diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst index 894a19897005..bac3789f3e8f 100644 --- a/Documentation/x86/boot.rst +++ b/Documentation/x86/boot.rst @@ -1416,7 +1416,7 @@ execution context provided by the EFI firmware.

The function prototype for the handover entry point looks like this::

- efi_main(void *handle, efi_system_table_t *table, struct boot_params *bp) + efi_stub_entry(void *handle, efi_system_table_t *table, struct boot_params *bp)

'handle' is the EFI image handle passed to the boot loader by the EFI firmware, 'table' is the EFI system table - these are the first two diff --git a/Documentation/x86/mds.rst b/Documentation/x86/mds.rst index 5d4330be200f..e801df0bb3a8 100644 --- a/Documentation/x86/mds.rst +++ b/Documentation/x86/mds.rst @@ -95,6 +95,9 @@ The kernel provides a function to invoke the buffer clearing:

mds_clear_cpu_buffers()

+Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path. +Other than CFLAGS.ZF, this macro doesn't clobber any registers. + The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state (idle) transitions.

@@ -138,17 +141,30 @@ Mitigation points

When transitioning from kernel to user space the CPU buffers are flushed on affected CPUs when the mitigation is not disabled on the kernel - command line. The migitation is enabled through the static key - mds_user_clear. - - The mitigation is invoked in prepare_exit_to_usermode() which covers - all but one of the kernel to user space transitions. The exception - is when we return from a Non Maskable Interrupt (NMI), which is - handled directly in do_nmi(). - - (The reason that NMI is special is that prepare_exit_to_usermode() can - enable IRQs. In NMI context, NMIs are blocked, and we don't want to - enable IRQs with NMIs blocked.) + command line. The mitigation is enabled through the feature flag + X86_FEATURE_CLEAR_CPU_BUF. + + The mitigation is invoked just before transitioning to userspace after + user registers are restored. This is done to minimize the window in + which kernel data could be accessed after VERW e.g. via an NMI after + VERW. + + **Corner case not handled** + Interrupts returning to kernel don't clear CPUs buffers since the + exit-to-user path is expected to do that anyways. But, there could be + a case when an NMI is generated in kernel after the exit-to-user path + has cleared the buffers. This case is not handled and NMI returning to + kernel don't clear CPU buffers because: + + 1. It is rare to get an NMI after VERW, but before returning to userspace. + 2. For an unprivileged user, there is no known way to make that NMI + less rare or target it. + 3. It would take a large number of these precisely-timed NMIs to mount + an actual attack. There's presumably not enough bandwidth. + 4. The NMI in question occurs after a VERW, i.e. when user state is + restored and most interesting data is already scrubbed. Whats left + is only the data that NMI touches, and that may or may not be of + any interest.

2. C-State transition diff --git a/MAINTAINERS b/MAINTAINERS index 13d1078808bb..bbfedb0b2093 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10051,6 +10051,7 @@ F: drivers/infiniband/ F: include/rdma/ F: include/trace/events/ib_mad.h F: include/trace/events/ib_umad.h +F: include/trace/misc/rdma.h F: include/uapi/linux/if_infiniband.h F: include/uapi/rdma/ F: samples/bpf/ibumad_kern.c @@ -11139,6 +11140,12 @@ F: fs/nfs_common/ F: fs/nfsd/ F: include/linux/lockd/ F: include/linux/sunrpc/ +F: include/trace/events/rpcgss.h +F: include/trace/events/rpcrdma.h +F: include/trace/events/sunrpc.h +F: include/trace/misc/fs.h +F: include/trace/misc/nfs.h +F: include/trace/misc/sunrpc.h F: include/uapi/linux/nfsd/ F: include/uapi/linux/sunrpc/ F: net/sunrpc/ diff --git a/Makefile b/Makefile index bc4adb561a7c..e13df565a1cb 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 80 +SUBLEVEL = 81 EXTRAVERSION = NAME = Curry Ramen

diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi index ec476b159649..b236d23f8071 100644 --- a/arch/arm/boot/dts/imx23.dtsi +++ b/arch/arm/boot/dts/imx23.dtsi @@ -59,7 +59,7 @@ icoll: interrupt-controller@80000000 { reg = <0x80000000 0x2000>; };

- dma_apbh: dma-apbh@80004000 { + dma_apbh: dma-controller@80004000 { compatible = "fsl,imx23-dma-apbh"; reg = <0x80004000 0x2000>; interrupts = <0 14 20 0 diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index b15df16ecb01..b81592a61311 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -78,7 +78,7 @@ hsadc: hsadc@80002000 { status = "disabled"; };

- dma_apbh: dma-apbh@80004000 { + dma_apbh: dma-controller@80004000 { compatible = "fsl,imx28-dma-apbh"; reg = <0x80004000 0x2000>; interrupts = <82 83 84 85 diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index ff1e0173b39b..2c6eada01d79 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -150,7 +150,7 @@ soc: soc { interrupt-parent = <&gpc>; ranges;

- dma_apbh: dma-apbh@110000 { + dma_apbh: dma-controller@110000 { compatible = "fsl,imx6q-dma-apbh", "fsl,imx28-dma-apbh"; reg = <0x00110000 0x2000>; interrupts = <0 13 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 1f1053a898fb..67d344ae76b5 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -209,7 +209,7 @@ gpu: gpu@1800000 { power-domains = <&pd_pu>; };

- dma_apbh: dma-apbh@1804000 { + dma_apbh: dma-controller@1804000 { compatible = "fsl,imx6sx-dma-apbh", "fsl,imx28-dma-apbh"; reg = <0x01804000 0x2000>; interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi index 2b5996395701..aac081b6daaa 100644 --- a/arch/arm/boot/dts/imx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul.dtsi @@ -164,7 +164,7 @@ intc: interrupt-controller@a01000 { <0x00a06000 0x2000>; };

- dma_apbh: dma-apbh@1804000 { + dma_apbh: dma-controller@1804000 { compatible = "fsl,imx6q-dma-apbh", "fsl,imx28-dma-apbh"; reg = <0x01804000 0x2000>; interrupts = <0 13 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 4b23630fc738..69aebc691526 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -1267,14 +1267,13 @@ fec1: ethernet@30be0000 { }; };

- dma_apbh: dma-apbh@33000000 { + dma_apbh: dma-controller@33000000 { compatible = "fsl,imx7d-dma-apbh", "fsl,imx28-dma-apbh"; reg = <0x33000000 0x2000>; interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "gpmi0", "gpmi1", "gpmi2", "gpmi3"; #dma-cells = <1>; dma-channels = <4>; clocks = <&clks IMX7D_NAND_USDHC_BUS_RAWNAND_CLK>; diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index bac4cabef607..467ac2f768ac 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -227,8 +227,19 @@ static int ctr_encrypt(struct skcipher_request *req) src += blocks * AES_BLOCK_SIZE; } if (nbytes && walk.nbytes == walk.total) { + u8 buf[AES_BLOCK_SIZE]; + u8 *d = dst; + + if (unlikely(nbytes < AES_BLOCK_SIZE)) + src = dst = memcpy(buf + sizeof(buf) - nbytes, + src, nbytes); + neon_aes_ctr_encrypt(dst, src, ctx->enc, ctx->key.rounds, nbytes, walk.iv); + + if (unlikely(nbytes < AES_BLOCK_SIZE)) + memcpy(d, dst, nbytes); + nbytes = 0; } kernel_neon_end(); diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 62c846be2d76..a75c0772ecfc 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -103,6 +103,7 @@ static inline void free_screen_info(struct screen_info *si) }

#define EFI_ALLOC_ALIGN SZ_64K +#define EFI_ALLOC_LIMIT ((1UL << 48) - 1)

/* * On ARM systems, virtually remapped UEFI runtime services are set up in two diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 97b026130c71..1e5f083cdb72 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -569,29 +569,6 @@ static void iommu_table_setparms(struct pci_controller *phb,

struct iommu_table_ops iommu_table_lpar_multi_ops;

-/* - * iommu_table_setparms_lpar - * - * Function: On pSeries LPAR systems, return TCE table info, given a pci bus. - */ -static void iommu_table_setparms_lpar(struct pci_controller *phb, - struct device_node *dn, - struct iommu_table *tbl, - struct iommu_table_group *table_group, - const __be32 *dma_window) -{ - unsigned long offset, size, liobn; - - of_parse_dma_window(dn, dma_window, &liobn, &offset, &size); - - iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL, - &iommu_table_lpar_multi_ops); - - - table_group->tce32_start = offset; - table_group->tce32_size = size; -} - struct iommu_table_ops iommu_table_pseries_ops = { .set = tce_build_pSeries, .clear = tce_free_pSeries, @@ -719,26 +696,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = { * dynamic 64bit DMA window, walking up the device tree. */ static struct device_node *pci_dma_find(struct device_node *dn, - const __be32 **dma_window) + struct dynamic_dma_window_prop *prop) { - const __be32 *dw = NULL; + const __be32 *default_prop = NULL; + const __be32 *ddw_prop = NULL; + struct device_node *rdn = NULL; + bool default_win = false, ddw_win = false;

for ( ; dn && PCI_DN(dn); dn = dn->parent) { - dw = of_get_property(dn, "ibm,dma-window", NULL); - if (dw) { - if (dma_window) - *dma_window = dw; - return dn; + default_prop = of_get_property(dn, "ibm,dma-window", NULL); + if (default_prop) { + rdn = dn; + default_win = true; + } + ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; + } + ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; } - dw = of_get_property(dn, DIRECT64_PROPNAME, NULL); - if (dw) - return dn; - dw = of_get_property(dn, DMA64_PROPNAME, NULL); - if (dw) - return dn; + + /* At least found default window, which is the case for normal boot */ + if (default_win) + break; }

- return NULL; + /* For PCI devices there will always be a DMA window, either on the device + * or parent bus + */ + WARN_ON(!(default_win | ddw_win)); + + /* caller doesn't want to get DMA window property */ + if (!prop) + return rdn; + + /* parse DMA window property. During normal system boot, only default + * DMA window is passed in OF. But, for kdump, a dedicated adapter might + * have both default and DDW in FDT. In this scenario, DDW takes precedence + * over default window. + */ + if (ddw_win) { + struct dynamic_dma_window_prop *p; + + p = (struct dynamic_dma_window_prop *)ddw_prop; + prop->liobn = p->liobn; + prop->dma_base = p->dma_base; + prop->tce_shift = p->tce_shift; + prop->window_shift = p->window_shift; + } else if (default_win) { + unsigned long offset, size, liobn; + + of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size); + + prop->liobn = cpu_to_be32((u32)liobn); + prop->dma_base = cpu_to_be64(offset); + prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K); + prop->window_shift = cpu_to_be32(order_base_2(size)); + } + + return rdn; }

static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) @@ -746,17 +768,20 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) struct iommu_table *tbl; struct device_node *dn, *pdn; struct pci_dn *ppci; - const __be32 *dma_window = NULL; + struct dynamic_dma_window_prop prop;

dn = pci_bus_to_OF_node(bus);

pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn);

- pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop);

- if (dma_window == NULL) - pr_debug(" no ibm,dma-window property !\n"); + /* In PPC architecture, there will always be DMA window on bus or one of the + * parent bus. During reboot, there will be ibm,dma-window property to + * define DMA window. For kdump, there will at least be default window or DDW + * or both. + */

ppci = PCI_DN(pdn);

@@ -766,13 +791,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); tbl = ppci->table_group->tables[0]; - if (dma_window) { - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, - ppci->table_group, dma_window);

- if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) - panic("Failed to initialize iommu table"); - } + iommu_table_setparms_common(tbl, ppci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); + + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -960,6 +996,12 @@ static void find_existing_ddw_windows_named(const char *name) continue; }

+ /* If at the time of system initialization, there are DDWs in OF, + * it means this is during kexec. DDW could be direct or dynamic. + * We will just mark DDWs as "dynamic" since this is kdump path, + * no need to worry about perforance. ddw_list_new_entry() will + * set window->direct = false. + */ window = ddw_list_new_entry(pdn, dma64); if (!window) { of_node_put(pdn); @@ -1525,8 +1567,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) { struct device_node *pdn, *dn; struct iommu_table *tbl; - const __be32 *dma_window = NULL; struct pci_dn *pci; + struct dynamic_dma_window_prop prop;

pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));

@@ -1539,7 +1581,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); pr_debug(" node is %pOF\n", dn);

- pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n", @@ -1552,8 +1594,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pci->table_group) { pci->table_group = iommu_pseries_alloc_group(pci->phb->node); tbl = pci->table_group->tables[0]; - iommu_table_setparms_lpar(pci->phb, pdn, tbl, - pci->table_group, dma_window); + + iommu_table_setparms_common(tbl, pci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + pci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);

iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index d47d87c2d7e3..dcf1bc9de584 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -25,6 +25,11 @@

#define ARCH_SUPPORTS_FTRACE_OPS 1 #ifndef __ASSEMBLY__ + +extern void *return_address(unsigned int level); + +#define ftrace_return_address(n) return_address(n) + void MCOUNT_NAME(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 59bb53da473d..63055c6ad2c2 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -79,7 +79,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START) +#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT))

#define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index ab333cb792fd..4c0805d264ca 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) @@ -41,6 +42,7 @@ obj-y += irq.o obj-y += process.o obj-y += ptrace.o obj-y += reset.o +obj-y += return_address.o obj-y += setup.o obj-y += signal.o obj-y += syscall_table.o diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c new file mode 100644 index 000000000000..c8115ec8fb30 --- /dev/null +++ b/arch/riscv/kernel/return_address.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code come from arch/arm64/kernel/return_address.c + * + * Copyright (C) 2023 SiFive. + */ + +#include <linux/export.h> +#include <linux/kprobes.h> +#include <linux/stacktrace.h> + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static bool save_return_addr(void *d, unsigned long pc) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)pc; + return false; + } + + --data->level; + + return true; +} +NOKPROBE_SYMBOL(save_return_addr); + +noinline void *return_address(unsigned int level) +{ + struct return_address_data data; + + data.level = level + 3; + data.addr = NULL; + + arch_stack_walk(save_return_addr, &data, current, NULL); + + if (!data.level) + return data.addr; + else + return NULL; + +} +EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4c9bfc4be58d..2f7af61b49b6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1982,6 +1982,23 @@ config EFI_STUB

See Documentation/admin-guide/efi-stub.rst for more information.

+config EFI_HANDOVER_PROTOCOL + bool "EFI handover protocol (DEPRECATED)" + depends on EFI_STUB + default y + help + Select this in order to include support for the deprecated EFI + handover protocol, which defines alternative entry points into the + EFI stub. This is a practice that has no basis in the UEFI + specification, and requires a priori knowledge on the part of the + bootloader about Linux/x86 specific ways of passing the command line + and initrd, and where in memory those assets may be loaded. + + If in doubt, say Y. Even though the corresponding support is not + present in upstream GRUB or other bootloaders, most distros build + GRUB with numerous downstream patches applied, and may rely on the + handover protocol as as result. + config EFI_MIXED bool "EFI mixed-mode support" depends on EFI_STUB && X86_64 diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 15b7b403a4bd..3965b2c9efee 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -74,6 +74,11 @@ LDFLAGS_vmlinux += -z noexecstack ifeq ($(CONFIG_LD_IS_BFD),y) LDFLAGS_vmlinux += $(call ld-option,--no-warn-rwx-segments) endif +ifeq ($(CONFIG_EFI_STUB),y) +# ensure that the static EFI stub library will be pulled in, even if it is +# never referenced explicitly from the startup code +LDFLAGS_vmlinux += -u efi_pe_entry +endif LDFLAGS_vmlinux += -T

hostprogs := mkpiggy @@ -100,7 +105,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/ident_map_64.o vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o - vmlinux-objs-y += $(obj)/mem_encrypt.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o endif @@ -108,11 +113,11 @@ endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o

-vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o -efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o +vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a

-$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) FORCE $(call if_changed,ld)

OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 9caf89063e77..55c98fdd67d2 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -30,13 +30,13 @@ __efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len) * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to * ACPI_TABLE_GUID because it has more features. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_20_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr;

/* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; @@ -56,15 +56,15 @@ static acpi_physical_address efi_get_rsdp_addr(void) enum efi_type et; int ret;

- et = efi_get_type(boot_params); + et = efi_get_type(boot_params_ptr); if (et == EFI_TYPE_NONE) return 0;

- systab_pa = efi_get_system_table(boot_params); + systab_pa = efi_get_system_table(boot_params_ptr); if (!systab_pa) error("EFI support advertised, but unable to locate system table.");

- ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len); + ret = efi_get_conf_table(boot_params_ptr, &cfg_tbl_pa, &cfg_tbl_len); if (ret || !cfg_tbl_pa) error("EFI config table not found.");

@@ -156,7 +156,7 @@ acpi_physical_address get_rsdp_addr(void) { acpi_physical_address pa;

- pa = boot_params->acpi_rsdp_addr; + pa = boot_params_ptr->acpi_rsdp_addr;

if (!pa) pa = efi_get_rsdp_addr(); @@ -210,7 +210,7 @@ static unsigned long get_acpi_srat_table(void) rsdp = (struct acpi_table_rsdp *)get_cmdline_acpi_rsdp(); if (!rsdp) rsdp = (struct acpi_table_rsdp *)(long) - boot_params->acpi_rsdp_addr; + boot_params_ptr->acpi_rsdp_addr;

if (!rsdp) return 0; diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index f1add5d85da9..c1bb180973ea 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -14,9 +14,9 @@ static inline char rdfs8(addr_t addr) #include "../cmdline.c" unsigned long get_cmd_line_ptr(void) { - unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; + unsigned long cmd_line_ptr = boot_params_ptr->hdr.cmd_line_ptr;

- cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32; + cmd_line_ptr |= (u64)boot_params_ptr->ext_cmd_line_ptr << 32;

