdev);
}

-static void mpls_ifdown(struct net_device *dev, int event)
+static int mpls_ifdown(struct net_device *dev, int event)
{
struct mpls_route __rcu **platform_label;
struct net *net = dev_net(dev);
- u8 alive, deleted;
unsigned index;

platform_label = rtnl_dereference(net->mpls.platform_label);
for (index = 0; index < net->mpls.platform_labels; index++) {
struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+ bool nh_del = false;
+ u8 alive = 0;

if (!rt)
continue;

- alive = 0;
- deleted = 0;
+ if (event == NETDEV_UNREGISTER) {
+ u8 deleted = 0;
+
+ for_nexthops(rt) {
+ struct net_device *nh_dev =
+ rtnl_dereference(nh->nh_dev);
+
+ if (!nh_dev || nh_dev == dev)
+ deleted++;
+ if (nh_dev == dev)
+ nh_del = true;
+ } endfor_nexthops(rt);
+
+ /* if there are no more nexthops, delete the route */
+ if (deleted == rt->rt_nhn) {
+ mpls_route_update(net, index, NULL, NULL);
+ continue;
+ }
+
+ if (nh_del) {
+ size_t size = sizeof(*rt) + rt->rt_nhn *
+ rt->rt_nh_size;
+ struct mpls_route *orig = rt;
+
+ rt = kmalloc(size, GFP_KERNEL);
+ if (!rt)
+ return -ENOMEM;
+ memcpy(rt, orig, size);
+ }
+ }
+
change_nexthops(rt) {
unsigned int nh_flags = nh->nh_flags;

@@ -1446,16 +1476,15 @@ static void mpls_ifdown(struct net_device *dev, int event)
next:
if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
alive++;
- if (!rtnl_dereference(nh->nh_dev))
- deleted++;
} endfor_nexthops(rt);

WRITE_ONCE(rt->rt_nhn_alive, alive);

- /* if there are no more nexthops, delete the route */
- if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
- mpls_route_update(net, index, NULL, NULL);
+ if (nh_del)
+ mpls_route_update(net, index, rt, NULL);
}
+
+ return 0;
}

static void mpls_ifup(struct net_device *dev, unsigned int flags)
@@ -1519,8 +1548,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
return NOTIFY_OK;

switch (event) {
+ int err;
+
case NETDEV_DOWN:
- mpls_ifdown(dev, event);
+ err = mpls_ifdown(dev, event);
+ if (err)
+ return notifier_from_errno(err);
break;
case NETDEV_UP:
flags = dev_get_flags(dev);
@@ -1531,13 +1564,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
break;
case NETDEV_CHANGE:
flags = dev_get_flags(dev);
- if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+ if (flags & (IFF_RUNNING | IFF_LOWER_UP)) {
mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
- else
- mpls_ifdown(dev, event);
+ } else {
+ err = mpls_ifdown(dev, event);
+ if (err)
+ return notifier_from_errno(err);
+ }
break;
case NETDEV_UNREGISTER:
- mpls_ifdown(dev, event);
+ err = mpls_ifdown(dev, event);
+ if (err)
+ return notifier_from_errno(err);
mdev = mpls_dev_get(dev);
if (mdev) {
mpls_dev_sysctl_unregister(dev, mdev);
@@ -1548,8 +1586,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
case NETDEV_CHANGENAME:
mdev = mpls_dev_get(dev);
if (mdev) {
- int err;
-
mpls_dev_sysctl_unregister(dev, mdev);
err = mpls_dev_sysctl_register(dev, mdev);
if (err)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index a95fe5fe9f04..4b9cd1c1c998 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1838,7 +1838,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
struct ip_vs_proto_data *pd;
struct ip_vs_conn *cp;
int ret, pkts;
- int conn_reuse_mode;
struct sock *sk;

/* Already marked as IPVS request or reply? */
@@ -1914,15 +1913,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
*/
cp = pp->conn_in_get(ipvs, af, skb, &iph);

- conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
- if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+ if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+ int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
bool old_ct = false, resched = false;

if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
unlikely(!atomic_read(&cp->dest->weight))) {
resched = true;
old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
- } else if (is_new_conn_expected(cp, conn_reuse_mode)) {
+ } else if (conn_reuse_mode &&
+ is_new_conn_expected(cp, conn_reuse_mode)) {
old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
if (!atomic_read(&cp->n_control)) {
resched = true;
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index c73651faa549..c6dc82f66bd9 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -485,6 +485,11 @@ static int nci_open_device(struct nci_dev *ndev)

mutex_lock(&ndev->req_lock);