return cmd_line_ptr; } diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S new file mode 100644 index 000000000000..8232c5b2a9bf --- /dev/null +++ b/arch/x86/boot/compressed/efi_mixed.S @@ -0,0 +1,328 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming + * + * Early support for invoking 32-bit EFI services from a 64-bit kernel. + * + * Because this thunking occurs before ExitBootServices() we have to + * restore the firmware's 32-bit GDT and IDT before we make EFI service + * calls. + * + * On the plus side, we don't have to worry about mangling 64-bit + * addresses into 32-bits because we're executing with an identity + * mapped pagetable and haven't transitioned to 64-bit virtual addresses + * yet. + */ + +#include <linux/linkage.h> +#include <asm/msr.h> +#include <asm/page_types.h> +#include <asm/processor-flags.h> +#include <asm/segment.h> + + .code64 + .text +/* + * When booting in 64-bit mode on 32-bit EFI firmware, startup_64_mixed_mode() + * is the first thing that runs after switching to long mode. Depending on + * whether the EFI handover protocol or the compat entry point was used to + * enter the kernel, it will either branch to the common 64-bit EFI stub + * entrypoint efi_stub_entry() directly, or via the 64-bit EFI PE/COFF + * entrypoint efi_pe_entry(). In the former case, the bootloader must provide a + * struct bootparams pointer as the third argument, so the presence of such a + * pointer is used to disambiguate. + * + * +--------------+ + * +------------------+ +------------+ +------>| efi_pe_entry | + * | efi32_pe_entry |---->| | | +-----------+--+ + * +------------------+ | | +------+----------------+ | + * | startup_32 |---->| startup_64_mixed_mode | | + * +------------------+ | | +------+----------------+ | + * | efi32_stub_entry |---->| | | | + * +------------------+ +------------+ | | + * V | + * +------------+ +----------------+ | + * | startup_64 |<----| efi_stub_entry |<--------+ + * +------------+ +----------------+ + */ +SYM_FUNC_START(startup_64_mixed_mode) + lea efi32_boot_args(%rip), %rdx + mov 0(%rdx), %edi + mov 4(%rdx), %esi +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL + mov 8(%rdx), %edx // saved bootparams pointer + test %edx, %edx + jnz efi_stub_entry +#endif + /* + * efi_pe_entry uses MS calling convention, which requires 32 bytes of + * shadow space on the stack even if all arguments are passed in + * registers. We also need an additional 8 bytes for the space that + * would be occupied by the return address, and this also results in + * the correct stack alignment for entry. + */ + sub $40, %rsp + mov %rdi, %rcx // MS calling convention + mov %rsi, %rdx + jmp efi_pe_entry +SYM_FUNC_END(startup_64_mixed_mode) + +SYM_FUNC_START(__efi64_thunk) + push %rbp + push %rbx + + movl %ds, %eax + push %rax + movl %es, %eax + push %rax + movl %ss, %eax + push %rax + + /* Copy args passed on stack */ + movq 0x30(%rsp), %rbp + movq 0x38(%rsp), %rbx + movq 0x40(%rsp), %rax + + /* + * Convert x86-64 ABI params to i386 ABI + */ + subq $64, %rsp + movl %esi, 0x0(%rsp) + movl %edx, 0x4(%rsp) + movl %ecx, 0x8(%rsp) + movl %r8d, 0xc(%rsp) + movl %r9d, 0x10(%rsp) + movl %ebp, 0x14(%rsp) + movl %ebx, 0x18(%rsp) + movl %eax, 0x1c(%rsp) + + leaq 0x20(%rsp), %rbx + sgdt (%rbx) + sidt 16(%rbx) + + leaq 1f(%rip), %rbp + + /* + * Switch to IDT and GDT with 32-bit segments. These are the firmware + * GDT and IDT that were installed when the kernel started executing. + * The pointers were saved by the efi32_entry() routine below. + * + * Pass the saved DS selector to the 32-bit code, and use far return to + * restore the saved CS selector. + */ + lidt efi32_boot_idt(%rip) + lgdt efi32_boot_gdt(%rip) + + movzwl efi32_boot_ds(%rip), %edx + movzwq efi32_boot_cs(%rip), %rax + pushq %rax + leaq efi_enter32(%rip), %rax + pushq %rax + lretq + +1: addq $64, %rsp + movq %rdi, %rax + + pop %rbx + movl %ebx, %ss + pop %rbx + movl %ebx, %es + pop %rbx + movl %ebx, %ds + /* Clear out 32-bit selector from FS and GS */ + xorl %ebx, %ebx + movl %ebx, %fs + movl %ebx, %gs + + /* + * Convert 32-bit status code into 64-bit. + */ + roll $1, %eax + rorq $1, %rax + + pop %rbx + pop %rbp + RET +SYM_FUNC_END(__efi64_thunk) + + .code32 +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL +SYM_FUNC_START(efi32_stub_entry) + call 1f +1: popl %ecx + + /* Clear BSS */ + xorl %eax, %eax + leal (_bss - 1b)(%ecx), %edi + leal (_ebss - 1b)(%ecx), %ecx + subl %edi, %ecx + shrl $2, %ecx + cld + rep stosl + + add $0x4, %esp /* Discard return address */ + popl %ecx + popl %edx + popl %esi + jmp efi32_entry +SYM_FUNC_END(efi32_stub_entry) +#endif + +/* + * EFI service pointer must be in %edi. + * + * The stack should represent the 32-bit calling convention. + */ +SYM_FUNC_START_LOCAL(efi_enter32) + /* Load firmware selector into data and stack segment registers */ + movl %edx, %ds + movl %edx, %es + movl %edx, %fs + movl %edx, %gs + movl %edx, %ss + + /* Reload pgtables */ + movl %cr3, %eax + movl %eax, %cr3 + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Disable long mode via EFER */ + movl $MSR_EFER, %ecx + rdmsr + btrl $_EFER_LME, %eax + wrmsr + + call *%edi + + /* We must preserve return value */ + movl %eax, %edi + + /* + * Some firmware will return with interrupts enabled. Be sure to + * disable them before we switch GDTs and IDTs. + */ + cli + + lidtl 16(%ebx) + lgdtl (%ebx) + + movl %cr4, %eax + btsl $(X86_CR4_PAE_BIT), %eax + movl %eax, %cr4 + + movl %cr3, %eax + movl %eax, %cr3 + + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + + xorl %eax, %eax + lldt %ax + + pushl $__KERNEL_CS + pushl %ebp + + /* Enable paging */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + lret +SYM_FUNC_END(efi_enter32) + +/* + * This is the common EFI stub entry point for mixed mode. + * + * Arguments: %ecx image handle + * %edx EFI system table pointer + * %esi struct bootparams pointer (or NULL when not using + * the EFI handover protocol) + * + * Since this is the point of no return for ordinary execution, no registers + * are considered live except for the function parameters. [Note that the EFI + * stub may still exit and return to the firmware using the Exit() EFI boot + * service.] + */ +SYM_FUNC_START_LOCAL(efi32_entry) + call 1f +1: pop %ebx + + /* Save firmware GDTR and code/data selectors */ + sgdtl (efi32_boot_gdt - 1b)(%ebx) + movw %cs, (efi32_boot_cs - 1b)(%ebx) + movw %ds, (efi32_boot_ds - 1b)(%ebx) + + /* Store firmware IDT descriptor */ + sidtl (efi32_boot_idt - 1b)(%ebx) + + /* Store boot arguments */ + leal (efi32_boot_args - 1b)(%ebx), %ebx + movl %ecx, 0(%ebx) + movl %edx, 4(%ebx) + movl %esi, 8(%ebx) + movb $0x0, 12(%ebx) // efi_is64 + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + jmp startup_32 +SYM_FUNC_END(efi32_entry) + +/* + * efi_status_t efi32_pe_entry(efi_handle_t image_handle, + * efi_system_table_32_t *sys_table) + */ +SYM_FUNC_START(efi32_pe_entry) + pushl %ebp + movl %esp, %ebp + pushl %ebx // save callee-save registers + pushl %edi + + call verify_cpu // check for long mode support + testl %eax, %eax + movl $0x80000003, %eax // EFI_UNSUPPORTED + jnz 2f + + movl 8(%ebp), %ecx // image_handle + movl 12(%ebp), %edx // sys_table + xorl %esi, %esi + jmp efi32_entry // pass %ecx, %edx, %esi + // no other registers remain live + +2: popl %edi // restore callee-save registers + popl %ebx + leave + RET +SYM_FUNC_END(efi32_pe_entry) + +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL + .org efi32_stub_entry + 0x200 + .code64 +SYM_FUNC_START_NOALIGN(efi64_stub_entry) + jmp efi_handover_entry +SYM_FUNC_END(efi64_stub_entry) +#endif + + .data + .balign 8 +SYM_DATA_START_LOCAL(efi32_boot_gdt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_gdt) + +SYM_DATA_START_LOCAL(efi32_boot_idt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_idt) + +SYM_DATA_LOCAL(efi32_boot_cs, .word 0) +SYM_DATA_LOCAL(efi32_boot_ds, .word 0) +SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) +SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S deleted file mode 100644 index 67e7edcdfea8..000000000000 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ /dev/null @@ -1,195 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming - * - * Early support for invoking 32-bit EFI services from a 64-bit kernel. - * - * Because this thunking occurs before ExitBootServices() we have to - * restore the firmware's 32-bit GDT and IDT before we make EFI service - * calls. - * - * On the plus side, we don't have to worry about mangling 64-bit - * addresses into 32-bits because we're executing with an identity - * mapped pagetable and haven't transitioned to 64-bit virtual addresses - * yet. - */ - -#include <linux/linkage.h> -#include <asm/msr.h> -#include <asm/page_types.h> -#include <asm/processor-flags.h> -#include <asm/segment.h> - - .code64 - .text -SYM_FUNC_START(__efi64_thunk) - push %rbp - push %rbx - - movl %ds, %eax - push %rax - movl %es, %eax - push %rax - movl %ss, %eax - push %rax - - /* Copy args passed on stack */ - movq 0x30(%rsp), %rbp - movq 0x38(%rsp), %rbx - movq 0x40(%rsp), %rax - - /* - * Convert x86-64 ABI params to i386 ABI - */ - subq $64, %rsp - movl %esi, 0x0(%rsp) - movl %edx, 0x4(%rsp) - movl %ecx, 0x8(%rsp) - movl %r8d, 0xc(%rsp) - movl %r9d, 0x10(%rsp) - movl %ebp, 0x14(%rsp) - movl %ebx, 0x18(%rsp) - movl %eax, 0x1c(%rsp) - - leaq 0x20(%rsp), %rbx - sgdt (%rbx) - - addq $16, %rbx - sidt (%rbx) - - leaq 1f(%rip), %rbp - - /* - * Switch to IDT and GDT with 32-bit segments. This is the firmware GDT - * and IDT that was installed when the kernel started executing. The - * pointers were saved at the EFI stub entry point in head_64.S. - * - * Pass the saved DS selector to the 32-bit code, and use far return to - * restore the saved CS selector. - */ - leaq efi32_boot_idt(%rip), %rax - lidt (%rax) - leaq efi32_boot_gdt(%rip), %rax - lgdt (%rax) - - movzwl efi32_boot_ds(%rip), %edx - movzwq efi32_boot_cs(%rip), %rax - pushq %rax - leaq efi_enter32(%rip), %rax - pushq %rax - lretq - -1: addq $64, %rsp - movq %rdi, %rax - - pop %rbx - movl %ebx, %ss - pop %rbx - movl %ebx, %es - pop %rbx - movl %ebx, %ds - /* Clear out 32-bit selector from FS and GS */ - xorl %ebx, %ebx - movl %ebx, %fs - movl %ebx, %gs - - /* - * Convert 32-bit status code into 64-bit. - */ - roll $1, %eax - rorq $1, %rax - - pop %rbx - pop %rbp - RET -SYM_FUNC_END(__efi64_thunk) - - .code32 -/* - * EFI service pointer must be in %edi. - * - * The stack should represent the 32-bit calling convention. - */ -SYM_FUNC_START_LOCAL(efi_enter32) - /* Load firmware selector into data and stack segment registers */ - movl %edx, %ds - movl %edx, %es - movl %edx, %fs - movl %edx, %gs - movl %edx, %ss - - /* Reload pgtables */ - movl %cr3, %eax - movl %eax, %cr3 - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - /* Disable long mode via EFER */ - movl $MSR_EFER, %ecx - rdmsr - btrl $_EFER_LME, %eax - wrmsr - - call *%edi - - /* We must preserve return value */ - movl %eax, %edi - - /* - * Some firmware will return with interrupts enabled. Be sure to - * disable them before we switch GDTs and IDTs. - */ - cli - - lidtl (%ebx) - subl $16, %ebx - - lgdtl (%ebx) - - movl %cr4, %eax - btsl $(X86_CR4_PAE_BIT), %eax - movl %eax, %cr4 - - movl %cr3, %eax - movl %eax, %cr3 - - movl $MSR_EFER, %ecx - rdmsr - btsl $_EFER_LME, %eax - wrmsr - - xorl %eax, %eax - lldt %ax - - pushl $__KERNEL_CS - pushl %ebp - - /* Enable paging */ - movl %cr0, %eax - btsl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - lret -SYM_FUNC_END(efi_enter32) - - .data - .balign 8 -SYM_DATA_START(efi32_boot_gdt) - .word 0 - .quad 0 -SYM_DATA_END(efi32_boot_gdt) - -SYM_DATA_START(efi32_boot_idt) - .word 0 - .quad 0 -SYM_DATA_END(efi32_boot_idt) - -SYM_DATA_START(efi32_boot_cs) - .word 0 -SYM_DATA_END(efi32_boot_cs) - -SYM_DATA_START(efi32_boot_ds) - .word 0 -SYM_DATA_END(efi32_boot_ds) diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 3b354eb9516d..1cfe9802a42f 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -84,19 +84,6 @@ SYM_FUNC_START(startup_32)

#ifdef CONFIG_RELOCATABLE leal startup_32@GOTOFF(%edx), %ebx - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32() will be at an - * offset to the start of the space allocated for the image. efi_pe_entry() will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - subl image_offset@GOTOFF(%edx), %ebx -#endif - movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx @@ -150,17 +137,6 @@ SYM_FUNC_START(startup_32) jmp *%eax SYM_FUNC_END(startup_32)

-#ifdef CONFIG_EFI_STUB -SYM_FUNC_START(efi32_stub_entry) - add $0x4, %esp - movl 8(%esp), %esi /* save boot_params pointer */ - call efi_main - /* efi_main returns the possibly relocated address of startup_32 */ - jmp *%eax -SYM_FUNC_END(efi32_stub_entry) -SYM_FUNC_ALIAS(efi_stub_entry, efi32_stub_entry) -#endif - .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)

@@ -179,15 +155,9 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) */ /* push arguments for extract_kernel: */

- pushl output_len@GOTOFF(%ebx) /* decompressed length, end of relocs */ pushl %ebp /* output address */ - pushl input_len@GOTOFF(%ebx) /* input_len */ - leal input_data@GOTOFF(%ebx), %eax - pushl %eax /* input_data */ - leal boot_heap@GOTOFF(%ebx), %eax - pushl %eax /* heap area */ pushl %esi /* real mode pointer */ - call extract_kernel /* returns kernel location in %eax */ + call extract_kernel /* returns kernel entry point in %eax */ addl $24, %esp

/* @@ -208,17 +178,11 @@ SYM_DATA_START_LOCAL(gdt) .quad 0x00cf92000000ffff /* __KERNEL_DS */ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)

-#ifdef CONFIG_EFI_STUB -SYM_DATA(image_offset, .long 0) -#endif - /* * Stack and heap for uncompression */ .bss .balign 4 -boot_heap: - .fill BOOT_HEAP_SIZE, 1, 0 boot_stack: .fill BOOT_STACK_SIZE, 1, 0 boot_stack_end: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index b4bd6df29116..0d7aef10b19a 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -118,7 +118,9 @@ SYM_FUNC_START(startup_32) 1:

/* Setup Exception handling for SEV-ES */ +#ifdef CONFIG_AMD_MEM_ENCRYPT call startup32_load_idt +#endif

/* Make sure cpu supports long mode. */ call verify_cpu @@ -136,19 +138,6 @@ SYM_FUNC_START(startup_32)

#ifdef CONFIG_RELOCATABLE movl %ebp, %ebx - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32 will be at an - * offset to the start of the space allocated for the image. efi_pe_entry will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - subl rva(image_offset)(%ebp), %ebx -#endif - movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx @@ -178,12 +167,13 @@ SYM_FUNC_START(startup_32) */ /* * If SEV is active then set the encryption mask in the page tables. - * This will insure that when the kernel is copied and decompressed + * This will ensure that when the kernel is copied and decompressed * it will be done so encrypted. */ - call get_sev_encryption_bit xorl %edx, %edx #ifdef CONFIG_AMD_MEM_ENCRYPT + call get_sev_encryption_bit + xorl %edx, %edx testl %eax, %eax jz 1f subl $32, %eax /* Encryption bit is always above bit 31 */ @@ -249,6 +239,11 @@ SYM_FUNC_START(startup_32) movl $__BOOT_TSS, %eax ltr %ax

+#ifdef CONFIG_AMD_MEM_ENCRYPT + /* Check if the C-bit position is correct when SEV is active */ + call startup32_check_sev_cbit +#endif + /* * Setup for the jump to 64bit mode * @@ -261,29 +256,11 @@ SYM_FUNC_START(startup_32) */ leal rva(startup_64)(%ebp), %eax #ifdef CONFIG_EFI_MIXED - movl rva(efi32_boot_args)(%ebp), %edi - testl %edi, %edi - jz 1f - leal rva(efi64_stub_entry)(%ebp), %eax - movl rva(efi32_boot_args+4)(%ebp), %esi - movl rva(efi32_boot_args+8)(%ebp), %edx // saved bootparams pointer - testl %edx, %edx - jnz 1f - /* - * efi_pe_entry uses MS calling convention, which requires 32 bytes of - * shadow space on the stack even if all arguments are passed in - * registers. We also need an additional 8 bytes for the space that - * would be occupied by the return address, and this also results in - * the correct stack alignment for entry. - */ - subl $40, %esp - leal rva(efi_pe_entry)(%ebp), %eax - movl %edi, %ecx // MS calling convention - movl %esi, %edx + cmpb $1, rva(efi_is64)(%ebp) + je 1f + leal rva(startup_64_mixed_mode)(%ebp), %eax 1: #endif - /* Check if the C-bit position is correct when SEV is active */ - call startup32_check_sev_cbit

pushl $__KERNEL_CS pushl %eax @@ -296,41 +273,6 @@ SYM_FUNC_START(startup_32) lret SYM_FUNC_END(startup_32)

-#ifdef CONFIG_EFI_MIXED - .org 0x190 -SYM_FUNC_START(efi32_stub_entry) - add $0x4, %esp /* Discard return address */ - popl %ecx - popl %edx - popl %esi - - call 1f -1: pop %ebp - subl $ rva(1b), %ebp - - movl %esi, rva(efi32_boot_args+8)(%ebp) -SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL) - movl %ecx, rva(efi32_boot_args)(%ebp) - movl %edx, rva(efi32_boot_args+4)(%ebp) - movb $0, rva(efi_is64)(%ebp) - - /* Save firmware GDTR and code/data selectors */ - sgdtl rva(efi32_boot_gdt)(%ebp) - movw %cs, rva(efi32_boot_cs)(%ebp) - movw %ds, rva(efi32_boot_ds)(%ebp) - - /* Store firmware IDT descriptor */ - sidtl rva(efi32_boot_idt)(%ebp) - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - jmp startup_32 -SYM_FUNC_END(efi32_stub_entry) -#endif - .code64 .org 0x200 SYM_CODE_START(startup_64) @@ -372,20 +314,6 @@ SYM_CODE_START(startup_64) /* Start with the delta to where the kernel will run at. */ #ifdef CONFIG_RELOCATABLE leaq startup_32(%rip) /* - $startup_32 */, %rbp - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32 will be at an - * offset to the start of the space allocated for the image. efi_pe_entry will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - movl image_offset(%rip), %eax - subq %rax, %rbp -#endif - movl BP_kernel_alignment(%rsi), %eax decl %eax addq %rax, %rbp @@ -424,10 +352,6 @@ SYM_CODE_START(startup_64) * For the trampoline, we need the top page table to reside in lower * memory as we don't have a way to load 64-bit values into CR3 in * 32-bit mode. - * - * We go though the trampoline even if we don't have to: if we're - * already in a desired paging mode. This way the trampoline code gets - * tested on every boot. */

/* Make sure we have GDT with 32-bit code segment */ @@ -442,10 +366,14 @@ SYM_CODE_START(startup_64) lretq

.Lon_kernel_cs: + /* + * RSI holds a pointer to a boot_params structure provided by the + * loader, and this needs to be preserved across C function calls. So + * move it into a callee saved register. + */ + movq %rsi, %r15

- pushq %rsi call load_stage1_idt - popq %rsi

#ifdef CONFIG_AMD_MEM_ENCRYPT /* @@ -456,82 +384,24 @@ SYM_CODE_START(startup_64) * CPUID instructions being issued, so go ahead and do that now via * sev_enable(), which will also handle the rest of the SEV-related * detection/setup to ensure that has been done in advance of any dependent - * code. + * code. Pass the boot_params pointer as the first argument. */ - pushq %rsi - movq %rsi, %rdi /* real mode address */ + movq %r15, %rdi call sev_enable - popq %rsi #endif

/* - * paging_prepare() sets up the trampoline and checks if we need to - * enable 5-level paging. - * - * paging_prepare() returns a two-quadword structure which lands - * into RDX:RAX: - * - Address of the trampoline is returned in RAX. - * - Non zero RDX means trampoline needs to enable 5-level - * paging. - * - * RSI holds real mode data and needs to be preserved across - * this function call. - */ - pushq %rsi - movq %rsi, %rdi /* real mode address */ - call paging_prepare - popq %rsi - - /* Save the trampoline address in RCX */ - movq %rax, %rcx - - /* Set up 32-bit addressable stack */ - leaq TRAMPOLINE_32BIT_STACK_END(%rcx), %rsp - - /* - * Preserve live 64-bit registers on the stack: this is necessary - * because the architecture does not guarantee that GPRs will retain - * their full 64-bit values across a 32-bit mode switch. - */ - pushq %rbp - pushq %rbx - pushq %rsi - - /* - * Push the 64-bit address of trampoline_return() onto the new stack. - * It will be used by the trampoline to return to the main code. Due to - * the 32-bit mode switch, it cannot be kept it in a register either. - */ - leaq trampoline_return(%rip), %rdi - pushq %rdi - - /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ - pushq $__KERNEL32_CS - leaq TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax - pushq %rax - lretq -trampoline_return: - /* Restore live 64-bit registers */ - popq %rsi - popq %rbx - popq %rbp - - /* Restore the stack, the 32-bit trampoline uses its own stack */ - leaq rva(boot_stack_end)(%rbx), %rsp - - /* - * cleanup_trampoline() would restore trampoline memory. - * - * RDI is address of the page table to use instead of page table - * in trampoline memory (if required). + * configure_5level_paging() updates the number of paging levels using + * a trampoline in 32-bit addressable memory if the current number does + * not match the desired number. * - * RSI holds real mode data and needs to be preserved across - * this function call. + * Pass the boot_params pointer as the first argument. The second + * argument is the relocated address of the page table to use instead + * of the page table in trampoline memory (if required). */ - pushq %rsi - leaq rva(top_pgtable)(%rbx), %rdi - call cleanup_trampoline - popq %rsi + movq %r15, %rdi + leaq rva(top_pgtable)(%rbx), %rsi + call configure_5level_paging

/* Zero EFLAGS */ pushq $0 @@ -541,7 +411,6 @@ trampoline_return: * Copy the compressed kernel to the end of our buffer * where decompression in place becomes safe. */ - pushq %rsi leaq (_bss-8)(%rip), %rsi leaq rva(_bss-8)(%rbx), %rdi movl $(_bss - startup_32), %ecx @@ -549,7 +418,6 @@ trampoline_return: std rep movsq cld - popq %rsi

/* * The GDT may get overwritten either during the copy we just did or @@ -568,19 +436,6 @@ trampoline_return: jmp *%rax SYM_CODE_END(startup_64)

-#ifdef CONFIG_EFI_STUB - .org 0x390 -SYM_FUNC_START(efi64_stub_entry) - and $~0xf, %rsp /* realign the stack */ - movq %rdx, %rbx /* save boot_params pointer */ - call efi_main - movq %rbx,%rsi - leaq rva(startup_64)(%rax), %rax - jmp *%rax -SYM_FUNC_END(efi64_stub_entry) -SYM_FUNC_ALIAS(efi_stub_entry, efi64_stub_entry) -#endif - .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)

@@ -594,125 +449,122 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq $3, %rcx rep stosq

- pushq %rsi call load_stage2_idt

/* Pass boot_params to initialize_identity_maps() */ - movq (%rsp), %rdi + movq %r15, %rdi call initialize_identity_maps - popq %rsi

/* * Do the extraction, and jump to the new kernel.. */ - pushq %rsi /* Save the real mode argument */ - movq %rsi, %rdi /* real mode address */ - leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ - leaq input_data(%rip), %rdx /* input_data */ - movl input_len(%rip), %ecx /* input_len */ - movq %rbp, %r8 /* output target address */ - movl output_len(%rip), %r9d /* decompressed length, end of relocs */ - call extract_kernel /* returns kernel location in %rax */ - popq %rsi + /* pass struct boot_params pointer and output target address */ + movq %r15, %rdi + movq %rbp, %rsi + call extract_kernel /* returns kernel entry point in %rax */

/* * Jump to the decompressed kernel. */ + movq %r15, %rsi jmp *%rax SYM_FUNC_END(.Lrelocated)

- .code32 /* - * This is the 32-bit trampoline that will be copied over to low memory. + * This is the 32-bit trampoline that will be copied over to low memory. It + * will be called using the ordinary 64-bit calling convention from code + * running in 64-bit mode. * * Return address is at the top of the stack (might be above 4G). - * ECX contains the base address of the trampoline memory. - * Non zero RDX means trampoline needs to enable 5-level paging. + * The first argument (EDI) contains the address of the temporary PGD level + * page table in 32-bit addressable memory which will be programmed into + * register CR3. */ + .section ".rodata", "a", @progbits SYM_CODE_START(trampoline_32bit_src) - /* Set up data and stack segments */ - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %ss + /* + * Preserve callee save 64-bit registers on the stack: this is + * necessary because the architecture does not guarantee that GPRs will + * retain their full 64-bit values across a 32-bit mode switch. + */ + pushq %r15 + pushq %r14 + pushq %r13 + pushq %r12 + pushq %rbp + pushq %rbx + + /* Preserve top half of RSP in a legacy mode GPR to avoid truncation */ + movq %rsp, %rbx + shrq $32, %rbx

+ /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ + pushq $__KERNEL32_CS + leaq 0f(%rip), %rax + pushq %rax + lretq + + /* + * The 32-bit code below will do a far jump back to long mode and end + * up here after reconfiguring the number of paging levels. First, the + * stack pointer needs to be restored to its full 64-bit value before + * the callee save register contents can be popped from the stack. + */ +.Lret: + shlq $32, %rbx + orq %rbx, %rsp + + /* Restore the preserved 64-bit registers */ + popq %rbx + popq %rbp + popq %r12 + popq %r13 + popq %r14 + popq %r15 + retq + + .code32 +0: /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax movl %eax, %cr0

- /* Check what paging mode we want to be in after the trampoline */ - testl %edx, %edx - jz 1f - - /* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */ - movl %cr4, %eax - testl $X86_CR4_LA57, %eax - jnz 3f - jmp 2f -1: - /* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */ - movl %cr4, %eax - testl $X86_CR4_LA57, %eax - jz 3f -2: /* Point CR3 to the trampoline's new top level page table */ - leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax - movl %eax, %cr3 -3: + movl %edi, %cr3 + /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ - pushl %ecx - pushl %edx movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax /* Avoid writing EFER if no change was made (for TDX guest) */ jc 1f wrmsr -1: popl %edx - popl %ecx - -#ifdef CONFIG_X86_MCE - /* - * Preserve CR4.MCE if the kernel will enable #MC support. - * Clearing MCE may fault in some environments (that also force #MC - * support). Any machine check that occurs before #MC support is fully - * configured will crash the system regardless of the CR4.MCE value set - * here. - */ - movl %cr4, %eax - andl $X86_CR4_MCE, %eax -#else - movl $0, %eax -#endif - - /* Enable PAE and LA57 (if required) paging modes */ - orl $X86_CR4_PAE, %eax - testl %edx, %edx - jz 1f - orl $X86_CR4_LA57, %eax 1: + /* Toggle CR4.LA57 */ + movl %cr4, %eax + btcl $X86_CR4_LA57_BIT, %eax movl %eax, %cr4

- /* Calculate address of paging_enabled() once we are executing in the trampoline */ - leal .Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax - - /* Prepare the stack for far return to Long Mode */ - pushl $__KERNEL_CS - pushl %eax - /* Enable paging again. */ movl %cr0, %eax btsl $X86_CR0_PG_BIT, %eax movl %eax, %cr0

- lret + /* + * Return to the 64-bit calling code using LJMP rather than LRET, to + * avoid the need for a 32-bit addressable stack. The destination + * address will be adjusted after the template code is copied into a + * 32-bit addressable buffer. + */ +.Ljmp: ljmpl $__KERNEL_CS, $(.Lret - trampoline_32bit_src) SYM_CODE_END(trampoline_32bit_src)

- .code64 -SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled) - /* Return from the trampoline */ - retq -SYM_FUNC_END(.Lpaging_enabled) +/* + * This symbol is placed right after trampoline_32bit_src() so its address can + * be used to infer the size of the trampoline code. + */ +SYM_DATA(trampoline_ljmp_imm_offset, .word .Ljmp + 1 - trampoline_32bit_src)

/* * The trampoline code has a size limit. @@ -721,7 +573,7 @@ SYM_FUNC_END(.Lpaging_enabled) */ .org trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE

- .code32 + .text SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) /* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */ 1: @@ -729,6 +581,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) jmp 1b SYM_FUNC_END(.Lno_longmode)

+ .globl verify_cpu #include "../../kernel/verify_cpu.S"

.data @@ -760,249 +613,11 @@ SYM_DATA_START(boot_idt) .endr SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end)

-#ifdef CONFIG_AMD_MEM_ENCRYPT -SYM_DATA_START(boot32_idt_desc) - .word boot32_idt_end - boot32_idt - 1 - .long 0 -SYM_DATA_END(boot32_idt_desc) - .balign 8 -SYM_DATA_START(boot32_idt) - .rept 32 - .quad 0 - .endr -SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLOBAL, boot32_idt_end) -#endif - -#ifdef CONFIG_EFI_STUB -SYM_DATA(image_offset, .long 0) -#endif -#ifdef CONFIG_EFI_MIXED -SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) -SYM_DATA(efi_is64, .byte 1) - -#define ST32_boottime 60 // offsetof(efi_system_table_32_t, boottime) -#define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol) -#define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base) - - __HEAD - .code32 -SYM_FUNC_START(efi32_pe_entry) -/* - * efi_status_t efi32_pe_entry(efi_handle_t image_handle, - * efi_system_table_32_t *sys_table) - */ - - pushl %ebp - movl %esp, %ebp - pushl %eax // dummy push to allocate loaded_image - - pushl %ebx // save callee-save registers - pushl %edi - - call verify_cpu // check for long mode support - testl %eax, %eax - movl $0x80000003, %eax // EFI_UNSUPPORTED - jnz 2f - - call 1f -1: pop %ebx - subl $ rva(1b), %ebx - - /* Get the loaded image protocol pointer from the image handle */ - leal -4(%ebp), %eax - pushl %eax // &loaded_image - leal rva(loaded_image_proto)(%ebx), %eax - pushl %eax // pass the GUID address - pushl 8(%ebp) // pass the image handle - - /* - * Note the alignment of the stack frame. - * sys_table - * handle <-- 16-byte aligned on entry by ABI - * return address - * frame pointer - * loaded_image <-- local variable - * saved %ebx <-- 16-byte aligned here - * saved %edi - * &loaded_image - * &loaded_image_proto - * handle <-- 16-byte aligned for call to handle_protocol - */ - - movl 12(%ebp), %eax // sys_table - movl ST32_boottime(%eax), %eax // sys_table->boottime - call *BS32_handle_protocol(%eax) // sys_table->boottime->handle_protocol - addl $12, %esp // restore argument space - testl %eax, %eax - jnz 2f - - movl 8(%ebp), %ecx // image_handle - movl 12(%ebp), %edx // sys_table - movl -4(%ebp), %esi // loaded_image - movl LI32_image_base(%esi), %esi // loaded_image->image_base - movl %ebx, %ebp // startup_32 for efi32_pe_stub_entry - /* - * We need to set the image_offset variable here since startup_32() will - * use it before we get to the 64-bit efi_pe_entry() in C code. - */ - subl %esi, %ebx - movl %ebx, rva(image_offset)(%ebp) // save image_offset - jmp efi32_pe_stub_entry - -2: popl %edi // restore callee-save registers - popl %ebx - leave - RET -SYM_FUNC_END(efi32_pe_entry) - - .section ".rodata" - /* EFI loaded image protocol GUID */ - .balign 4 -SYM_DATA_START_LOCAL(loaded_image_proto) - .long 0x5b1b31a1 - .word 0x9562, 0x11d2 - .byte 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b -SYM_DATA_END(loaded_image_proto) -#endif - -#ifdef CONFIG_AMD_MEM_ENCRYPT - __HEAD - .code32 -/* - * Write an IDT entry into boot32_idt - * - * Parameters: - * - * %eax: Handler address - * %edx: Vector number - * - * Physical offset is expected in %ebp - */ -SYM_FUNC_START(startup32_set_idt_entry) - push %ebx - push %ecx - - /* IDT entry address to %ebx */ - leal rva(boot32_idt)(%ebp), %ebx - shl $3, %edx - addl %edx, %ebx - - /* Build IDT entry, lower 4 bytes */ - movl %eax, %edx - andl $0x0000ffff, %edx # Target code segment offset [15:0] - movl $__KERNEL32_CS, %ecx # Target code segment selector - shl $16, %ecx - orl %ecx, %edx - - /* Store lower 4 bytes to IDT */ - movl %edx, (%ebx) - - /* Build IDT entry, upper 4 bytes */ - movl %eax, %edx - andl $0xffff0000, %edx # Target code segment offset [31:16] - orl $0x00008e00, %edx # Present, Type 32-bit Interrupt Gate - - /* Store upper 4 bytes to IDT */ - movl %edx, 4(%ebx) - - pop %ecx - pop %ebx - RET -SYM_FUNC_END(startup32_set_idt_entry) -#endif - -SYM_FUNC_START(startup32_load_idt) -#ifdef CONFIG_AMD_MEM_ENCRYPT - /* #VC handler */ - leal rva(startup32_vc_handler)(%ebp), %eax - movl $X86_TRAP_VC, %edx - call startup32_set_idt_entry - - /* Load IDT */ - leal rva(boot32_idt)(%ebp), %eax - movl %eax, rva(boot32_idt_desc+2)(%ebp) - lidt rva(boot32_idt_desc)(%ebp) -#endif - RET -SYM_FUNC_END(startup32_load_idt) - -/* - * Check for the correct C-bit position when the startup_32 boot-path is used. - * - * The check makes use of the fact that all memory is encrypted when paging is - * disabled. The function creates 64 bits of random data using the RDRAND - * instruction. RDRAND is mandatory for SEV guests, so always available. If the - * hypervisor violates that the kernel will crash right here. - * - * The 64 bits of random data are stored to a memory location and at the same - * time kept in the %eax and %ebx registers. Since encryption is always active - * when paging is off the random data will be stored encrypted in main memory. - * - * Then paging is enabled. When the C-bit position is correct all memory is - * still mapped encrypted and comparing the register values with memory will - * succeed. An incorrect C-bit position will map all memory unencrypted, so that - * the compare will use the encrypted random data and fail. - */ -SYM_FUNC_START(startup32_check_sev_cbit) -#ifdef CONFIG_AMD_MEM_ENCRYPT - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - - /* Check for non-zero sev_status */ - movl rva(sev_status)(%ebp), %eax - testl %eax, %eax - jz 4f - - /* - * Get two 32-bit random values - Don't bail out if RDRAND fails - * because it is better to prevent forward progress if no random value - * can be gathered. - */ -1: rdrand %eax - jnc 1b -2: rdrand %ebx - jnc 2b - - /* Store to memory and keep it in the registers */ - movl %eax, rva(sev_check_data)(%ebp) - movl %ebx, rva(sev_check_data+4)(%ebp) - - /* Enable paging to see if encryption is active */ - movl %cr0, %edx /* Backup %cr0 in %edx */ - movl $(X86_CR0_PG | X86_CR0_PE), %ecx /* Enable Paging and Protected mode */ - movl %ecx, %cr0 - - cmpl %eax, rva(sev_check_data)(%ebp) - jne 3f - cmpl %ebx, rva(sev_check_data+4)(%ebp) - jne 3f - - movl %edx, %cr0 /* Restore previous %cr0 */ - - jmp 4f - -3: /* Check failed - hlt the machine */ - hlt - jmp 3b - -4: - popl %edx - popl %ecx - popl %ebx - popl %eax -#endif - RET -SYM_FUNC_END(startup32_check_sev_cbit) - /* * Stack and heap for uncompression */ .bss .balign 4 -SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) - SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 .balign 16 diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d34222816c9f..b8c42339bc35 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -167,8 +167,9 @@ void initialize_identity_maps(void *rmode) * or does not touch all the pages covering them. */ kernel_add_identity_map((unsigned long)_head, (unsigned long)_end); - boot_params = rmode; - kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + boot_params_ptr = rmode; + kernel_add_identity_map((unsigned long)boot_params_ptr, + (unsigned long)(boot_params_ptr + 1)); cmdline = get_cmd_line_ptr(); kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);

@@ -176,7 +177,7 @@ void initialize_identity_maps(void *rmode) * Also map the setup_data entries passed via boot_params in case they * need to be accessed by uncompressed kernel via the identity mapping. */ - sd = (struct setup_data *)boot_params->hdr.setup_data; + sd = (struct setup_data *)boot_params_ptr->hdr.setup_data; while (sd) { unsigned long sd_addr = (unsigned long)sd;

diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index e476bcbd9b42..9794d9174795 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -63,7 +63,7 @@ static unsigned long get_boot_seed(void) unsigned long hash = 0;

hash = rotate_xor(hash, build_str, sizeof(build_str)); - hash = rotate_xor(hash, boot_params, sizeof(*boot_params)); + hash = rotate_xor(hash, boot_params_ptr, sizeof(*boot_params_ptr));

return hash; } @@ -383,7 +383,7 @@ static void handle_mem_options(void) static void mem_avoid_init(unsigned long input, unsigned long input_size, unsigned long output) { - unsigned long init_size = boot_params->hdr.init_size; + unsigned long init_size = boot_params_ptr->hdr.init_size; u64 initrd_start, initrd_size; unsigned long cmd_line, cmd_line_size;

@@ -395,10 +395,10 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input;

/* Avoid initrd. */ - initrd_start = (u64)boot_params->ext_ramdisk_image << 32; - initrd_start |= boot_params->hdr.ramdisk_image; - initrd_size = (u64)boot_params->ext_ramdisk_size << 32; - initrd_size |= boot_params->hdr.ramdisk_size; + initrd_start = (u64)boot_params_ptr->ext_ramdisk_image << 32; + initrd_start |= boot_params_ptr->hdr.ramdisk_image; + initrd_size = (u64)boot_params_ptr->ext_ramdisk_size << 32; + initrd_size |= boot_params_ptr->hdr.ramdisk_size; mem_avoid[MEM_AVOID_INITRD].start = initrd_start; mem_avoid[MEM_AVOID_INITRD].size = initrd_size; /* No need to set mapping for initrd, it will be handled in VO. */ @@ -413,8 +413,8 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, }

/* Avoid boot parameters. */ - mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; - mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); + mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params_ptr; + mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params_ptr);

/* We don't need to set a mapping for setup_data. */

@@ -447,7 +447,7 @@ static bool mem_avoid_overlap(struct mem_vector *img, }

/* Avoid all entries in the setup_data linked list. */ - ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; + ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data; while (ptr) { struct mem_vector avoid;

@@ -679,7 +679,7 @@ static bool process_mem_region(struct mem_vector *region, static bool process_efi_entries(unsigned long minimum, unsigned long image_size) { - struct efi_info *e = &boot_params->efi_info; + struct efi_info *e = &boot_params_ptr->efi_info; bool efi_mirror_found = false; struct mem_vector region; efi_memory_desc_t *md; @@ -761,8 +761,8 @@ static void process_e820_entries(unsigned long minimum, struct boot_e820_entry *entry;

/* Verify potential e820 positions, appending to slots list. */ - for (i = 0; i < boot_params->e820_entries; i++) { - entry = &boot_params->e820_table[i]; + for (i = 0; i < boot_params_ptr->e820_entries; i++) { + entry = &boot_params_ptr->e820_table[i]; /* Skip non-RAM entries. */ if (entry->type != E820_TYPE_RAM) continue; @@ -836,7 +836,7 @@ void choose_random_location(unsigned long input, return; }

- boot_params->hdr.loadflags |= KASLR_FLAG; + boot_params_ptr->hdr.loadflags |= KASLR_FLAG;

if (IS_ENABLED(CONFIG_X86_32)) mem_limit = KERNEL_IMAGE_SIZE; diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index a73e4d783cae..32f7cc8a8625 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -12,16 +12,13 @@ #include <asm/processor-flags.h> #include <asm/msr.h> #include <asm/asm-offsets.h> +#include <asm/segment.h> +#include <asm/trapnr.h>

.text .code32 SYM_FUNC_START(get_sev_encryption_bit) - xor %eax, %eax - -#ifdef CONFIG_AMD_MEM_ENCRYPT push %ebx - push %ecx - push %edx

movl $0x80000000, %eax /* CPUID to check the highest leaf */ cpuid @@ -52,12 +49,7 @@ SYM_FUNC_START(get_sev_encryption_bit) xor %eax, %eax

.Lsev_exit: - pop %edx - pop %ecx pop %ebx - -#endif /* CONFIG_AMD_MEM_ENCRYPT */ - RET SYM_FUNC_END(get_sev_encryption_bit)

@@ -98,7 +90,7 @@ SYM_CODE_START_LOCAL(sev_es_req_cpuid) jmp 1b SYM_CODE_END(sev_es_req_cpuid)

-SYM_CODE_START(startup32_vc_handler) +SYM_CODE_START_LOCAL(startup32_vc_handler) pushl %eax pushl %ebx pushl %ecx @@ -184,15 +176,149 @@ SYM_CODE_START(startup32_vc_handler) jmp .Lfail SYM_CODE_END(startup32_vc_handler)

+/* + * Write an IDT entry into boot32_idt + * + * Parameters: + * + * %eax: Handler address + * %edx: Vector number + * %ecx: IDT address + */ +SYM_FUNC_START_LOCAL(startup32_set_idt_entry) + /* IDT entry address to %ecx */ + leal (%ecx, %edx, 8), %ecx + + /* Build IDT entry, lower 4 bytes */ + movl %eax, %edx + andl $0x0000ffff, %edx # Target code segment offset [15:0] + orl $(__KERNEL32_CS << 16), %edx # Target code segment selector + + /* Store lower 4 bytes to IDT */ + movl %edx, (%ecx) + + /* Build IDT entry, upper 4 bytes */ + movl %eax, %edx + andl $0xffff0000, %edx # Target code segment offset [31:16] + orl $0x00008e00, %edx # Present, Type 32-bit Interrupt Gate + + /* Store upper 4 bytes to IDT */ + movl %edx, 4(%ecx) + + RET +SYM_FUNC_END(startup32_set_idt_entry) + +SYM_FUNC_START(startup32_load_idt) + push %ebp + push %ebx + + call 1f +1: pop %ebp + + leal (boot32_idt - 1b)(%ebp), %ebx + + /* #VC handler */ + leal (startup32_vc_handler - 1b)(%ebp), %eax + movl $X86_TRAP_VC, %edx + movl %ebx, %ecx + call startup32_set_idt_entry + + /* Load IDT */ + leal (boot32_idt_desc - 1b)(%ebp), %ecx + movl %ebx, 2(%ecx) + lidt (%ecx) + + pop %ebx + pop %ebp + RET +SYM_FUNC_END(startup32_load_idt) + +/* + * Check for the correct C-bit position when the startup_32 boot-path is used. + * + * The check makes use of the fact that all memory is encrypted when paging is + * disabled. The function creates 64 bits of random data using the RDRAND + * instruction. RDRAND is mandatory for SEV guests, so always available. If the + * hypervisor violates that the kernel will crash right here. + * + * The 64 bits of random data are stored to a memory location and at the same + * time kept in the %eax and %ebx registers. Since encryption is always active + * when paging is off the random data will be stored encrypted in main memory. + * + * Then paging is enabled. When the C-bit position is correct all memory is + * still mapped encrypted and comparing the register values with memory will + * succeed. An incorrect C-bit position will map all memory unencrypted, so that + * the compare will use the encrypted random data and fail. + */ +SYM_FUNC_START(startup32_check_sev_cbit) + pushl %ebx + pushl %ebp + + call 0f +0: popl %ebp + + /* Check for non-zero sev_status */ + movl (sev_status - 0b)(%ebp), %eax + testl %eax, %eax + jz 4f + + /* + * Get two 32-bit random values - Don't bail out if RDRAND fails + * because it is better to prevent forward progress if no random value + * can be gathered. + */ +1: rdrand %eax + jnc 1b +2: rdrand %ebx + jnc 2b + + /* Store to memory and keep it in the registers */ + leal (sev_check_data - 0b)(%ebp), %ebp + movl %eax, 0(%ebp) + movl %ebx, 4(%ebp) + + /* Enable paging to see if encryption is active */ + movl %cr0, %edx /* Backup %cr0 in %edx */ + movl $(X86_CR0_PG | X86_CR0_PE), %ecx /* Enable Paging and Protected mode */ + movl %ecx, %cr0 + + cmpl %eax, 0(%ebp) + jne 3f + cmpl %ebx, 4(%ebp) + jne 3f + + movl %edx, %cr0 /* Restore previous %cr0 */ + + jmp 4f + +3: /* Check failed - hlt the machine */ + hlt + jmp 3b + +4: + popl %ebp + popl %ebx + RET +SYM_FUNC_END(startup32_check_sev_cbit) + .code64