+ if (test_bit(NCI_UNREG, &ndev->flags)) {
+ rc = -ENODEV;
+ goto done;
+ }
+
if (test_bit(NCI_UP, &ndev->flags)) {
rc = -EALREADY;
goto done;
@@ -548,6 +553,10 @@ static int nci_open_device(struct nci_dev *ndev)
static int nci_close_device(struct nci_dev *ndev)
{
nci_req_cancel(ndev, ENODEV);
+
+ /* This mutex needs to be held as a barrier for
+ * caller nci_unregister_device
+ */
mutex_lock(&ndev->req_lock);

if (!test_and_clear_bit(NCI_UP, &ndev->flags)) {
@@ -585,8 +594,8 @@ static int nci_close_device(struct nci_dev *ndev)
/* Flush cmd wq */
flush_workqueue(ndev->cmd_wq);

- /* Clear flags */
- ndev->flags = 0;
+ /* Clear flags except NCI_UNREG */
+ ndev->flags &= BIT(NCI_UNREG);

mutex_unlock(&ndev->req_lock);

@@ -1270,6 +1279,12 @@ void nci_unregister_device(struct nci_dev *ndev)
{
struct nci_conn_info *conn_info, *n;

+ /* This set_bit is not protected with specialized barrier,
+ * However, it is fine because the mutex_lock(&ndev->req_lock);
+ * in nci_close_device() will help to emit one.
+ */
+ set_bit(NCI_UNREG, &ndev->flags);
+
nci_close_device(ndev);

destroy_workqueue(ndev->cmd_wq);
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 82e9ffecd90e..55bae71bf339 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -392,7 +392,7 @@ void rds_tcp_tune(struct socket *sock)
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
}
if (rtn->rcvbuf_size > 0) {
- sk->sk_sndbuf = rtn->rcvbuf_size;
+ sk->sk_rcvbuf = rtn->rcvbuf_size;
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
}
release_sock(sk);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 8c71f0929fbb..f2c907d52812 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1178,8 +1178,10 @@ static unsigned int smc_poll(struct file *file, struct socket *sock,
static int smc_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
+ bool do_shutdown = true;
struct smc_sock *smc;
int rc = -EINVAL;
+ int old_state;
int rc1 = 0;

smc = smc_sk(sk);
@@ -1206,7 +1208,11 @@ static int smc_shutdown(struct socket *sock, int how)
}
switch (how) {
case SHUT_RDWR: /* shutdown in both directions */
+ old_state = sk->sk_state;
rc = smc_close_active(smc);
+ if (old_state == SMC_ACTIVE &&
+ sk->sk_state == SMC_PEERCLOSEWAIT1)
+ do_shutdown = false;
break;
case SHUT_WR:
rc = smc_close_shutdown_write(smc);
@@ -1216,7 +1222,7 @@ static int smc_shutdown(struct socket *sock, int how)
/* nothing more to do because peer is not involved */
break;
}
- if (smc->clcsock)
+ if (do_shutdown && smc->clcsock)
rc1 = kernel_sock_shutdown(smc->clcsock, how);
/* map sock_shutdown_cmd constants to sk_shutdown value range */
sk->sk_shutdown |= how + 1;
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 2427a1f3d0d1..5cda681e5cc4 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -180,6 +180,7 @@ int smc_close_active(struct smc_sock *smc)
int old_state;
long timeout;
int rc = 0;
+ int rc1 = 0;

timeout = current->flags & PF_EXITING ?
0 : sock_flag(sk, SOCK_LINGER) ?
@@ -215,6 +216,15 @@ int smc_close_active(struct smc_sock *smc)
/* send close request */
rc = smc_close_final(conn);
sk->sk_state = SMC_PEERCLOSEWAIT1;
+
+ /* actively shutdown clcsock before peer close it,
+ * prevent peer from entering TIME_WAIT state.
+ */
+ if (smc->clcsock && smc->clcsock->sk) {
+ rc1 = kernel_sock_shutdown(smc->clcsock,
+ SHUT_RDWR);
+ rc = rc ? rc : rc1;
+ }
} else {
/* peer event has changed the state */
goto again;
diff --git a/sound/pci/ctxfi/ctamixer.c b/sound/pci/ctxfi/ctamixer.c
index 5fcbb065d870..d32685ce6c05 100644
--- a/sound/pci/ctxfi/ctamixer.c
+++ b/sound/pci/ctxfi/ctamixer.c
@@ -27,16 +27,15 @@