#include "../../kernel/sev_verify_cbit.S"

.data

-#ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 SYM_DATA(sme_me_mask, .quad 0) SYM_DATA(sev_status, .quad 0) SYM_DATA(sev_check_data, .quad 0) -#endif + +SYM_DATA_START_LOCAL(boot32_idt) + .rept 32 + .quad 0 + .endr +SYM_DATA_END(boot32_idt) + +SYM_DATA_START_LOCAL(boot32_idt_desc) + .word . - boot32_idt - 1 + .long 0 +SYM_DATA_END(boot32_idt_desc) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index cf690d8712f4..8ae7893d712f 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -46,7 +46,7 @@ void *memmove(void *dest, const void *src, size_t n); /* * This is set up by the setup-routine at boot-time */ -struct boot_params *boot_params; +struct boot_params *boot_params_ptr;

struct port_io_ops pio_ops;

@@ -132,8 +132,8 @@ void __putstr(const char *s) if (lines == 0 || cols == 0) return;

- x = boot_params->screen_info.orig_x; - y = boot_params->screen_info.orig_y; + x = boot_params_ptr->screen_info.orig_x; + y = boot_params_ptr->screen_info.orig_y;

while ((c = *s++) != '\0') { if (c == '\n') { @@ -154,8 +154,8 @@ void __putstr(const char *s) } }

- boot_params->screen_info.orig_x = x; - boot_params->screen_info.orig_y = y; + boot_params_ptr->screen_info.orig_x = x; + boot_params_ptr->screen_info.orig_y = y;

pos = (x + cols * y) * 2; /* Update cursor position */ outb(14, vidport); @@ -277,7 +277,7 @@ static inline void handle_relocations(void *output, unsigned long output_len, { } #endif

-static void parse_elf(void *output) +static size_t parse_elf(void *output) { #ifdef CONFIG_X86_64 Elf64_Ehdr ehdr; @@ -293,10 +293,8 @@ static void parse_elf(void *output) if (ehdr.e_ident[EI_MAG0] != ELFMAG0 || ehdr.e_ident[EI_MAG1] != ELFMAG1 || ehdr.e_ident[EI_MAG2] != ELFMAG2 || - ehdr.e_ident[EI_MAG3] != ELFMAG3) { + ehdr.e_ident[EI_MAG3] != ELFMAG3) error("Kernel is not a valid ELF file"); - return; - }

debug_putstr("Parsing ELF... ");

@@ -328,6 +326,35 @@ static void parse_elf(void *output) }

free(phdrs); + + return ehdr.e_entry - LOAD_PHYSICAL_ADDR; +} + +const unsigned long kernel_total_size = VO__end - VO__text; + +static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4); + +extern unsigned char input_data[]; +extern unsigned int input_len, output_len; + +unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, + void (*error)(char *x)) +{ + unsigned long entry; + + if (!free_mem_ptr) { + free_mem_ptr = (unsigned long)boot_heap; + free_mem_end_ptr = (unsigned long)boot_heap + sizeof(boot_heap); + } + + if (__decompress(input_data, input_len, NULL, NULL, outbuf, output_len, + NULL, error) < 0) + return ULONG_MAX; + + entry = parse_elf(outbuf); + handle_relocations(outbuf, output_len, virt_addr); + + return entry; }

/* @@ -347,25 +374,22 @@ static void parse_elf(void *output) * |-------uncompressed kernel image---------| * */ -asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, - unsigned char *input_data, - unsigned long input_len, - unsigned char *output, - unsigned long output_len) +asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) { - const unsigned long kernel_total_size = VO__end - VO__text; unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + memptr heap = (memptr)boot_heap; unsigned long needed_size; + size_t entry_offset;

/* Retain x86 boot parameters pointer passed from startup_32/64. */ - boot_params = rmode; + boot_params_ptr = rmode;

/* Clear flags intended for solely in-kernel use. */ - boot_params->hdr.loadflags &= ~KASLR_FLAG; + boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG;

- sanitize_boot_params(boot_params); + sanitize_boot_params(boot_params_ptr);

- if (boot_params->screen_info.orig_video_mode == 7) { + if (boot_params_ptr->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; } else { @@ -373,8 +397,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, vidport = 0x3d4; }

- lines = boot_params->screen_info.orig_video_lines; - cols = boot_params->screen_info.orig_video_cols; + lines = boot_params_ptr->screen_info.orig_video_lines; + cols = boot_params_ptr->screen_info.orig_video_cols;

init_default_io_ops();

@@ -393,7 +417,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, * so that early debugging output from the RSDP parsing code can be * collected. */ - boot_params->acpi_rsdp_addr = get_rsdp_addr(); + boot_params_ptr->acpi_rsdp_addr = get_rsdp_addr();

debug_putstr("early console in extract_kernel\n");

@@ -411,7 +435,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, * entries. This ensures the full mapped area is usable RAM * and doesn't include any reserved areas. */ - needed_size = max(output_len, kernel_total_size); + needed_size = max_t(unsigned long, output_len, kernel_total_size); #ifdef CONFIG_X86_64 needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN); #endif @@ -442,7 +466,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #ifdef CONFIG_X86_64 if (heap > 0x3fffffffffffUL) error("Destination address too large"); - if (virt_addr + max(output_len, kernel_total_size) > KERNEL_IMAGE_SIZE) + if (virt_addr + needed_size > KERNEL_IMAGE_SIZE) error("Destination virtual address is beyond the kernel mapping area"); #else if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) @@ -454,16 +478,17 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #endif

debug_putstr("\nDecompressing Linux... "); - __decompress(input_data, input_len, NULL, NULL, output, output_len, - NULL, error); - parse_elf(output); - handle_relocations(output, output_len, virt_addr); - debug_putstr("done.\nBooting the kernel.\n"); + + entry_offset = decompress_kernel(output, virt_addr, error); + + debug_putstr("done.\nBooting the kernel (entry_offset: 0x"); + debug_puthex(entry_offset); + debug_putstr(").\n");

/* Disable exception handling before booting the kernel */ cleanup_exception_handling();

- return output; + return output + entry_offset; }

void fortify_panic(const char *name) diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index a49d9219c06e..254acd76efde 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -52,7 +52,6 @@ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; void *malloc(int size); void free(void *where); -extern struct boot_params *boot_params; void __putstr(const char *s); void __puthex(unsigned long value); #define error_putstr(__x) __putstr(__x) @@ -170,9 +169,7 @@ static inline int count_immovable_mem_regions(void) { return 0; } #endif

/* ident_map_64.c */ -#ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; -#endif extern void kernel_add_identity_map(unsigned long start, unsigned long end);

/* Used by PAGE_KERN* macros: */ diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h index cc9b2529a086..6d595abe06b3 100644 --- a/arch/x86/boot/compressed/pgtable.h +++ b/arch/x86/boot/compressed/pgtable.h @@ -3,18 +3,16 @@

#define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE)

-#define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 - #define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x80 - -#define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE +#define TRAMPOLINE_32BIT_CODE_SIZE 0xA0

#ifndef __ASSEMBLER__

extern unsigned long *trampoline_32bit;

-extern void trampoline_32bit_src(void *return_ptr); +extern void trampoline_32bit_src(void *trampoline, bool enable_5lvl); + +extern const u16 trampoline_ljmp_imm_offset;

#endif /* __ASSEMBLER__ */ #endif /* BOOT_COMPRESSED_PAGETABLE_H */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 2ac12ff4111b..51f957b24ba7 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -16,11 +16,6 @@ unsigned int __section(".data") pgdir_shift = 39; unsigned int __section(".data") ptrs_per_p4d = 1; #endif

-struct paging_config { - unsigned long trampoline_start; - unsigned long l5_required; -}; - /* Buffer to preserve trampoline memory */ static char trampoline_save[TRAMPOLINE_32BIT_SIZE];

@@ -29,11 +24,10 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; * purposes. * * Avoid putting the pointer into .bss as it will be cleared between - * paging_prepare() and extract_kernel(). + * configure_5level_paging() and extract_kernel(). */ unsigned long *trampoline_32bit __section(".data");

-extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option);

static unsigned long find_trampoline_placement(void) @@ -54,7 +48,7 @@ static unsigned long find_trampoline_placement(void) * * Only look for values in the legacy ROM for non-EFI system. */ - signature = (char *)&boot_params->efi_info.efi_loader_signature; + signature = (char *)&boot_params_ptr->efi_info.efi_loader_signature; if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) && strncmp(signature, EFI64_LOADER_SIGNATURE, 4)) { ebda_start = *(unsigned short *)0x40e << 4; @@ -70,10 +64,10 @@ static unsigned long find_trampoline_placement(void) bios_start = round_down(bios_start, PAGE_SIZE);

/* Find the first usable memory region under bios_start. */ - for (i = boot_params->e820_entries - 1; i >= 0; i--) { + for (i = boot_params_ptr->e820_entries - 1; i >= 0; i--) { unsigned long new = bios_start;

- entry = &boot_params->e820_table[i]; + entry = &boot_params_ptr->e820_table[i];

/* Skip all entries above bios_start. */ if (bios_start <= entry->addr) @@ -106,12 +100,13 @@ static unsigned long find_trampoline_placement(void) return bios_start - TRAMPOLINE_32BIT_SIZE; }

-struct paging_config paging_prepare(void *rmode) +asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable) { - struct paging_config paging_config = {}; + void (*toggle_la57)(void *cr3); + bool l5_required = false;

/* Initialize boot_params. Required for cmdline_find_option_bool(). */ - boot_params = rmode; + boot_params_ptr = bp;

/* * Check if LA57 is desired and supported. @@ -129,12 +124,22 @@ struct paging_config paging_prepare(void *rmode) !cmdline_find_option_bool("no5lvl") && native_cpuid_eax(0) >= 7 && (native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) { - paging_config.l5_required = 1; + l5_required = true; + + /* Initialize variables for 5-level paging */ + __pgtable_l5_enabled = 1; + pgdir_shift = 48; + ptrs_per_p4d = 512; }

- paging_config.trampoline_start = find_trampoline_placement(); + /* + * The trampoline will not be used if the paging mode is already set to + * the desired one. + */ + if (l5_required == !!(native_read_cr4() & X86_CR4_LA57)) + return;

- trampoline_32bit = (unsigned long *)paging_config.trampoline_start; + trampoline_32bit = (unsigned long *)find_trampoline_placement();

/* Preserve trampoline memory */ memcpy(trampoline_save, trampoline_32bit, TRAMPOLINE_32BIT_SIZE); @@ -143,32 +148,32 @@ struct paging_config paging_prepare(void *rmode) memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE);

/* Copy trampoline code in place */ - memcpy(trampoline_32bit + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), + toggle_la57 = memcpy(trampoline_32bit + + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), &trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE);

+ /* + * Avoid the need for a stack in the 32-bit trampoline code, by using + * LJMP rather than LRET to return back to long mode. LJMP takes an + * immediate absolute address, which needs to be adjusted based on the + * placement of the trampoline. + */ + *(u32 *)((u8 *)toggle_la57 + trampoline_ljmp_imm_offset) += + (unsigned long)toggle_la57; + /* * The code below prepares page table in trampoline memory. * * The new page table will be used by trampoline code for switching * from 4- to 5-level paging or vice versa. - * - * If switching is not required, the page table is unused: trampoline - * code wouldn't touch CR3. - */ - - /* - * We are not going to use the page table in trampoline memory if we - * are already in the desired paging mode. */ - if (paging_config.l5_required == !!(native_read_cr4() & X86_CR4_LA57)) - goto out;

- if (paging_config.l5_required) { + if (l5_required) { /* * For 4- to 5-level paging transition, set up current CR3 as * the first and the only entry in a new top-level page table. */ - trampoline_32bit[TRAMPOLINE_32BIT_PGTABLE_OFFSET] = __native_read_cr3() | _PAGE_TABLE_NOENC; + *trampoline_32bit = __native_read_cr3() | _PAGE_TABLE_NOENC; } else { unsigned long src;

@@ -181,38 +186,17 @@ struct paging_config paging_prepare(void *rmode) * may be above 4G. */ src = *(unsigned long *)__native_read_cr3() & PAGE_MASK; - memcpy(trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long), - (void *)src, PAGE_SIZE); + memcpy(trampoline_32bit, (void *)src, PAGE_SIZE); }

-out: - return paging_config; -} - -void cleanup_trampoline(void *pgtable) -{ - void *trampoline_pgtable; - - trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long); + toggle_la57(trampoline_32bit);

/* - * Move the top level page table out of trampoline memory, - * if it's there. + * Move the top level page table out of trampoline memory. */ - if ((void *)__native_read_cr3() == trampoline_pgtable) { - memcpy(pgtable, trampoline_pgtable, PAGE_SIZE); - native_write_cr3((unsigned long)pgtable); - } + memcpy(pgtable, trampoline_32bit, PAGE_SIZE); + native_write_cr3((unsigned long)pgtable);

/* Restore trampoline memory */ memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE); - - /* Initialize variables for 5-level paging */ -#ifdef CONFIG_X86_5LEVEL - if (__read_cr4() & X86_CR4_LA57) { - __pgtable_l5_enabled = 1; - pgdir_shift = 48; - ptrs_per_p4d = 512; - } -#endif } diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 9c91cc40f456..d07e665bb265 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -327,20 +327,25 @@ static void enforce_vmpl0(void) */ #define SNP_FEATURES_PRESENT (0)

+u64 snp_get_unsupported_features(u64 status) +{ + if (!(status & MSR_AMD64_SEV_SNP_ENABLED)) + return 0; + + return status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; +} + void snp_check_features(void) { u64 unsupported;

- if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) - return; - /* * Terminate the boot if hypervisor has enabled any feature lacking * guest side implementation. Pass on the unsupported features mask through * EXIT_INFO_2 of the GHCB protocol so that those features can be reported * as part of the guest boot failure. */ - unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; + unsupported = snp_get_unsupported_features(sev_status); if (unsupported) { if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb())) sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); @@ -350,35 +355,22 @@ void snp_check_features(void) } }

-void sev_enable(struct boot_params *bp) +/* + * sev_check_cpu_support - Check for SEV support in the CPU capabilities + * + * Returns < 0 if SEV is not supported, otherwise the position of the + * encryption bit in the page table descriptors. + */ +static int sev_check_cpu_support(void) { unsigned int eax, ebx, ecx, edx; - struct msr m; - bool snp; - - /* - * bp->cc_blob_address should only be set by boot/compressed kernel. - * Initialize it to 0 to ensure that uninitialized values from - * buggy bootloaders aren't propagated. - */ - if (bp) - bp->cc_blob_address = 0; - - /* - * Do an initial SEV capability check before snp_init() which - * loads the CPUID page and the same checks afterwards are done - * without the hypervisor and are trustworthy. - * - * If the HV fakes SEV support, the guest will crash'n'burn - * which is good enough. - */

/* Check for the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); if (eax < 0x8000001f) - return; + return -ENODEV;

/* * Check for the SME/SEV feature: @@ -393,6 +385,35 @@ void sev_enable(struct boot_params *bp) native_cpuid(&eax, &ebx, &ecx, &edx); /* Check whether SEV is supported */ if (!(eax & BIT(1))) + return -ENODEV; + + return ebx & 0x3f; +} + +void sev_enable(struct boot_params *bp) +{ + struct msr m; + int bitpos; + bool snp; + + /* + * bp->cc_blob_address should only be set by boot/compressed kernel. + * Initialize it to 0 to ensure that uninitialized values from + * buggy bootloaders aren't propagated. + */ + if (bp) + bp->cc_blob_address = 0; + + /* + * Do an initial SEV capability check before snp_init() which + * loads the CPUID page and the same checks afterwards are done + * without the hypervisor and are trustworthy. + * + * If the HV fakes SEV support, the guest will crash'n'burn + * which is good enough. + */ + + if (sev_check_cpu_support() < 0) return;

/* @@ -403,26 +424,8 @@ void sev_enable(struct boot_params *bp)

/* Now repeat the checks with the SNP CPUID table. */

- /* Recheck the SME/SEV support leaf */ - eax = 0x80000000; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - if (eax < 0x8000001f) - return; - - /* - * Recheck for the SME/SEV feature: - * CPUID Fn8000_001F[EAX] - * - Bit 0 - Secure Memory Encryption support - * - Bit 1 - Secure Encrypted Virtualization support - * CPUID Fn8000_001F[EBX] - * - Bits 5:0 - Pagetable bit position used to indicate encryption - */ - eax = 0x8000001f; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - /* Check whether SEV is supported */ - if (!(eax & BIT(1))) { + bitpos = sev_check_cpu_support(); + if (bitpos < 0) { if (snp) error("SEV-SNP support indicated by CC blob, but not CPUID."); return; @@ -454,7 +457,24 @@ void sev_enable(struct boot_params *bp) if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) error("SEV-SNP supported indicated by CC blob, but not SEV status MSR.");

- sme_me_mask = BIT_ULL(ebx & 0x3f); + sme_me_mask = BIT_ULL(bitpos); +} + +/* + * sev_get_status - Retrieve the SEV status mask + * + * Returns 0 if the CPU is not SEV capable, otherwise the value of the + * AMD64_SEV MSR. + */ +u64 sev_get_status(void) +{ + struct msr m; + + if (sev_check_cpu_support() < 0) + return 0; + + boot_rdmsr(MSR_AMD64_SEV, &m); + return m.q; }

/* Search for Confidential Computing blob in the EFI config table. */ @@ -545,7 +565,7 @@ void sev_prep_identity_maps(unsigned long top_level_pgt) * accessed after switchover. */ if (sev_snp_enabled()) { - unsigned long cc_info_pa = boot_params->cc_blob_address; + unsigned long cc_info_pa = boot_params_ptr->cc_blob_address; struct cc_blob_sev_info *cc_info;

kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info)); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index f912d7770130..d31982509654 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -406,7 +406,7 @@ xloadflags: # define XLF1 0 #endif

-#ifdef CONFIG_EFI_STUB +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL # ifdef CONFIG_EFI_MIXED # define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64) # else diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index a3725ad46c5a..bd247692b701 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -290,6 +290,7 @@ static void efi_stub_entry_update(void) { unsigned long addr = efi32_stub_entry;

+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL #ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */ addr = efi64_stub_entry - 0x200; @@ -298,6 +299,7 @@ static void efi_stub_entry_update(void) #ifdef CONFIG_EFI_MIXED if (efi32_stub_entry != addr) die("32-bit and 64-bit EFI entry points do not match\n"); +#endif #endif put_unaligned_le32(addr, &buf[0x264]); } diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index bfb7bcb362bc..09e99d13fc0b 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,9 @@ #include <linux/linkage.h> #include <asm/export.h> #include <asm/msr-index.h> +#include <asm/unwind_hints.h> +#include <asm/segment.h> +#include <asm/cache.h>

.pushsection .noinstr.text, "ax"

@@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb) EXPORT_SYMBOL_GPL(entry_ibpb);

.popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index e309e7156038..ee5def1060c8 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -912,6 +912,7 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax + CLEAR_CPU_BUFFERS

/* * Return back to the vDSO, which will pop ecx and edx. @@ -981,6 +982,7 @@ restore_all_switch_stack:

/* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1173,6 +1175,7 @@ SYM_CODE_START(asm_exc_nmi)

/* Not on SYSENTER stack. */ call exc_nmi + CLEAR_CPU_BUFFERS jmp .Lnmi_return

.Lnmi_from_sysenter_stack: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9953d966d124..c2383c2880ec 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -223,6 +223,7 @@ syscall_return_via_sysret: SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR swapgs + CLEAR_CPU_BUFFERS sysretq SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR @@ -656,6 +657,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi swapgs + CLEAR_CPU_BUFFERS jmp .Lnative_iret

@@ -767,6 +769,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */

+ CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -1493,6 +1497,12 @@ nmi_restore: std movq $0, 5*8(%rsp) /* clear "NMI executing" */

+ /* + * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like + * NMI in kernel after user state is restored. For an unprivileged user + * these conditions are hard to meet. + */ + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this @@ -1511,6 +1521,7 @@ SYM_CODE_START(ignore_sysret) UNWIND_HINT_EMPTY ENDBR mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(ignore_sysret) #endif diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index d6c08d8986b1..4bcd009a232b 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -272,6 +272,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 215d37f7dde8..a38cc0afc90a 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -79,4 +79,14 @@ # define BOOT_STACK_SIZE 0x1000 #endif

+#ifndef __ASSEMBLY__ +extern unsigned int output_len; +extern const unsigned long kernel_total_size; + +unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, + void (*error)(char *x)); + +extern struct boot_params *boot_params_ptr; +#endif + #endif /* _ASM_X86_BOOT_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b122708792c4..b60f24b30cb9 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -304,7 +304,7 @@ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ - +#define X86_FEATURE_CLEAR_CPU_BUF (11*32+18) /* "" Clear CPU buffers using VERW */

#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 233ae6986d6f..e601264b1a24 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -88,6 +88,8 @@ static inline void efi_fpu_end(void) }

#ifdef CONFIG_X86_32 +#define EFI_X86_KERNEL_ALLOC_LIMIT (SZ_512M - 1) + #define arch_efi_call_virt_setup() \ ({ \ efi_fpu_begin(); \ @@ -101,8 +103,7 @@ static inline void efi_fpu_end(void) })

#else /* !CONFIG_X86_32 */ - -#define EFI_LOADER_SIGNATURE "EL64" +#define EFI_X86_KERNEL_ALLOC_LIMIT EFI_ALLOC_LIMIT

extern asmlinkage u64 __efi_call(void *fp, ...);

@@ -214,6 +215,8 @@ efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size,

#ifdef CONFIG_EFI_MIXED

+#define EFI_ALLOC_LIMIT (efi_is_64bit() ? ULONG_MAX : U32_MAX) + #define ARCH_HAS_EFISTUB_WRAPPERS

static inline bool efi_is_64bit(void) @@ -325,6 +328,13 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_set_memory_space_attributes(phys, size, flags) \ (__efi64_split(phys), __efi64_split(size), __efi64_split(flags))

+/* Memory Attribute Protocol */ +#define __efi64_argmap_set_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + +#define __efi64_argmap_clear_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + /* * The macros below handle the plumbing for the argument mapping. To add a * mapping for a specific EFI method, simply define a macro diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 11203a9fe0a8..ffe72790ceaf 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,

static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index d3706de91a93..8f6f17a8617b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -194,6 +194,19 @@ #endif .endm

+/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS + ALTERNATIVE "jmp .Lskip_verw_@", "", X86_FEATURE_CLEAR_CPU_BUF + verw _ASM_RIP(mds_verw_sel) +.Lskip_verw_@: +.endm + #else /* __ASSEMBLY__ */

#define ANNOTATE_RETPOLINE_SAFE \ @@ -368,13 +381,14 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);

-DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear);

DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);

DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);

+extern u16 mds_verw_sel; + #include <asm/segment.h>

/** @@ -400,17 +414,6 @@ static __always_inline void mds_clear_cpu_buffers(void) asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); }

-/** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_inline void mds_user_clear_cpu_buffers(void) -{ - if (static_branch_likely(&mds_user_clear)) - mds_clear_cpu_buffers(); -} - /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 7ca5c9ec8b52..cf98fc28601f 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -157,6 +157,7 @@ static __always_inline void sev_es_nmi_complete(void) __sev_es_nmi_complete(); } extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd); +extern void sev_enable(struct boot_params *bp);

static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { @@ -202,12 +203,15 @@ void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); void __init __noreturn snp_abort(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); +u64 snp_get_unsupported_features(u64 status); +u64 sev_get_status(void); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } static inline void sev_es_nmi_complete(void) { } static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; } +static inline void sev_enable(struct boot_params *bp) { } static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; } static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; } static inline void setup_ghcb(void) { } @@ -225,6 +229,9 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in { return -ENOTTY; } + +static inline u64 snp_get_unsupported_features(u64 status) { return 0; } +static inline u64 sev_get_status(void) { return 0; } #endif

#endif diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 13dffc43ded0..d1895930e6eb 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -110,9 +110,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);

-/* Control MDS CPU buffer clear before returning to user space */ -DEFINE_STATIC_KEY_FALSE(mds_user_clear); -EXPORT_SYMBOL_GPL(mds_user_clear); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -251,7 +248,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV;

- static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);

if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -355,7 +352,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);

if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -423,7 +420,7 @@ static void __init mmio_select_mitigation(void) */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else static_branch_enable(&mmio_stale_data_clear);

@@ -483,12 +480,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return;

- if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out;

/* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 427899650483..32bd64017047 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -216,6 +216,90 @@ int intel_cpu_collect_info(struct ucode_cpu_info *uci) } EXPORT_SYMBOL_GPL(intel_cpu_collect_info);

+#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -367,6 +451,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); }

static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -527,90 +618,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif }

-#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -747,9 +754,6 @@ static void init_intel(struct cpuinfo_x86 *c)

init_ia32_feat_ctl(c);

- if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c);

split_lock_init(); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 9dac24680ff8..993734e96615 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);

/* - * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need - * to be reserved. + * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by + * kexec and do not need to be reserved. */ - if (data->type != SETUP_EFI && data->type != SETUP_IMA) + if (data->type != SETUP_EFI && + data->type != SETUP_IMA && + data->type != SETUP_RNG_SEED) e820__range_update_kexec(pa_data, sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index cec0bfa3bc04..ed6cce6c3950 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -522,9 +522,6 @@ DEFINE_IDTENTRY_RAW(exc_nmi) write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); }

#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc189..6a9bfdfbb6e5 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H

-#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT)

#endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 0b5db4de4d09..0b2cad66dee1 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -106,7 +106,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX

/* Check if vmlaunch or vmresume is needed */ - testb $VMX_RUN_VMRESUME, %bl + bt $VMX_RUN_VMRESUME_SHIFT, %bx

/* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -128,8 +128,11 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX

- /* Check EFLAGS.ZF from 'testb' above */ - jz .Lvmlaunch + /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch

/* * After a successful VMRESUME/VMLAUNCH, control flow "magically" diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 57c1374fdfd4..5c1590855ffc 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -407,7 +407,8 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)

static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + vmx_fb_clear_ctrl_available;

/* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS @@ -7120,11 +7121,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, { guest_state_enter_irqoff();

- /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index c9064d34d830..0211f704a358 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -152,7 +152,7 @@ static int qca_send_patch_config_cmd(struct hci_dev *hdev) bt_dev_dbg(hdev, "QCA Patch config");

skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, sizeof(cmd), - cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT); + cmd, 0, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { err = PTR_ERR(skb); bt_dev_err(hdev, "Sending QCA Patch config failed (%d)", err); @@ -594,27 +594,48 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, /* Firmware files to download are based on ROM version. * ROM version is derived from last two bytes of soc_ver. */ - rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f); + if (soc_type == QCA_WCN3988) + rom_ver = ((soc_ver & 0x00000f00) >> 0x05) | (soc_ver & 0x0000000f); + else + rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f);

if (soc_type == QCA_WCN6750) qca_send_patch_config_cmd(hdev);

/* Download rampatch file */ config.type = TLV_TYPE_PATCH; - if (qca_is_wcn399x(soc_type)) { + switch (soc_type) { + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: snprintf(config.fwname, sizeof(config.fwname), "qca/crbtfw%02x.tlv", rom_ver); - } else if (soc_type == QCA_QCA6390) { + break; + case QCA_WCN3988: + snprintf(config.fwname, sizeof(config.fwname), + "qca/apbtfw%02x.tlv", rom_ver); + break; + case QCA_QCA6390: snprintf(config.fwname, sizeof(config.fwname), "qca/htbtfw%02x.tlv", rom_ver); - } else if (soc_type == QCA_WCN6750) { + break; + case QCA_WCN6750: /* Choose mbn file by default.If mbn file is not found * then choose tlv file */ config.type = ELF_TYPE_PATCH; snprintf(config.fwname, sizeof(config.fwname), "qca/msbtfw%02x.mbn", rom_ver); - } else { + break; + case QCA_WCN6855: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpbtfw%02x.tlv", rom_ver); + break; + case QCA_WCN7850: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hmtbtfw%02x.tlv", rom_ver); + break; + default: snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin", soc_ver); } @@ -630,27 +651,48 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,

/* Download NVM configuration */ config.type = TLV_TYPE_NVM; - if (firmware_name) + if (firmware_name) { snprintf(config.fwname, sizeof(config.fwname), "qca/%s", firmware_name); - else if (qca_is_wcn399x(soc_type)) { - if (ver.soc_id == QCA_WCN3991_SOC_ID) { + } else { + switch (soc_type) { + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) { + snprintf(config.fwname, sizeof(config.fwname), + "qca/crnv%02xu.bin", rom_ver); + } else { + snprintf(config.fwname, sizeof(config.fwname), + "qca/crnv%02x.bin", rom_ver); + } + break; + case QCA_WCN3988: snprintf(config.fwname, sizeof(config.fwname), - "qca/crnv%02xu.bin", rom_ver); - } else { + "qca/apnv%02x.bin", rom_ver); + break; + case QCA_QCA6390: + snprintf(config.fwname, sizeof(config.fwname), + "qca/htnv%02x.bin", rom_ver); + break; + case QCA_WCN6750: snprintf(config.fwname, sizeof(config.fwname), - "qca/crnv%02x.bin", rom_ver); + "qca/msnv%02x.bin", rom_ver); + break; + case QCA_WCN6855: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpnv%02x.bin", rom_ver); + break; + case QCA_WCN7850: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hmtnv%02x.bin", rom_ver); + break; + + default: + snprintf(config.fwname, sizeof(config.fwname), + "qca/nvm_%08x.bin", soc_ver); } } - else if (soc_type == QCA_QCA6390) - snprintf(config.fwname, sizeof(config.fwname), - "qca/htnv%02x.bin", rom_ver); - else if (soc_type == QCA_WCN6750) - snprintf(config.fwname, sizeof(config.fwname), - "qca/msnv%02x.bin", rom_ver); - else - snprintf(config.fwname, sizeof(config.fwname), - "qca/nvm_%08x.bin", soc_ver);

err = qca_download_firmware(hdev, &config, soc_type, rom_ver); if (err < 0) { @@ -658,16 +700,25 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, return err; }

- if (soc_type >= QCA_WCN3991) { + switch (soc_type) { + case QCA_WCN3991: + case QCA_QCA6390: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: err = qca_disable_soc_logging(hdev); if (err < 0) return err; + break; + default: + break; }

/* WCN399x and WCN6750 supports the Microsoft vendor extension with 0xFD70 as the * VsMsftOpCode. */ switch (soc_type) { + case QCA_WCN3988: case QCA_WCN3990: case QCA_WCN3991: case QCA_WCN3998: @@ -685,11 +736,18 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, return err; }

- if (soc_type == QCA_WCN3991 || soc_type == QCA_WCN6750) { + switch (soc_type) { + case QCA_WCN3991: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: /* get fw build info */ err = qca_read_fw_build_info(hdev); if (err < 0) return err; + break; + default: + break; }

bt_dev_info(hdev, "QCA setup on UART is completed"); diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index 61e9a50e66ae..03bff5c0059d 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -142,11 +142,14 @@ enum qca_btsoc_type { QCA_INVALID = -1, QCA_AR3002, QCA_ROME, + QCA_WCN3988, QCA_WCN3990, QCA_WCN3998, QCA_WCN3991, QCA_QCA6390, QCA_WCN6750, + QCA_WCN6855, + QCA_WCN7850, };

#if IS_ENABLED(CONFIG_BT_QCA) @@ -159,16 +162,6 @@ int qca_read_soc_version(struct hci_dev *hdev, struct qca_btsoc_version *ver, enum qca_btsoc_type); int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr); int qca_send_pre_shutdown_cmd(struct hci_dev *hdev); -static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type) -{ - return soc_type == QCA_WCN3990 || soc_type == QCA_WCN3991 || - soc_type == QCA_WCN3998; -} -static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type) -{ - return soc_type == QCA_WCN6750; -} - #else

static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) @@ -196,16 +189,6 @@ static inline int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr) return -EOPNOTSUPP; }

-static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type) -{ - return false; -} - -static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type) -{ - return false; -} - static inline int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) { return -EOPNOTSUPP; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 76ceb8a0183d..8bfef7f81b41 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -7,6 +7,7 @@ * * Copyright (C) 2007 Texas Instruments, Inc. * Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved. + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. * * Acknowledgements: * This file is based on hci_ll.c, which was... @@ -606,9 +607,18 @@ static int qca_open(struct hci_uart *hu) if (hu->serdev) { qcadev = serdev_device_get_drvdata(hu->serdev);

- if (qca_is_wcn399x(qcadev->btsoc_type) || - qca_is_wcn6750(qcadev->btsoc_type)) + switch (qcadev->btsoc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: hu->init_speed = qcadev->init_speed; + break; + + default: + break; + }

if (qcadev->oper_speed) hu->oper_speed = qcadev->oper_speed; @@ -1314,11 +1324,20 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate) msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS));

/* Give the controller time to process the request */ - if (qca_is_wcn399x(qca_soc_type(hu)) || - qca_is_wcn6750(qca_soc_type(hu))) + switch (qca_soc_type(hu)) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: usleep_range(1000, 10000); - else + break; + + default: msleep(300); + }

return 0; } @@ -1391,12 +1410,20 @@ static unsigned int qca_get_speed(struct hci_uart *hu,

static int qca_check_speeds(struct hci_uart *hu) { - if (qca_is_wcn399x(qca_soc_type(hu)) || - qca_is_wcn6750(qca_soc_type(hu))) { + switch (qca_soc_type(hu)) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: if (!qca_get_speed(hu, QCA_INIT_SPEED) && !qca_get_speed(hu, QCA_OPER_SPEED)) return -EINVAL; - } else { + break; + + default: if (!qca_get_speed(hu, QCA_INIT_SPEED) || !qca_get_speed(hu, QCA_OPER_SPEED)) return -EINVAL; @@ -1425,13 +1452,29 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type) /* Disable flow control for wcn3990 to deassert RTS while * changing the baudrate of chip and host. */ - if (qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type)) + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: hci_uart_set_flow_control(hu, true); + break;

- if (soc_type == QCA_WCN3990) { + default: + break; + } + + switch (soc_type) { + case QCA_WCN3990: reinit_completion(&qca->drop_ev_comp); set_bit(QCA_DROP_VENDOR_EVENT, &qca->flags); + break; + + default: + break; }

qca_baudrate = qca_get_baudrate_value(speed); @@ -1443,11 +1486,23 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type) host_set_baudrate(hu, speed);

error: - if (qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type)) + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: hci_uart_set_flow_control(hu, false); + break;

- if (soc_type == QCA_WCN3990) { + default: + break; + } + + switch (soc_type) { + case QCA_WCN3990: /* Wait for the controller to send the vendor event * for the baudrate change command. */ @@ -1459,6 +1514,10 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type) }

clear_bit(QCA_DROP_VENDOR_EVENT, &qca->flags); + break; + + default: + break; } }

@@ -1620,12 +1679,20 @@ static int qca_regulator_init(struct hci_uart *hu) } }

- if (qca_is_wcn399x(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: /* Forcefully enable wcn399x to enter in to boot mode. */ host_set_baudrate(hu, 2400); ret = qca_send_power_pulse(hu, false); if (ret) return ret; + break; + + default: + break; }

/* For wcn6750 need to enable gpio bt_en */ @@ -1642,10 +1709,18 @@ static int qca_regulator_init(struct hci_uart *hu)

qca_set_speed(hu, QCA_INIT_SPEED);

- if (qca_is_wcn399x(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: ret = qca_send_power_pulse(hu, true); if (ret) return ret; + break; + + default: + break; }

/* Now the device is in ready state to communicate with host. @@ -1679,10 +1754,18 @@ static int qca_power_on(struct hci_dev *hdev) if (!hu->serdev) return 0;

- if (qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: ret = qca_regulator_init(hu); - } else { + break; + + default: qcadev = serdev_device_get_drvdata(hu->serdev); if (qcadev->bt_en) { gpiod_set_value_cansleep(qcadev->bt_en, 1); @@ -1705,6 +1788,7 @@ static int qca_setup(struct hci_uart *hu) const char *firmware_name = qca_get_firmware_name(hu); int ret; struct qca_btsoc_version ver; + const char *soc_name;

ret = qca_check_speeds(hu); if (ret) @@ -1719,9 +1803,30 @@ static int qca_setup(struct hci_uart *hu) */ set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks);

- bt_dev_info(hdev, "setting up %s", - qca_is_wcn399x(soc_type) ? "wcn399x" : - (soc_type == QCA_WCN6750) ? "wcn6750" : "ROME/QCA6390"); + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + soc_name = "wcn399x"; + break; + + case QCA_WCN6750: + soc_name = "wcn6750"; + break; + + case QCA_WCN6855: + soc_name = "wcn6855"; + break; + + case QCA_WCN7850: + soc_name = "wcn7850"; + break; + + default: + soc_name = "ROME/QCA6390"; + } + bt_dev_info(hdev, "setting up %s", soc_name);

qca->memdump_state = QCA_MEMDUMP_IDLE;

@@ -1732,15 +1837,33 @@ static int qca_setup(struct hci_uart *hu)

clear_bit(QCA_SSR_TRIGGERED, &qca->flags);

- if (qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type)) { - set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: + + /* Set BDA quirk bit for reading BDA value from fwnode property + * only if that property exist in DT. + */ + if (fwnode_property_present(dev_fwnode(hdev->dev.parent), "local-bd-address")) { + set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); + bt_dev_info(hdev, "setting quirk bit to read BDA from fwnode later"); + } else { + bt_dev_dbg(hdev, "local-bd-address` is not present in the devicetree so not setting quirk bit for BDA"); + } + hci_set_aosp_capable(hdev);

ret = qca_read_soc_version(hdev, &ver, soc_type); if (ret) goto out; - } else { + break; + + default: qca_set_speed(hu, QCA_INIT_SPEED); }

@@ -1754,8 +1877,17 @@ static int qca_setup(struct hci_uart *hu) qca_baudrate = qca_get_baudrate_value(speed); }

- if (!(qca_is_wcn399x(soc_type) || - qca_is_wcn6750(soc_type))) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: + break; + + default: /* Get QCA version information */ ret = qca_read_soc_version(hdev, &ver, soc_type); if (ret) @@ -1824,7 +1956,18 @@ static const struct hci_uart_proto qca_proto = { .dequeue = qca_dequeue, };

-static const struct qca_device_data qca_soc_data_wcn3990 = { +static const struct qca_device_data qca_soc_data_wcn3988 __maybe_unused = { + .soc_type = QCA_WCN3988, + .vregs = (struct qca_vreg []) { + { "vddio", 15000 }, + { "vddxo", 80000 }, + { "vddrf", 300000 }, + { "vddch0", 450000 }, + }, + .num_vregs = 4, +}; + +static const struct qca_device_data qca_soc_data_wcn3990 __maybe_unused = { .soc_type = QCA_WCN3990, .vregs = (struct qca_vreg []) { { "vddio", 15000 }, @@ -1835,7 +1978,7 @@ static const struct qca_device_data qca_soc_data_wcn3990 = { .num_vregs = 4, };

-static const struct qca_device_data qca_soc_data_wcn3991 = { +static const struct qca_device_data qca_soc_data_wcn3991 __maybe_unused = { .soc_type = QCA_WCN3991, .vregs = (struct qca_vreg []) { { "vddio", 15000 }, @@ -1847,7 +1990,7 @@ static const struct qca_device_data qca_soc_data_wcn3991 = { .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, };

-static const struct qca_device_data qca_soc_data_wcn3998 = { +static const struct qca_device_data qca_soc_data_wcn3998 __maybe_unused = { .soc_type = QCA_WCN3998, .vregs = (struct qca_vreg []) { { "vddio", 10000 }, @@ -1858,13 +2001,13 @@ static const struct qca_device_data qca_soc_data_wcn3998 = { .num_vregs = 4, };

-static const struct qca_device_data qca_soc_data_qca6390 = { +static const struct qca_device_data qca_soc_data_qca6390 __maybe_unused = { .soc_type = QCA_QCA6390, .num_vregs = 0, .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, };

-static const struct qca_device_data qca_soc_data_wcn6750 = { +static const struct qca_device_data qca_soc_data_wcn6750 __maybe_unused = { .soc_type = QCA_WCN6750, .vregs = (struct qca_vreg []) { { "vddio", 5000 }, @@ -1881,6 +2024,34 @@ static const struct qca_device_data qca_soc_data_wcn6750 = { .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, };

+static const struct qca_device_data qca_soc_data_wcn6855 = { + .soc_type = QCA_WCN6855, + .vregs = (struct qca_vreg []) { + { "vddio", 5000 }, + { "vddbtcxmx", 126000 }, + { "vddrfacmn", 12500 }, + { "vddrfa0p8", 102000 }, + { "vddrfa1p7", 302000 }, + { "vddrfa1p2", 257000 }, + }, + .num_vregs = 6, + .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, +}; + +static const struct qca_device_data qca_soc_data_wcn7850 __maybe_unused = { + .soc_type = QCA_WCN7850, + .vregs = (struct qca_vreg []) { + { "vddio", 5000 }, + { "vddaon", 26000 }, + { "vdddig", 126000 }, + { "vddrfa0p8", 102000 }, + { "vddrfa1p2", 257000 }, + { "vddrfa1p9", 302000 }, + }, + .num_vregs = 6, + .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, +}; + static void qca_power_shutdown(struct hci_uart *hu) { struct qca_serdev *qcadev; @@ -1906,11 +2077,18 @@ static void qca_power_shutdown(struct hci_uart *hu)

qcadev = serdev_device_get_drvdata(hu->serdev);

- if (qca_is_wcn399x(soc_type)) { + switch (soc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: host_set_baudrate(hu, 2400); qca_send_power_pulse(hu, false); qca_regulator_disable(qcadev); - } else if (soc_type == QCA_WCN6750) { + break; + + case QCA_WCN6750: + case QCA_WCN6855: gpiod_set_value_cansleep(qcadev->bt_en, 0); msleep(100); qca_regulator_disable(qcadev); @@ -1918,7 +2096,9 @@ static void qca_power_shutdown(struct hci_uart *hu) sw_ctrl_state = gpiod_get_value_cansleep(qcadev->sw_ctrl); bt_dev_dbg(hu->hdev, "SW_CTRL is %d", sw_ctrl_state); } - } else if (qcadev->bt_en) { + break; + + default: gpiod_set_value_cansleep(qcadev->bt_en, 0); }