#define BLANK_SLOT 4094

-static int amixer_master(struct rsc *rsc)
+static void amixer_master(struct rsc *rsc)
{
rsc->conj = 0;
- return rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0];
+ rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0];
}

-static int amixer_next_conj(struct rsc *rsc)
+static void amixer_next_conj(struct rsc *rsc)
{
rsc->conj++;
- return container_of(rsc, struct amixer, rsc)->idx[rsc->conj];
}

static int amixer_index(const struct rsc *rsc)
@@ -335,16 +334,15 @@ int amixer_mgr_destroy(struct amixer_mgr *amixer_mgr)

/* SUM resource management */

-static int sum_master(struct rsc *rsc)
+static void sum_master(struct rsc *rsc)
{
rsc->conj = 0;
- return rsc->idx = container_of(rsc, struct sum, rsc)->idx[0];
+ rsc->idx = container_of(rsc, struct sum, rsc)->idx[0];
}

-static int sum_next_conj(struct rsc *rsc)
+static void sum_next_conj(struct rsc *rsc)
{
rsc->conj++;
- return container_of(rsc, struct sum, rsc)->idx[rsc->conj];
}

static int sum_index(const struct rsc *rsc)
diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c
index 7f089cb433e1..df326b7663a2 100644
--- a/sound/pci/ctxfi/ctdaio.c
+++ b/sound/pci/ctxfi/ctdaio.c
@@ -55,12 +55,12 @@ static struct daio_rsc_idx idx_20k2[NUM_DAIOTYP] = {
[SPDIFIO] = {.left = 0x05, .right = 0x85},
};

-static int daio_master(struct rsc *rsc)
+static void daio_master(struct rsc *rsc)
{
/* Actually, this is not the resource index of DAIO.
* For DAO, it is the input mapper index. And, for DAI,
* it is the output time-slot index. */
- return rsc->conj = rsc->idx;
+ rsc->conj = rsc->idx;
}

static int daio_index(const struct rsc *rsc)
@@ -68,19 +68,19 @@ static int daio_index(const struct rsc *rsc)
return rsc->conj;
}

-static int daio_out_next_conj(struct rsc *rsc)
+static void daio_out_next_conj(struct rsc *rsc)
{
- return rsc->conj += 2;
+ rsc->conj += 2;
}

-static int daio_in_next_conj_20k1(struct rsc *rsc)
+static void daio_in_next_conj_20k1(struct rsc *rsc)
{
- return rsc->conj += 0x200;
+ rsc->conj += 0x200;
}

-static int daio_in_next_conj_20k2(struct rsc *rsc)
+static void daio_in_next_conj_20k2(struct rsc *rsc)
{
- return rsc->conj += 0x100;
+ rsc->conj += 0x100;
}

static const struct rsc_ops daio_out_rsc_ops = {
diff --git a/sound/pci/ctxfi/ctresource.c b/sound/pci/ctxfi/ctresource.c
index 80c4d84f9667..f05a09ed42b8 100644
--- a/sound/pci/ctxfi/ctresource.c
+++ b/sound/pci/ctxfi/ctresource.c
@@ -113,18 +113,17 @@ static int audio_ring_slot(const struct rsc *rsc)
return (rsc->conj << 4) + offset_in_audio_slot_block[rsc->type];
}

-static int rsc_next_conj(struct rsc *rsc)
+static void rsc_next_conj(struct rsc *rsc)
{
unsigned int i;
for (i = 0; (i < 8) && (!(rsc->msr & (0x1 << i))); )
i++;
rsc->conj += (AUDIO_SLOT_BLOCK_NUM >> i);
- return rsc->conj;
}