@@ -2043,10 +2223,19 @@ static int qca_serdev_probe(struct serdev_device *serdev) if (!qcadev->oper_speed) BT_DBG("UART will pick default operating speed");

- if (data && - (qca_is_wcn399x(data->soc_type) || - qca_is_wcn6750(data->soc_type))) { + if (data) qcadev->btsoc_type = data->soc_type; + else + qcadev->btsoc_type = QCA_ROME; + + switch (qcadev->btsoc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: qcadev->bt_power = devm_kzalloc(&serdev->dev, sizeof(struct qca_power), GFP_KERNEL); @@ -2065,14 +2254,19 @@ static int qca_serdev_probe(struct serdev_device *serdev)

qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en) && data->soc_type == QCA_WCN6750) { + if (IS_ERR_OR_NULL(qcadev->bt_en) && + (data->soc_type == QCA_WCN6750 || + data->soc_type == QCA_WCN6855)) { dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n"); power_ctrl_enabled = false; }

qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl", GPIOD_IN); - if (IS_ERR_OR_NULL(qcadev->sw_ctrl) && data->soc_type == QCA_WCN6750) + if (IS_ERR_OR_NULL(qcadev->sw_ctrl) && + (data->soc_type == QCA_WCN6750 || + data->soc_type == QCA_WCN6855 || + data->soc_type == QCA_WCN7850)) dev_warn(&serdev->dev, "failed to acquire SW_CTRL gpio\n");

qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); @@ -2086,12 +2280,9 @@ static int qca_serdev_probe(struct serdev_device *serdev) BT_ERR("wcn3990 serdev registration failed"); return err; } - } else { - if (data) - qcadev->btsoc_type = data->soc_type; - else - qcadev->btsoc_type = QCA_ROME; + break;

+ default: qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); if (IS_ERR_OR_NULL(qcadev->bt_en)) { @@ -2147,12 +2338,24 @@ static void qca_serdev_remove(struct serdev_device *serdev) struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); struct qca_power *power = qcadev->bt_power;

- if ((qca_is_wcn399x(qcadev->btsoc_type) || - qca_is_wcn6750(qcadev->btsoc_type)) && - power->vregs_on) - qca_power_shutdown(&qcadev->serdev_hu); - else if (qcadev->susclk) - clk_disable_unprepare(qcadev->susclk); + switch (qcadev->btsoc_type) { + case QCA_WCN3988: + case QCA_WCN3990: + case QCA_WCN3991: + case QCA_WCN3998: + case QCA_WCN6750: + case QCA_WCN6855: + case QCA_WCN7850: + if (power->vregs_on) { + qca_power_shutdown(&qcadev->serdev_hu); + break; + } + fallthrough; + + default: + if (qcadev->susclk) + clk_disable_unprepare(qcadev->susclk); + }

hci_uart_unregister_device(&qcadev->serdev_hu); } @@ -2329,10 +2532,13 @@ static const struct of_device_id qca_bluetooth_of_match[] = { { .compatible = "qcom,qca6174-bt" }, { .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390}, { .compatible = "qcom,qca9377-bt" }, + { .compatible = "qcom,wcn3988-bt", .data = &qca_soc_data_wcn3988}, { .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data_wcn3990}, { .compatible = "qcom,wcn3991-bt", .data = &qca_soc_data_wcn3991}, { .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998}, { .compatible = "qcom,wcn6750-bt", .data = &qca_soc_data_wcn6750}, + { .compatible = "qcom,wcn6855-bt", .data = &qca_soc_data_wcn6855}, + { .compatible = "qcom,wcn7850-bt", .data = &qca_soc_data_wcn7850}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match); diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index 422d78247553..dcacc5064d33 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -21,24 +21,24 @@ #define MISC_CLK_ENB 0x48

#define OSC_CTRL 0x50 -#define OSC_CTRL_OSC_FREQ_MASK (3<<30) -#define OSC_CTRL_OSC_FREQ_13MHZ (0<<30) -#define OSC_CTRL_OSC_FREQ_19_2MHZ (1<<30) -#define OSC_CTRL_OSC_FREQ_12MHZ (2<<30) -#define OSC_CTRL_OSC_FREQ_26MHZ (3<<30) -#define OSC_CTRL_MASK (0x3f2 | OSC_CTRL_OSC_FREQ_MASK) - -#define OSC_CTRL_PLL_REF_DIV_MASK (3<<28) -#define OSC_CTRL_PLL_REF_DIV_1 (0<<28) -#define OSC_CTRL_PLL_REF_DIV_2 (1<<28) -#define OSC_CTRL_PLL_REF_DIV_4 (2<<28) +#define OSC_CTRL_OSC_FREQ_MASK (3u<<30) +#define OSC_CTRL_OSC_FREQ_13MHZ (0u<<30) +#define OSC_CTRL_OSC_FREQ_19_2MHZ (1u<<30) +#define OSC_CTRL_OSC_FREQ_12MHZ (2u<<30) +#define OSC_CTRL_OSC_FREQ_26MHZ (3u<<30) +#define OSC_CTRL_MASK (0x3f2u | OSC_CTRL_OSC_FREQ_MASK) + +#define OSC_CTRL_PLL_REF_DIV_MASK (3u<<28) +#define OSC_CTRL_PLL_REF_DIV_1 (0u<<28) +#define OSC_CTRL_PLL_REF_DIV_2 (1u<<28) +#define OSC_CTRL_PLL_REF_DIV_4 (2u<<28)

#define OSC_FREQ_DET 0x58 -#define OSC_FREQ_DET_TRIG (1<<31) +#define OSC_FREQ_DET_TRIG (1u<<31)

#define OSC_FREQ_DET_STATUS 0x5c -#define OSC_FREQ_DET_BUSY (1<<31) -#define OSC_FREQ_DET_CNT_MASK 0xFFFF +#define OSC_FREQ_DET_BUSYu (1<<31) +#define OSC_FREQ_DET_CNT_MASK 0xFFFFu

#define TEGRA20_CLK_PERIPH_BANKS 3

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index abdd26f7d04c..5771f3fc6115 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2952,6 +2952,9 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum, if (min_pstate < cpu->min_perf_ratio) min_pstate = cpu->min_perf_ratio;

+ if (min_pstate > cpu->max_perf_ratio) + min_pstate = cpu->max_perf_ratio; + max_pstate = min(cap_pstate, cpu->max_perf_ratio); if (max_pstate < min_pstate) max_pstate = min_pstate; diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c index f383f219ed00..7082a5a6814a 100644 --- a/drivers/dma/fsl-qdma.c +++ b/drivers/dma/fsl-qdma.c @@ -109,6 +109,7 @@ #define FSL_QDMA_CMD_WTHROTL_OFFSET 20 #define FSL_QDMA_CMD_DSEN_OFFSET 19 #define FSL_QDMA_CMD_LWC_OFFSET 16 +#define FSL_QDMA_CMD_PF BIT(17)

/* Field definition for Descriptor status */ #define QDMA_CCDF_STATUS_RTE BIT(5) @@ -384,7 +385,8 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp, qdma_csgf_set_f(csgf_dest, len); /* Descriptor Buffer */ cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << - FSL_QDMA_CMD_RWTTYPE_OFFSET); + FSL_QDMA_CMD_RWTTYPE_OFFSET) | + FSL_QDMA_CMD_PF; sdf->data = QDMA_SDDF_CMD(cmd);

cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << @@ -1201,10 +1203,6 @@ static int fsl_qdma_probe(struct platform_device *pdev) if (!fsl_qdma->queue) return -ENOMEM;

- ret = fsl_qdma_irq_init(pdev, fsl_qdma); - if (ret) - return ret; - fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0"); if (fsl_qdma->irq_base < 0) return fsl_qdma->irq_base; @@ -1243,16 +1241,19 @@ static int fsl_qdma_probe(struct platform_device *pdev)

platform_set_drvdata(pdev, fsl_qdma);

- ret = dma_async_device_register(&fsl_qdma->dma_dev); + ret = fsl_qdma_reg_init(fsl_qdma); if (ret) { - dev_err(&pdev->dev, - "Can't register NXP Layerscape qDMA engine.\n"); + dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); return ret; }

- ret = fsl_qdma_reg_init(fsl_qdma); + ret = fsl_qdma_irq_init(pdev, fsl_qdma); + if (ret) + return ret; + + ret = dma_async_device_register(&fsl_qdma->dma_dev); if (ret) { - dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); + dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n"); return ret; }

diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/ptdma/ptdma-dmaengine.c index 1aa65e5de0f3..f79240734807 100644 --- a/drivers/dma/ptdma/ptdma-dmaengine.c +++ b/drivers/dma/ptdma/ptdma-dmaengine.c @@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_device *pt) chan->vc.desc_free = pt_do_cleanup; vchan_init(&chan->vc, dma_dev);

- dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64)); - ret = dma_async_device_register(dma_dev); if (ret) goto err_reg; diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 3e8d4b51a814..97bafb5f7038 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file) return -ENOMEM; }

- cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL); + cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL); if (!cap_info->phys) { kfree(cap_info->pages); kfree(cap_info); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index b7c0e8cc0764..9077353d1c98 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -185,8 +185,27 @@ static const struct attribute_group efi_subsys_attr_group = { static struct efivars generic_efivars; static struct efivar_operations generic_ops;

+static bool generic_ops_supported(void) +{ + unsigned long name_size; + efi_status_t status; + efi_char16_t name; + efi_guid_t guid; + + name_size = sizeof(name); + + status = efi.get_next_variable(&name_size, &name, &guid); + if (status == EFI_UNSUPPORTED) + return false; + + return true; +} + static int generic_ops_register(void) { + if (!generic_ops_supported()) + return 0; + generic_ops.get_variable = efi.get_variable; generic_ops.get_next_variable = efi.get_next_variable; generic_ops.query_variable_store = efi_query_variable_store; @@ -200,6 +219,9 @@ static int generic_ops_register(void)

static void generic_ops_unregister(void) { + if (!generic_ops.get_variable) + return; + efivars_unregister(&generic_efivars); }

diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index b6e1dcb98a64..473ef18421db 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -84,6 +84,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB) += efi-stub.o string.o intrinsics.o systable.o lib-$(CONFIG_ARM) += arm32-stub.o lib-$(CONFIG_ARM64) += arm64-stub.o smbios.o lib-$(CONFIG_X86) += x86-stub.o +lib-$(CONFIG_X86_64) += x86-5lvl.o lib-$(CONFIG_RISCV) += riscv-stub.o lib-$(CONFIG_LOONGARCH) += loongarch-stub.o

diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c index 1de9878ddd3a..6b83c492c3b8 100644 --- a/drivers/firmware/efi/libstub/alignedmem.c +++ b/drivers/firmware/efi/libstub/alignedmem.c @@ -22,12 +22,15 @@ * Return: status code */ efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr, - unsigned long max, unsigned long align) + unsigned long max, unsigned long align, + int memory_type) { efi_physical_addr_t alloc_addr; efi_status_t status; int slack;

+ max = min(max, EFI_ALLOC_LIMIT); + if (align < EFI_ALLOC_ALIGN) align = EFI_ALLOC_ALIGN;

@@ -36,7 +39,7 @@ efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr, slack = align / EFI_PAGE_SIZE - 1;

status = efi_bs_call(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS, - EFI_LOADER_DATA, size / EFI_PAGE_SIZE + slack, + memory_type, size / EFI_PAGE_SIZE + slack, &alloc_addr); if (status != EFI_SUCCESS) return status; diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index e2f90566b291..16f15e36f9a7 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -180,7 +180,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, * locate the kernel at a randomized offset in physical memory. */ status = efi_random_alloc(*reserve_size, min_kimg_align, - reserve_addr, phys_seed); + reserve_addr, phys_seed, + EFI_LOADER_CODE, 0, EFI_ALLOC_LIMIT); if (status != EFI_SUCCESS) efi_warn("efi_random_alloc() failed: 0x%lx\n", status); } else { @@ -190,10 +191,11 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (status != EFI_SUCCESS) { if (!check_image_region((u64)_text, kernel_memsize)) { efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n"); - } else if (IS_ALIGNED((u64)_text, min_kimg_align)) { + } else if (IS_ALIGNED((u64)_text, min_kimg_align) && + (u64)_end < EFI_ALLOC_LIMIT) { /* * Just execute from wherever we were loaded by the - * UEFI PE/COFF loader if the alignment is suitable. + * UEFI PE/COFF loader if the placement is suitable. */ *image_addr = (u64)_text; *reserve_size = 0; @@ -201,7 +203,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, }

status = efi_allocate_pages_aligned(*reserve_size, reserve_addr, - ULONG_MAX, min_kimg_align); + ULONG_MAX, min_kimg_align, + EFI_LOADER_CODE);

if (status != EFI_SUCCESS) { efi_err("Failed to relocate kernel\n"); diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 3d9b2469a0df..97744822dd95 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -216,6 +216,8 @@ efi_status_t efi_parse_options(char const *cmdline) efi_loglevel = CONSOLE_LOGLEVEL_QUIET; } else if (!strcmp(param, "noinitrd")) { efi_noinitrd = true; + } else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) { + efi_no5lvl = true; } else if (!strcmp(param, "efi") && val) { efi_nochunk = parse_option_str(val, "nochunk"); efi_novamap |= parse_option_str(val, "novamap"); diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 970e86e3aab0..6741f3d900c5 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -29,6 +29,11 @@ #define EFI_ALLOC_ALIGN EFI_PAGE_SIZE #endif

+#ifndef EFI_ALLOC_LIMIT +#define EFI_ALLOC_LIMIT ULONG_MAX +#endif + +extern bool efi_no5lvl; extern bool efi_nochunk; extern bool efi_nokaslr; extern int efi_loglevel; @@ -415,6 +420,26 @@ union efi_dxe_services_table { } mixed_mode; };

+typedef union efi_memory_attribute_protocol efi_memory_attribute_protocol_t; + +union efi_memory_attribute_protocol { + struct { + efi_status_t (__efiapi *get_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64 *); + + efi_status_t (__efiapi *set_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64); + + efi_status_t (__efiapi *clear_memory_attributes)( + efi_memory_attribute_protocol_t *, efi_physical_addr_t, u64, u64); + }; + struct { + u32 get_memory_attributes; + u32 set_memory_attributes; + u32 clear_memory_attributes; + } mixed_mode; +}; + typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t;

union efi_uga_draw_protocol { @@ -880,7 +905,9 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size, efi_status_t efi_get_random_bytes(unsigned long size, u8 *out);

efi_status_t efi_random_alloc(unsigned long size, unsigned long align, - unsigned long *addr, unsigned long random_seed); + unsigned long *addr, unsigned long random_seed, + int memory_type, unsigned long alloc_min, + unsigned long alloc_max);

efi_status_t efi_random_get_seed(void);

@@ -907,7 +934,8 @@ efi_status_t efi_allocate_pages(unsigned long size, unsigned long *addr, unsigned long max);

efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr, - unsigned long max, unsigned long align); + unsigned long max, unsigned long align, + int memory_type);

efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, unsigned long *addr, unsigned long min); diff --git a/drivers/firmware/efi/libstub/mem.c b/drivers/firmware/efi/libstub/mem.c index 45841ef55a9f..4f1fa302234d 100644 --- a/drivers/firmware/efi/libstub/mem.c +++ b/drivers/firmware/efi/libstub/mem.c @@ -89,9 +89,12 @@ efi_status_t efi_allocate_pages(unsigned long size, unsigned long *addr, efi_physical_addr_t alloc_addr; efi_status_t status;

+ max = min(max, EFI_ALLOC_LIMIT); + if (EFI_ALLOC_ALIGN > EFI_PAGE_SIZE) return efi_allocate_pages_aligned(size, addr, max, - EFI_ALLOC_ALIGN); + EFI_ALLOC_ALIGN, + EFI_LOADER_DATA);

alloc_addr = ALIGN_DOWN(max + 1, EFI_ALLOC_ALIGN) - 1; status = efi_bs_call(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS, diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index 9fb5869896be..7ba05719a53b 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -16,7 +16,8 @@ */ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, unsigned long size, - unsigned long align_shift) + unsigned long align_shift, + u64 alloc_min, u64 alloc_max) { unsigned long align = 1UL << align_shift; u64 first_slot, last_slot, region_end; @@ -29,11 +30,11 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, return 0;

region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1, - (u64)ULONG_MAX); + alloc_max); if (region_end < size) return 0;

- first_slot = round_up(md->phys_addr, align); + first_slot = round_up(max(md->phys_addr, alloc_min), align); last_slot = round_down(region_end - size + 1, align);

if (first_slot > last_slot) @@ -53,7 +54,10 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, efi_status_t efi_random_alloc(unsigned long size, unsigned long align, unsigned long *addr, - unsigned long random_seed) + unsigned long random_seed, + int memory_type, + unsigned long alloc_min, + unsigned long alloc_max) { unsigned long total_slots = 0, target_slot; unsigned long total_mirrored_slots = 0; @@ -75,7 +79,8 @@ efi_status_t efi_random_alloc(unsigned long size, efi_memory_desc_t *md = (void *)map->map + map_offset; unsigned long slots;

- slots = get_entry_num_slots(md, size, ilog2(align)); + slots = get_entry_num_slots(md, size, ilog2(align), alloc_min, + alloc_max); MD_NUM_SLOTS(md) = slots; total_slots += slots; if (md->attribute & EFI_MEMORY_MORE_RELIABLE) @@ -118,7 +123,7 @@ efi_status_t efi_random_alloc(unsigned long size, pages = size / EFI_PAGE_SIZE;

status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, - EFI_LOADER_DATA, pages, &target); + memory_type, pages, &target); if (status == EFI_SUCCESS) *addr = target; break; diff --git a/drivers/firmware/efi/libstub/x86-5lvl.c b/drivers/firmware/efi/libstub/x86-5lvl.c new file mode 100644 index 000000000000..479dd445acdc --- /dev/null +++ b/drivers/firmware/efi/libstub/x86-5lvl.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/efi.h> + +#include <asm/boot.h> +#include <asm/desc.h> +#include <asm/efi.h> + +#include "efistub.h" +#include "x86-stub.h" + +bool efi_no5lvl; + +static void (*la57_toggle)(void *cr3); + +static const struct desc_struct gdt[] = { + [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), +}; + +/* + * Enabling (or disabling) 5 level paging is tricky, because it can only be + * done from 32-bit mode with paging disabled. This means not only that the + * code itself must be running from 32-bit addressable physical memory, but + * also that the root page table must be 32-bit addressable, as programming + * a 64-bit value into CR3 when running in 32-bit mode is not supported. + */ +efi_status_t efi_setup_5level_paging(void) +{ + u8 tmpl_size = (u8 *)&trampoline_ljmp_imm_offset - (u8 *)&trampoline_32bit_src; + efi_status_t status; + u8 *la57_code; + + if (!efi_is_64bit()) + return EFI_SUCCESS; + + /* check for 5 level paging support */ + if (native_cpuid_eax(0) < 7 || + !(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) + return EFI_SUCCESS; + + /* allocate some 32-bit addressable memory for code and a page table */ + status = efi_allocate_pages(2 * PAGE_SIZE, (unsigned long *)&la57_code, + U32_MAX); + if (status != EFI_SUCCESS) + return status; + + la57_toggle = memcpy(la57_code, trampoline_32bit_src, tmpl_size); + memset(la57_code + tmpl_size, 0x90, PAGE_SIZE - tmpl_size); + + /* + * To avoid the need to allocate a 32-bit addressable stack, the + * trampoline uses a LJMP instruction to switch back to long mode. + * LJMP takes an absolute destination address, which needs to be + * fixed up at runtime. + */ + *(u32 *)&la57_code[trampoline_ljmp_imm_offset] += (unsigned long)la57_code; + + efi_adjust_memory_range_protection((unsigned long)la57_toggle, PAGE_SIZE); + + return EFI_SUCCESS; +} + +void efi_5level_switch(void) +{ + bool want_la57 = IS_ENABLED(CONFIG_X86_5LEVEL) && !efi_no5lvl; + bool have_la57 = native_read_cr4() & X86_CR4_LA57; + bool need_toggle = want_la57 ^ have_la57; + u64 *pgt = (void *)la57_toggle + PAGE_SIZE; + u64 *cr3 = (u64 *)__native_read_cr3(); + u64 *new_cr3; + + if (!la57_toggle || !need_toggle) + return; + + if (!have_la57) { + /* + * 5 level paging will be enabled, so a root level page needs + * to be allocated from the 32-bit addressable physical region, + * with its first entry referring to the existing hierarchy. + */ + new_cr3 = memset(pgt, 0, PAGE_SIZE); + new_cr3[0] = (u64)cr3 | _PAGE_TABLE_NOENC; + } else { + /* take the new root table pointer from the current entry #0 */ + new_cr3 = (u64 *)(cr3[0] & PAGE_MASK); + + /* copy the new root table if it is not 32-bit addressable */ + if ((u64)new_cr3 > U32_MAX) + new_cr3 = memcpy(pgt, new_cr3, PAGE_SIZE); + } + + native_load_gdt(&(struct desc_ptr){ sizeof(gdt) - 1, (u64)gdt }); + + la57_toggle(new_cr3); +} diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 4f0152b11a89..784e1b2ae5cc 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -15,16 +15,16 @@ #include <asm/setup.h> #include <asm/desc.h> #include <asm/boot.h> +#include <asm/kaslr.h> +#include <asm/sev.h>

#include "efistub.h" - -/* Maximum physical address for 64-bit kernel with 4-level paging */ -#define MAXMEM_X86_64_4LEVEL (1ull << 46) +#include "x86-stub.h"

const efi_system_table_t *efi_system_table; const efi_dxe_services_table_t *efi_dxe_table; -extern u32 image_offset; static efi_loaded_image_t *image = NULL; +static efi_memory_attribute_protocol_t *memattr;

static efi_status_t preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) @@ -212,8 +212,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) } }

-static void -adjust_memory_range_protection(unsigned long start, unsigned long size) +efi_status_t efi_adjust_memory_range_protection(unsigned long start, + unsigned long size) { efi_status_t status; efi_gcd_memory_space_desc_t desc; @@ -221,12 +221,22 @@ adjust_memory_range_protection(unsigned long start, unsigned long size) unsigned long rounded_start, rounded_end; unsigned long unprotect_start, unprotect_size;

- if (efi_dxe_table == NULL) - return; - rounded_start = rounddown(start, EFI_PAGE_SIZE); rounded_end = roundup(start + size, EFI_PAGE_SIZE);

+ if (memattr != NULL) { + status = efi_call_proto(memattr, clear_memory_attributes, + rounded_start, + rounded_end - rounded_start, + EFI_MEMORY_XP); + if (status != EFI_SUCCESS) + efi_warn("Failed to clear EFI_MEMORY_XP attribute\n"); + return status; + } + + if (efi_dxe_table == NULL) + return EFI_SUCCESS; + /* * Don't modify memory region attributes, they are * already suitable, to lower the possibility to @@ -238,7 +248,7 @@ adjust_memory_range_protection(unsigned long start, unsigned long size) status = efi_dxe_call(get_memory_space_descriptor, start, &desc);

if (status != EFI_SUCCESS) - return; + break;

next = desc.base_address + desc.length;

@@ -263,69 +273,26 @@ adjust_memory_range_protection(unsigned long start, unsigned long size) unprotect_start, unprotect_start + unprotect_size, status); + break; } } + return EFI_SUCCESS; }

-/* - * Trampoline takes 2 pages and can be loaded in first megabyte of memory - * with its end placed between 128k and 640k where BIOS might start. - * (see arch/x86/boot/compressed/pgtable_64.c) - * - * We cannot find exact trampoline placement since memory map - * can be modified by UEFI, and it can alter the computed address. - */ - -#define TRAMPOLINE_PLACEMENT_BASE ((128 - 8)*1024) -#define TRAMPOLINE_PLACEMENT_SIZE (640*1024 - (128 - 8)*1024) - -void startup_32(struct boot_params *boot_params); - -static void -setup_memory_protection(unsigned long image_base, unsigned long image_size) +static efi_char16_t *efistub_fw_vendor(void) { - /* - * Allow execution of possible trampoline used - * for switching between 4- and 5-level page tables - * and relocated kernel image. - */ - - adjust_memory_range_protection(TRAMPOLINE_PLACEMENT_BASE, - TRAMPOLINE_PLACEMENT_SIZE); + unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor);

-#ifdef CONFIG_64BIT - if (image_base != (unsigned long)startup_32) - adjust_memory_range_protection(image_base, image_size); -#else - /* - * Clear protection flags on a whole range of possible - * addresses used for KASLR. We don't need to do that - * on x86_64, since KASLR/extraction is performed after - * dedicated identity page tables are built and we only - * need to remove possible protection on relocated image - * itself disregarding further relocations. - */ - adjust_memory_range_protection(LOAD_PHYSICAL_ADDR, - KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR); -#endif + return (efi_char16_t *)vendor; }

static const efi_char16_t apple[] = L"Apple";

-static void setup_quirks(struct boot_params *boot_params, - unsigned long image_base, - unsigned long image_size) +static void setup_quirks(struct boot_params *boot_params) { - efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table, fw_vendor); - - if (!memcmp(fw_vendor, apple, sizeof(apple))) { - if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) - retrieve_apple_device_properties(boot_params); - } - - if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES)) - setup_memory_protection(image_base, image_size); + if (IS_ENABLED(CONFIG_APPLE_PROPERTIES) && + !memcmp(efistub_fw_vendor(), apple, sizeof(apple))) + retrieve_apple_device_properties(boot_params); }

/* @@ -478,7 +445,6 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, }

image_base = efi_table_attr(image, image_base); - image_offset = (void *)startup_32 - image_base;

status = efi_allocate_pages(sizeof(struct boot_params), (unsigned long *)&boot_params, ULONG_MAX); @@ -760,85 +726,139 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) return EFI_SUCCESS; }

+static bool have_unsupported_snp_features(void) +{ + u64 unsupported; + + unsupported = snp_get_unsupported_features(sev_get_status()); + if (unsupported) { + efi_err("Unsupported SEV-SNP features detected: 0x%llx\n", + unsupported); + return true; + } + return false; +} + +static void efi_get_seed(void *seed, int size) +{ + efi_get_random_bytes(size, seed); + + /* + * This only updates seed[0] when running on 32-bit, but in that case, + * seed[1] is not used anyway, as there is no virtual KASLR on 32-bit. + */ + *(unsigned long *)seed ^= kaslr_get_random_long("EFI"); +} + +static void error(char *str) +{ + efi_warn("Decompression failed: %s\n", str); +} + +static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) +{ + unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + unsigned long addr, alloc_size, entry; + efi_status_t status; + u32 seed[2] = {}; + + /* determine the required size of the allocation */ + alloc_size = ALIGN(max_t(unsigned long, output_len, kernel_total_size), + MIN_KERNEL_ALIGN); + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) { + u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size; + static const efi_char16_t ami[] = L"American Megatrends"; + + efi_get_seed(seed, sizeof(seed)); + + virt_addr += (range * seed[1]) >> 32; + virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1); + + /* + * Older Dell systems with AMI UEFI firmware v2.0 may hang + * while decompressing the kernel if physical address + * randomization is enabled. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=218173 + */ + if (efi_system_table->hdr.revision <= EFI_2_00_SYSTEM_TABLE_REVISION && + !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) { + efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n"); + seed[0] = 0; + } + + boot_params_ptr->hdr.loadflags |= KASLR_FLAG; + } + + status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr, + seed[0], EFI_LOADER_CODE, + LOAD_PHYSICAL_ADDR, + EFI_X86_KERNEL_ALLOC_LIMIT); + if (status != EFI_SUCCESS) + return status; + + entry = decompress_kernel((void *)addr, virt_addr, error); + if (entry == ULONG_MAX) { + efi_free(alloc_size, addr); + return EFI_LOAD_ERROR; + } + + *kernel_entry = addr + entry; + + return efi_adjust_memory_range_protection(addr, kernel_total_size); +} + +static void __noreturn enter_kernel(unsigned long kernel_addr, + struct boot_params *boot_params) +{ + /* enter decompressed kernel with boot_params pointer in RSI/ESI */ + asm("jmp *%0"::"r"(kernel_addr), "S"(boot_params)); + + unreachable(); +} + /* - * On success, we return the address of startup_32, which has potentially been - * relocated by efi_relocate_kernel. - * On failure, we exit to the firmware via efi_exit instead of returning. + * On success, this routine will jump to the relocated image directly and never + * return. On failure, it will exit to the firmware via efi_exit() instead of + * returning. */ -asmlinkage unsigned long efi_main(efi_handle_t handle, - efi_system_table_t *sys_table_arg, - struct boot_params *boot_params) +void __noreturn efi_stub_entry(efi_handle_t handle, + efi_system_table_t *sys_table_arg, + struct boot_params *boot_params) { - unsigned long bzimage_addr = (unsigned long)startup_32; - unsigned long buffer_start, buffer_end; + efi_guid_t guid = EFI_MEMORY_ATTRIBUTE_PROTOCOL_GUID; struct setup_header *hdr = &boot_params->hdr; const struct linux_efi_initrd *initrd = NULL; + unsigned long kernel_entry; efi_status_t status;

+ boot_params_ptr = boot_params; + efi_system_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) efi_exit(handle, EFI_INVALID_PARAMETER);

- efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID); - if (efi_dxe_table && - efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) { - efi_warn("Ignoring DXE services table: invalid signature\n"); - efi_dxe_table = NULL; + if (have_unsupported_snp_features()) + efi_exit(handle, EFI_UNSUPPORTED); + + if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES)) { + efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID); + if (efi_dxe_table && + efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) { + efi_warn("Ignoring DXE services table: invalid signature\n"); + efi_dxe_table = NULL; + } }

- /* - * If the kernel isn't already loaded at a suitable address, - * relocate it. - * - * It must be loaded above LOAD_PHYSICAL_ADDR. - * - * The maximum address for 64-bit is 1 << 46 for 4-level paging. This - * is defined as the macro MAXMEM, but unfortunately that is not a - * compile-time constant if 5-level paging is configured, so we instead - * define our own macro for use here. - * - * For 32-bit, the maximum address is complicated to figure out, for - * now use KERNEL_IMAGE_SIZE, which will be 512MiB, the same as what - * KASLR uses. - * - * Also relocate it if image_offset is zero, i.e. the kernel wasn't - * loaded by LoadImage, but rather by a bootloader that called the - * handover entry. The reason we must always relocate in this case is - * to handle the case of systemd-boot booting a unified kernel image, - * which is a PE executable that contains the bzImage and an initrd as - * COFF sections. The initrd section is placed after the bzImage - * without ensuring that there are at least init_size bytes available - * for the bzImage, and thus the compressed kernel's startup code may - * overwrite the initrd unless it is moved out of the way. - */ + /* grab the memory attributes protocol if it exists */ + efi_bs_call(locate_protocol, &guid, NULL, (void **)&memattr);

- buffer_start = ALIGN(bzimage_addr - image_offset, - hdr->kernel_alignment); - buffer_end = buffer_start + hdr->init_size; - - if ((buffer_start < LOAD_PHYSICAL_ADDR) || - (IS_ENABLED(CONFIG_X86_32) && buffer_end > KERNEL_IMAGE_SIZE) || - (IS_ENABLED(CONFIG_X86_64) && buffer_end > MAXMEM_X86_64_4LEVEL) || - (image_offset == 0)) { - extern char _bss[]; - - status = efi_relocate_kernel(&bzimage_addr, - (unsigned long)_bss - bzimage_addr, - hdr->init_size, - hdr->pref_address, - hdr->kernel_alignment, - LOAD_PHYSICAL_ADDR); - if (status != EFI_SUCCESS) { - efi_err("efi_relocate_kernel() failed!\n"); - goto fail; - } - /* - * Now that we've copied the kernel elsewhere, we no longer - * have a set up block before startup_32(), so reset image_offset - * to zero in case it was set earlier. - */ - image_offset = 0; + status = efi_setup_5level_paging(); + if (status != EFI_SUCCESS) { + efi_err("efi_setup_5level_paging() failed!\n"); + goto fail; }

#ifdef CONFIG_CMDLINE_BOOL @@ -858,6 +878,12 @@ asmlinkage unsigned long efi_main(efi_handle_t handle, } }

+ status = efi_decompress_kernel(&kernel_entry); + if (status != EFI_SUCCESS) { + efi_err("Failed to decompress kernel\n"); + goto fail; + } + /* * At this point, an initrd may already have been loaded by the * bootloader and passed via bootparams. We permit an initrd loaded @@ -897,7 +923,7 @@ asmlinkage unsigned long efi_main(efi_handle_t handle,

setup_efi_pci(boot_params);

- setup_quirks(boot_params, bzimage_addr, buffer_end - buffer_start); + setup_quirks(boot_params);

status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { @@ -905,9 +931,38 @@ asmlinkage unsigned long efi_main(efi_handle_t handle, goto fail; }

- return bzimage_addr; + /* + * Call the SEV init code while still running with the firmware's + * GDT/IDT, so #VC exceptions will be handled by EFI. + */ + sev_enable(boot_params); + + efi_5level_switch(); + + enter_kernel(kernel_entry, boot_params); fail: - efi_err("efi_main() failed!\n"); + efi_err("efi_stub_entry() failed!\n");

efi_exit(handle, status); } + +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL +void efi_handover_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, + struct boot_params *boot_params) +{ + extern char _bss[], _ebss[]; + + memset(_bss, 0, _ebss - _bss); + efi_stub_entry(handle, sys_table_arg, boot_params); +} + +#ifndef CONFIG_EFI_MIXED +extern __alias(efi_handover_entry) +void efi32_stub_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, + struct boot_params *boot_params); + +extern __alias(efi_handover_entry) +void efi64_stub_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg, + struct boot_params *boot_params); +#endif +#endif diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h new file mode 100644 index 000000000000..1c20e99a6494 --- /dev/null +++ b/drivers/firmware/efi/libstub/x86-stub.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include <linux/efi.h> + +extern void trampoline_32bit_src(void *, bool); +extern const u16 trampoline_ljmp_imm_offset; + +efi_status_t efi_adjust_memory_range_protection(unsigned long start, + unsigned long size); + +#ifdef CONFIG_X86_64 +efi_status_t efi_setup_5level_paging(void); +void efi_5level_switch(void); +#else +static inline efi_status_t efi_setup_5level_paging(void) { return EFI_SUCCESS; } +static inline void efi_5level_switch(void) {} +#endif diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 0ba9f18312f5..4ca256bcd697 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -66,19 +66,28 @@ int efivars_register(struct efivars *efivars, const struct efivar_operations *ops, struct kobject *kobject) { + int rv; + if (down_interruptible(&efivars_lock)) return -EINTR;

+ if (__efivars) { + pr_warn("efivars already registered\n"); + rv = -EBUSY; + goto out; + } + efivars->ops = ops; efivars->kobject = kobject;

__efivars = efivars;

pr_info("Registered efivars operations\n"); - + rv = 0; +out: up(&efivars_lock);

- return 0; + return rv; } EXPORT_SYMBOL_GPL(efivars_register);

diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c index e00c33310517..753e7be039e4 100644 --- a/drivers/gpio/gpio-74x164.c +++ b/drivers/gpio/gpio-74x164.c @@ -127,8 +127,6 @@ static int gen_74x164_probe(struct spi_device *spi) if (IS_ERR(chip->gpiod_oe)) return PTR_ERR(chip->gpiod_oe);

- gpiod_set_value_cansleep(chip->gpiod_oe, 1); - spi_set_drvdata(spi, chip);

chip->gpio_chip.label = spi->modalias; @@ -153,6 +151,8 @@ static int gen_74x164_probe(struct spi_device *spi) goto exit_destroy; }

+ gpiod_set_value_cansleep(chip->gpiod_oe, 1); + ret = gpiochip_add_data(&chip->gpio_chip, chip); if (!ret) return 0; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 6d3e3454a6ed..9d8c78312403 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -784,11 +784,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,

ret = gpiochip_irqchip_init_valid_mask(gc); if (ret) - goto err_remove_acpi_chip; + goto err_free_hogs;

ret = gpiochip_irqchip_init_hw(gc); if (ret) - goto err_remove_acpi_chip; + goto err_remove_irqchip_mask;

ret = gpiochip_add_irqchip(gc, lock_key, request_key); if (ret) @@ -813,13 +813,13 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, gpiochip_irqchip_remove(gc); err_remove_irqchip_mask: gpiochip_irqchip_free_valid_mask(gc); -err_remove_acpi_chip: +err_free_hogs: + gpiochip_free_hogs(gc); acpi_gpiochip_remove(gc); + gpiochip_remove_pin_ranges(gc); err_remove_of_chip: - gpiochip_free_hogs(gc); of_gpiochip_remove(gc); err_free_gpiochip_mask: - gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); if (gdev->dev.release) { /* release() has been registered by gpiochip_setup_dev() */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 6fdf87a6e240..6c7b286e1123 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -51,8 +51,12 @@ endif endif

ifneq ($(CONFIG_FRAME_WARN),0) +ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) +frame_warn_flag := -Wframe-larger-than=3072 +else frame_warn_flag := -Wframe-larger-than=2048 endif +endif

CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index dc0a6fba7050..ff1032de4f76 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_device *adev) return 0; }

+static int si_set_temperature_range(struct amdgpu_device *adev) +{ + int ret; + + ret = si_thermal_enable_alert(adev, false); + if (ret) + return ret; + ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX); + if (ret) + return ret; + ret = si_thermal_enable_alert(adev, true); + if (ret) + return ret; + + return ret; +} + static void si_dpm_disable(struct amdgpu_device *adev) { struct rv7xx_power_info *pi = rv770_get_pi(adev); @@ -7608,6 +7625,18 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev,

static int si_dpm_late_init(void *handle) { + int ret; + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + if (!adev->pm.dpm_enabled) + return 0; + + ret = si_set_temperature_range(adev); + if (ret) + return ret; +#if 0 //TODO ? + si_dpm_powergate_uvd(adev, true); +#endif return 0; }

diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 7098f125b54a..fd32041f8226 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm, u64 start, u64 end, unsigned int order) { + u64 req_size = mm->chunk_size << order; struct drm_buddy_block *block; struct drm_buddy_block *buddy; LIST_HEAD(dfs); @@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm, if (drm_buddy_block_is_allocated(block)) continue;

+ if (block_start < start || block_end > end) { + u64 adjusted_start = max(block_start, start); + u64 adjusted_end = min(block_end, end); + + if (round_down(adjusted_end + 1, req_size) <= + round_up(adjusted_start, req_size)) + continue; + } + if (contains(start, end, block_start, block_end) && order == drm_buddy_block_order(block)) { /* diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 119544d88b58..fbac39aa38cc 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -316,32 +316,34 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) goto exit_afbcd;

if (has_components) { - ret = component_bind_all(drm->dev, drm); + ret = component_bind_all(dev, drm); if (ret) { dev_err(drm->dev, "Couldn't bind all components\n"); + /* Do not try to unbind */ + has_components = false; goto exit_afbcd; } }

ret = meson_encoder_hdmi_init(priv); if (ret) - goto unbind_all; + goto exit_afbcd;

ret = meson_plane_create(priv); if (ret) - goto unbind_all; + goto exit_afbcd;

ret = meson_overlay_create(priv); if (ret) - goto unbind_all; + goto exit_afbcd;

ret = meson_crtc_create(priv); if (ret) - goto unbind_all; + goto exit_afbcd;

ret = request_irq(priv->vsync_irq, meson_irq, 0, drm->driver->name, drm); if (ret) - goto unbind_all; + goto exit_afbcd;

drm_mode_config_reset(drm);

@@ -359,15 +361,18 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)

uninstall_irq: free_irq(priv->vsync_irq, drm); -unbind_all: - if (has_components) - component_unbind_all(drm->dev, drm); exit_afbcd: if (priv->afbcd.ops) priv->afbcd.ops->exit(priv); free_drm: drm_dev_put(drm);

+ meson_encoder_hdmi_remove(priv); + meson_encoder_cvbs_remove(priv); + + if (has_components) + component_unbind_all(dev, drm); + return ret; }

diff --git a/drivers/gpu/drm/meson/meson_encoder_cvbs.c b/drivers/gpu/drm/meson/meson_encoder_cvbs.c index 3f73b211fa8e..3407450435e2 100644 --- a/drivers/gpu/drm/meson/meson_encoder_cvbs.c +++ b/drivers/gpu/drm/meson/meson_encoder_cvbs.c @@ -294,6 +294,5 @@ void meson_encoder_cvbs_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_CVBS]) { meson_encoder_cvbs = priv->encoders[MESON_ENC_CVBS]; drm_bridge_remove(&meson_encoder_cvbs->bridge); - drm_bridge_remove(meson_encoder_cvbs->next_bridge); } } diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index b14e6e507c61..03062e7a02b6 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -472,6 +472,5 @@ void meson_encoder_hdmi_remove(struct meson_drm *priv) if (priv->encoders[MESON_ENC_HDMI]) { meson_encoder_hdmi = priv->encoders[MESON_ENC_HDMI]; drm_bridge_remove(&meson_encoder_hdmi->bridge); - drm_bridge_remove(meson_encoder_hdmi->next_bridge); } } diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 5fc55b9777cb..6806779f8ecc 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1252,9 +1252,26 @@ static int host1x_drm_probe(struct host1x_device *dev)

drm_mode_config_reset(drm);

- err = drm_aperture_remove_framebuffers(&tegra_drm_driver); - if (err < 0) - goto hub; + /* + * Only take over from a potential firmware framebuffer if any CRTCs + * have been registered. This must not be a fatal error because there + * are other accelerators that are exposed via this driver. + * + * Another case where this happens is on Tegra234 where the display + * hardware is no longer part of the host1x complex, so this driver + * will not expose any modesetting features. + */ + if (drm->mode_config.num_crtc > 0) { + err = drm_aperture_remove_framebuffers(&tegra_drm_driver); + if (err < 0) + goto hub; + } else { + /* + * Indicate to userspace that this doesn't expose any display + * capabilities. + */ + drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC); + }

err = tegra_drm_fb_init(drm); if (err < 0) diff --git a/drivers/infiniband/core/cm_trace.h b/drivers/infiniband/core/cm_trace.h index e9d282679ef1..944d9071245d 100644 --- a/drivers/infiniband/core/cm_trace.h +++ b/drivers/infiniband/core/cm_trace.h @@ -16,7 +16,7 @@