-static int rsc_master(struct rsc *rsc)
+static void rsc_master(struct rsc *rsc)
{
- return rsc->conj = rsc->idx;
+ rsc->conj = rsc->idx;
}

static const struct rsc_ops rsc_generic_ops = {
diff --git a/sound/pci/ctxfi/ctresource.h b/sound/pci/ctxfi/ctresource.h
index 736d9f7e9e16..29b6fe6de659 100644
--- a/sound/pci/ctxfi/ctresource.h
+++ b/sound/pci/ctxfi/ctresource.h
@@ -43,8 +43,8 @@ struct rsc {
};

struct rsc_ops {
- int (*master)(struct rsc *rsc); /* Move to master resource */
- int (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */
+ void (*master)(struct rsc *rsc); /* Move to master resource */
+ void (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */
int (*index)(const struct rsc *rsc); /* Return the index of resource */
/* Return the output slot number */
int (*output_slot)(const struct rsc *rsc);
diff --git a/sound/pci/ctxfi/ctsrc.c b/sound/pci/ctxfi/ctsrc.c
index bb4c9c3c89ae..93d660276c82 100644
--- a/sound/pci/ctxfi/ctsrc.c
+++ b/sound/pci/ctxfi/ctsrc.c
@@ -594,16 +594,15 @@ int src_mgr_destroy(struct src_mgr *src_mgr)

/* SRCIMP resource manager operations */

-static int srcimp_master(struct rsc *rsc)
+static void srcimp_master(struct rsc *rsc)
{
rsc->conj = 0;
- return rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0];
+ rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0];
}

-static int srcimp_next_conj(struct rsc *rsc)
+static void srcimp_next_conj(struct rsc *rsc)
{
rsc->conj++;
- return container_of(rsc, struct srcimp, rsc)->idx[rsc->conj];
}

static int srcimp_index(const struct rsc *rsc)
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 50aa45525be5..0fbe50502699 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -2585,6 +2585,7 @@ EXPORT_SYMBOL_GPL(snd_soc_tplg_widget_remove_all);
/* remove dynamic controls from the component driver */
int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index)
{
+ struct snd_card *card = comp->card->snd_card;
struct snd_soc_dobj *dobj, *next_dobj;
int pass = SOC_TPLG_PASS_END;

@@ -2592,6 +2593,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index)
while (pass >= SOC_TPLG_PASS_START) {

/* remove mixer controls */
+ down_write(&card->controls_rwsem);
list_for_each_entry_safe(dobj, next_dobj, &comp->dobj_list,
list) {

@@ -2625,6 +2627,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index)
break;
}
}
+ up_write(&card->controls_rwsem);
pass--;
}

diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 706f6f1e9c7d..445a7012b117 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -468,6 +468,18 @@ struct perf_hpp_list perf_hpp_list = {
#undef __HPP_SORT_ACC_FN
#undef __HPP_SORT_RAW_FN

+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+ /*
+ * At this point fmt should be completely
+ * unhooked, if not it's a bug.
+ */
+ BUG_ON(!list_empty(&fmt->list));
+ BUG_ON(!list_empty(&fmt->sort_list));
+
+ if (fmt->free)
+ fmt->free(fmt);
+}

void perf_hpp__init(void)
{
@@ -531,9 +543,10 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
list_add(&format->sort_list, &list->sorts);
}

-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
{
list_del_init(&format->list);
+ fmt_free(format);
}

void perf_hpp__cancel_cumulate(void)
@@ -605,19 +618,6 @@ void perf_hpp__append_sort_keys(struct perf_hpp_list *list)
}


-static void fmt_free(struct perf_hpp_fmt *fmt)
-{
- /*
- * At this point fmt should be completely
- * unhooked, if not it's a bug.
- */
- BUG_ON(!list_empty(&fmt->list));
- BUG_ON(!list_empty(&fmt->sort_list));
-
- if (fmt->free)
- fmt->free(fmt);
-}
-
void perf_hpp__reset_output_field(struct perf_hpp_list *list)
{
struct perf_hpp_fmt *fmt, *tmp;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 595f91f46811..2eb71eeec485 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -339,7 +339,6 @@ enum {
};

void perf_hpp__init(void);
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
void perf_hpp__cancel_cumulate(void);
void perf_hpp__setup_output_field(struct perf_hpp_list *list);
void perf_hpp__reset_output_field(struct perf_hpp_list *list);
\
 
 \ /
  Last update: 2021-12-08 09:29    [W:0.744 / U:0.228 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site