#include <linux/tracepoint.h> #include <rdma/ib_cm.h> -#include <trace/events/rdma.h> +#include <trace/misc/rdma.h>

/* * enum ib_cm_state, from include/rdma/ib_cm.h diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 0773ca7ace24..067d7f42871f 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3547,121 +3547,6 @@ static int cma_resolve_ib_addr(struct rdma_id_private *id_priv) return ret; }

-static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, - const struct sockaddr *dst_addr) -{ - struct sockaddr_storage zero_sock = {}; - - if (src_addr && src_addr->sa_family) - return rdma_bind_addr(id, src_addr); - - /* - * When the src_addr is not specified, automatically supply an any addr - */ - zero_sock.ss_family = dst_addr->sa_family; - if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { - struct sockaddr_in6 *src_addr6 = - (struct sockaddr_in6 *)&zero_sock; - struct sockaddr_in6 *dst_addr6 = - (struct sockaddr_in6 *)dst_addr; - - src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; - if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - id->route.addr.dev_addr.bound_dev_if = - dst_addr6->sin6_scope_id; - } else if (dst_addr->sa_family == AF_IB) { - ((struct sockaddr_ib *)&zero_sock)->sib_pkey = - ((struct sockaddr_ib *)dst_addr)->sib_pkey; - } - return rdma_bind_addr(id, (struct sockaddr *)&zero_sock); -} - -/* - * If required, resolve the source address for bind and leave the id_priv in - * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior - * calls made by ULP, a previously bound ID will not be re-bound and src_addr is - * ignored. - */ -static int resolve_prepare_src(struct rdma_id_private *id_priv, - struct sockaddr *src_addr, - const struct sockaddr *dst_addr) -{ - int ret; - - memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); - if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { - /* For a well behaved ULP state will be RDMA_CM_IDLE */ - ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); - if (ret) - goto err_dst; - if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, - RDMA_CM_ADDR_QUERY))) { - ret = -EINVAL; - goto err_dst; - } - } - - if (cma_family(id_priv) != dst_addr->sa_family) { - ret = -EINVAL; - goto err_state; - } - return 0; - -err_state: - cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); -err_dst: - memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr)); - return ret; -} - -int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, - const struct sockaddr *dst_addr, unsigned long timeout_ms) -{ - struct rdma_id_private *id_priv = - container_of(id, struct rdma_id_private, id); - int ret; - - ret = resolve_prepare_src(id_priv, src_addr, dst_addr); - if (ret) - return ret; - - if (cma_any_addr(dst_addr)) { - ret = cma_resolve_loopback(id_priv); - } else { - if (dst_addr->sa_family == AF_IB) { - ret = cma_resolve_ib_addr(id_priv); - } else { - /* - * The FSM can return back to RDMA_CM_ADDR_BOUND after - * rdma_resolve_ip() is called, eg through the error - * path in addr_handler(). If this happens the existing - * request must be canceled before issuing a new one. - * Since canceling a request is a bit slow and this - * oddball path is rare, keep track once a request has - * been issued. The track turns out to be a permanent - * state since this is the only cancel as it is - * immediately before rdma_resolve_ip(). - */ - if (id_priv->used_resolve_ip) - rdma_addr_cancel(&id->route.addr.dev_addr); - else - id_priv->used_resolve_ip = 1; - ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, - &id->route.addr.dev_addr, - timeout_ms, addr_handler, - false, id_priv); - } - } - if (ret) - goto err; - - return 0; -err: - cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); - return ret; -} -EXPORT_SYMBOL(rdma_resolve_addr); - int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) { struct rdma_id_private *id_priv; @@ -4064,27 +3949,26 @@ int rdma_listen(struct rdma_cm_id *id, int backlog) } EXPORT_SYMBOL(rdma_listen);

-int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) +static int rdma_bind_addr_dst(struct rdma_id_private *id_priv, + struct sockaddr *addr, const struct sockaddr *daddr) { - struct rdma_id_private *id_priv; + struct sockaddr *id_daddr; int ret; - struct sockaddr *daddr;

if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 && addr->sa_family != AF_IB) return -EAFNOSUPPORT;

- id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND)) return -EINVAL;

- ret = cma_check_linklocal(&id->route.addr.dev_addr, addr); + ret = cma_check_linklocal(&id_priv->id.route.addr.dev_addr, addr); if (ret) goto err1;

memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!cma_any_addr(addr)) { - ret = cma_translate_addr(addr, &id->route.addr.dev_addr); + ret = cma_translate_addr(addr, &id_priv->id.route.addr.dev_addr); if (ret) goto err1;

@@ -4104,8 +3988,10 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) } #endif } - daddr = cma_dst_addr(id_priv); - daddr->sa_family = addr->sa_family; + id_daddr = cma_dst_addr(id_priv); + if (daddr != id_daddr) + memcpy(id_daddr, daddr, rdma_addr_size(addr)); + id_daddr->sa_family = addr->sa_family;

ret = cma_get_port(id_priv); if (ret) @@ -4121,6 +4007,129 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE); return ret; } + +static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, + const struct sockaddr *dst_addr) +{ + struct rdma_id_private *id_priv = + container_of(id, struct rdma_id_private, id); + struct sockaddr_storage zero_sock = {}; + + if (src_addr && src_addr->sa_family) + return rdma_bind_addr_dst(id_priv, src_addr, dst_addr); + + /* + * When the src_addr is not specified, automatically supply an any addr + */ + zero_sock.ss_family = dst_addr->sa_family; + if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { + struct sockaddr_in6 *src_addr6 = + (struct sockaddr_in6 *)&zero_sock; + struct sockaddr_in6 *dst_addr6 = + (struct sockaddr_in6 *)dst_addr; + + src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; + if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) + id->route.addr.dev_addr.bound_dev_if = + dst_addr6->sin6_scope_id; + } else if (dst_addr->sa_family == AF_IB) { + ((struct sockaddr_ib *)&zero_sock)->sib_pkey = + ((struct sockaddr_ib *)dst_addr)->sib_pkey; + } + return rdma_bind_addr_dst(id_priv, (struct sockaddr *)&zero_sock, dst_addr); +} + +/* + * If required, resolve the source address for bind and leave the id_priv in + * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior + * calls made by ULP, a previously bound ID will not be re-bound and src_addr is + * ignored. + */ +static int resolve_prepare_src(struct rdma_id_private *id_priv, + struct sockaddr *src_addr, + const struct sockaddr *dst_addr) +{ + int ret; + + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { + /* For a well behaved ULP state will be RDMA_CM_IDLE */ + ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); + if (ret) + return ret; + if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, + RDMA_CM_ADDR_QUERY))) + return -EINVAL; + + } else { + memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); + } + + if (cma_family(id_priv) != dst_addr->sa_family) { + ret = -EINVAL; + goto err_state; + } + return 0; + +err_state: + cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); + return ret; +} + +int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, + const struct sockaddr *dst_addr, unsigned long timeout_ms) +{ + struct rdma_id_private *id_priv = + container_of(id, struct rdma_id_private, id); + int ret; + + ret = resolve_prepare_src(id_priv, src_addr, dst_addr); + if (ret) + return ret; + + if (cma_any_addr(dst_addr)) { + ret = cma_resolve_loopback(id_priv); + } else { + if (dst_addr->sa_family == AF_IB) { + ret = cma_resolve_ib_addr(id_priv); + } else { + /* + * The FSM can return back to RDMA_CM_ADDR_BOUND after + * rdma_resolve_ip() is called, eg through the error + * path in addr_handler(). If this happens the existing + * request must be canceled before issuing a new one. + * Since canceling a request is a bit slow and this + * oddball path is rare, keep track once a request has + * been issued. The track turns out to be a permanent + * state since this is the only cancel as it is + * immediately before rdma_resolve_ip(). + */ + if (id_priv->used_resolve_ip) + rdma_addr_cancel(&id->route.addr.dev_addr); + else + id_priv->used_resolve_ip = 1; + ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, + &id->route.addr.dev_addr, + timeout_ms, addr_handler, + false, id_priv); + } + } + if (ret) + goto err; + + return 0; +err: + cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); + return ret; +} +EXPORT_SYMBOL(rdma_resolve_addr); + +int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) +{ + struct rdma_id_private *id_priv = + container_of(id, struct rdma_id_private, id); + + return rdma_bind_addr_dst(id_priv, addr, cma_dst_addr(id_priv)); +} EXPORT_SYMBOL(rdma_bind_addr);

static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv) diff --git a/drivers/infiniband/core/cma_trace.h b/drivers/infiniband/core/cma_trace.h index e45264267bcc..47f3c6e4be89 100644 --- a/drivers/infiniband/core/cma_trace.h +++ b/drivers/infiniband/core/cma_trace.h @@ -15,7 +15,7 @@ #define _TRACE_RDMA_CMA_H

#include <linux/tracepoint.h> -#include <trace/events/rdma.h> +#include <trace/misc/rdma.h>

DECLARE_EVENT_CLASS(cma_fsm_class, diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index d96c78e436f9..5c284dfbe692 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -131,6 +131,11 @@ struct ib_umad_packet { struct ib_user_mad mad; };

+struct ib_rmpp_mad_hdr { + struct ib_mad_hdr mad_hdr; + struct ib_rmpp_hdr rmpp_hdr; +} __packed; + #define CREATE_TRACE_POINTS #include <trace/events/ib_umad.h>

@@ -494,11 +499,11 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_umad_file *file = filp->private_data; + struct ib_rmpp_mad_hdr *rmpp_mad_hdr; struct ib_umad_packet *packet; struct ib_mad_agent *agent; struct rdma_ah_attr ah_attr; struct ib_ah *ah; - struct ib_rmpp_mad *rmpp_mad; __be64 *tid; int ret, data_len, hdr_len, copy_offset, rmpp_active; u8 base_version; @@ -506,7 +511,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, if (count < hdr_size(file) + IB_MGMT_RMPP_HDR) return -EINVAL;

- packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL); + packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL); if (!packet) return -ENOMEM;

@@ -560,13 +565,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, goto err_up; }

- rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data; - hdr_len = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class); + rmpp_mad_hdr = (struct ib_rmpp_mad_hdr *)packet->mad.data; + hdr_len = ib_get_mad_data_offset(rmpp_mad_hdr->mad_hdr.mgmt_class);

- if (ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class) + if (ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) && ib_mad_kernel_rmpp_agent(agent)) { copy_offset = IB_MGMT_RMPP_HDR; - rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & + rmpp_active = ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE; } else { copy_offset = IB_MGMT_MAD_HDR; @@ -615,12 +620,12 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, tid = &((struct ib_mad_hdr *) packet->msg->mad)->tid; *tid = cpu_to_be64(((u64) agent->hi_tid) << 32 | (be64_to_cpup(tid) & 0xffffffff)); - rmpp_mad->mad_hdr.tid = *tid; + rmpp_mad_hdr->mad_hdr.tid = *tid; }

if (!ib_mad_kernel_rmpp_agent(agent) - && ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class) - && (ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { + && ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) + && (ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { spin_lock_irq(&file->send_lock); list_add_tail(&packet->list, &file->send_list); spin_unlock_irq(&file->send_lock); diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 02f3bc4e4895..13c36f51b935 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -564,6 +564,9 @@ struct xboxone_init_packet { #define GIP_MOTOR_LT BIT(3) #define GIP_MOTOR_ALL (GIP_MOTOR_R | GIP_MOTOR_L | GIP_MOTOR_RT | GIP_MOTOR_LT)

+#define GIP_WIRED_INTF_DATA 0 +#define GIP_WIRED_INTF_AUDIO 1 + /* * This packet is required for all Xbox One pads with 2015 * or later firmware installed (or present from the factory). @@ -2008,7 +2011,7 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id }

if (xpad->xtype == XTYPE_XBOXONE && - intf->cur_altsetting->desc.bInterfaceNumber != 0) { + intf->cur_altsetting->desc.bInterfaceNumber != GIP_WIRED_INTF_DATA) { /* * The Xbox One controller lists three interfaces all with the * same interface class, subclass and protocol. Differentiate by diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 1d9494f64a21..4526ff2e1bd5 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -29,7 +29,6 @@ static LIST_HEAD(icc_providers); static int providers_count; static bool synced_state; static DEFINE_MUTEX(icc_lock); -static DEFINE_MUTEX(icc_bw_lock); static struct dentry *icc_debugfs_dir;

static void icc_summary_show_one(struct seq_file *s, struct icc_node *n) @@ -636,7 +635,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) if (WARN_ON(IS_ERR(path) || !path->num_nodes)) return -EINVAL;

- mutex_lock(&icc_bw_lock); + mutex_lock(&icc_lock);

old_avg = path->reqs[0].avg_bw; old_peak = path->reqs[0].peak_bw; @@ -668,7 +667,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw) apply_constraints(path); }

- mutex_unlock(&icc_bw_lock); + mutex_unlock(&icc_lock);

trace_icc_set_bw_end(path, ret);

@@ -971,7 +970,6 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) return;

mutex_lock(&icc_lock); - mutex_lock(&icc_bw_lock);

node->provider = provider; list_add_tail(&node->node_list, &provider->nodes); @@ -997,7 +995,6 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) node->avg_bw = 0; node->peak_bw = 0;

- mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_node_add); @@ -1137,7 +1134,6 @@ void icc_sync_state(struct device *dev) return;

mutex_lock(&icc_lock); - mutex_lock(&icc_bw_lock); synced_state = true; list_for_each_entry(p, &icc_providers, provider_list) { dev_dbg(p->dev, "interconnect provider is in synced state\n"); @@ -1150,21 +1146,13 @@ void icc_sync_state(struct device *dev) } } } - mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); } EXPORT_SYMBOL_GPL(icc_sync_state);

static int __init icc_init(void) { - struct device_node *root; - - /* Teach lockdep about lock ordering wrt. shrinker: */ - fs_reclaim_acquire(GFP_KERNEL); - might_lock(&icc_bw_lock); - fs_reclaim_release(GFP_KERNEL); - - root = of_find_node_by_path("/"); + struct device_node *root = of_find_node_by_path("/");

providers_count = of_count_icc_providers(root); of_node_put(root); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 8966f7d5aab6..82f100e591b5 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -152,6 +152,18 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q) q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons); }

+static void queue_sync_cons_ovf(struct arm_smmu_queue *q) +{ + struct arm_smmu_ll_queue *llq = &q->llq; + + if (likely(Q_OVF(llq->prod) == Q_OVF(llq->cons))) + return; + + llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | + Q_IDX(llq, llq->cons); + queue_sync_cons_out(q); +} + static int queue_sync_prod_in(struct arm_smmu_queue *q) { u32 prod; @@ -1583,8 +1595,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev) } while (!queue_empty(llq));

/* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); + queue_sync_cons_ovf(q); return IRQ_HANDLED; }

@@ -1642,9 +1653,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev) } while (!queue_empty(llq));

/* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); - queue_sync_cons_out(q); + queue_sync_cons_ovf(q); return IRQ_HANDLED; }

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index d80065c8105a..f15dcb9e4175 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -267,12 +267,26 @@ static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain,

static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu) { - unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + unsigned int last_s2cr; u32 reg; u32 smr; int i;

+ /* + * Some platforms support more than the Arm SMMU architected maximum of + * 128 stream matching groups. For unknown reasons, the additional + * groups don't exhibit the same behavior as the architected registers, + * so limit the groups to 128 until the behavior is fixed for the other + * groups. + */ + if (smmu->num_mapping_groups > 128) { + dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n"); + smmu->num_mapping_groups = 128; + } + + last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); + /* * With some firmware versions writes to S2CR of type FAULT are * ignored, and writing BYPASS will end up written as FAULT in the diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index 8261066de07d..e4358393fe37 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -152,13 +152,6 @@ static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type) return &dom->domain; }

-static void sprd_iommu_domain_free(struct iommu_domain *domain) -{ - struct sprd_iommu_domain *dom = to_sprd_domain(domain); - - kfree(dom); -} - static void sprd_iommu_first_vpn(struct sprd_iommu_domain *dom) { struct sprd_iommu_device *sdev = dom->sdev; @@ -231,6 +224,28 @@ static void sprd_iommu_hw_en(struct sprd_iommu_device *sdev, bool en) sprd_iommu_update_bits(sdev, reg_cfg, mask, 0, val); }

+static void sprd_iommu_cleanup(struct sprd_iommu_domain *dom) +{ + size_t pgt_size; + + /* Nothing need to do if the domain hasn't been attached */ + if (!dom->sdev) + return; + + pgt_size = sprd_iommu_pgt_size(&dom->domain); + dma_free_coherent(dom->sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa); + dom->sdev = NULL; + sprd_iommu_hw_en(dom->sdev, false); +} + +static void sprd_iommu_domain_free(struct iommu_domain *domain) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + + sprd_iommu_cleanup(dom); + kfree(dom); +} + static int sprd_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index a46ce0868fe1..3a927452a650 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1007,10 +1007,12 @@ static int mmc_select_bus_width(struct mmc_card *card) static unsigned ext_csd_bits[] = { EXT_CSD_BUS_WIDTH_8, EXT_CSD_BUS_WIDTH_4, + EXT_CSD_BUS_WIDTH_1, }; static unsigned bus_widths[] = { MMC_BUS_WIDTH_8, MMC_BUS_WIDTH_4, + MMC_BUS_WIDTH_1, }; struct mmc_host *host = card->host; unsigned idx, bus_width = 0; diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 60bca78a72b1..0511583ffa76 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -200,6 +200,8 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) struct scatterlist *sg; int i;

+ host->dma_in_progress = true; + if (!host->variant->dma_lli || data->sg_len == 1 || idma->use_bounce_buffer) { u32 dma_addr; @@ -238,9 +240,30 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) return 0; }

+static void sdmmc_idma_error(struct mmci_host *host) +{ + struct mmc_data *data = host->data; + struct sdmmc_idma *idma = host->dma_priv; + + if (!dma_inprogress(host)) + return; + + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; + data->host_cookie = 0; + + if (!idma->use_bounce_buffer) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + mmc_get_dma_dir(data)); +} + static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data) { + if (!dma_inprogress(host)) + return; + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false;

if (!data->host_cookie) sdmmc_idma_unprep_data(host, data, 0); @@ -567,6 +590,7 @@ static struct mmci_host_ops sdmmc_variant_ops = { .dma_setup = sdmmc_idma_setup, .dma_start = sdmmc_idma_start, .dma_finalize = sdmmc_idma_finalize, + .dma_error = sdmmc_idma_error, .set_clkreg = mmci_sdmmc_set_clkreg, .set_pwrreg = mmci_sdmmc_set_pwrreg, .busy_complete = sdmmc_busy_complete, diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c index 8cf3a375de65..cc9d28b75eb9 100644 --- a/drivers/mmc/host/sdhci-xenon-phy.c +++ b/drivers/mmc/host/sdhci-xenon-phy.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/ktime.h> +#include <linux/iopoll.h> #include <linux/of_address.h>

#include "sdhci-pltfm.h" @@ -109,6 +110,8 @@ #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST (XENON_EMMC_PHY_REG_BASE + 0x18) #define XENON_LOGIC_TIMING_VALUE 0x00AA8977

+#define XENON_MAX_PHY_TIMEOUT_LOOPS 100 + /* * List offset of PHY registers and some special register values * in eMMC PHY 5.0 or eMMC PHY 5.1 @@ -216,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct sdhci_host *host) return 0; }

+static int xenon_check_stability_internal_clk(struct sdhci_host *host) +{ + u32 reg; + int err; + + err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE, + 1100, 20000, false, host, SDHCI_CLOCK_CONTROL); + if (err) + dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n"); + + return err; +} + /* * eMMC 5.0/5.1 PHY init/re-init. * eMMC PHY init should be executed after: @@ -232,6 +248,11 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host); struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;

+ int ret = xenon_check_stability_internal_clk(host); + + if (ret) + return ret; + reg = sdhci_readl(host, phy_regs->timing_adj); reg |= XENON_PHY_INITIALIZAION; sdhci_writel(host, reg, phy_regs->timing_adj); @@ -259,18 +280,27 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) /* get the wait time */ wait /= clock; wait++; - /* wait for host eMMC PHY init completes */ - udelay(wait);

- reg = sdhci_readl(host, phy_regs->timing_adj); - reg &= XENON_PHY_INITIALIZAION; - if (reg) { + /* + * AC5X spec says bit must be polled until zero. + * We see cases in which timeout can take longer + * than the standard calculation on AC5X, which is + * expected following the spec comment above. + * According to the spec, we must wait as long as + * it takes for that bit to toggle on AC5X. + * Cap that with 100 delay loops so we won't get + * stuck here forever: + */ + + ret = read_poll_timeout(sdhci_readl, reg, + !(reg & XENON_PHY_INITIALIZAION), + wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait, + false, host, phy_regs->timing_adj); + if (ret) dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n", - wait); - return -ETIMEDOUT; - } + wait * XENON_MAX_PHY_TIMEOUT_LOOPS);

- return 0; + return ret; }

#define ARMADA_3700_SOC_PAD_1_8V 0x1 diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c index 6b043e24855f..9116ee7f023e 100644 --- a/drivers/mtd/nand/spi/gigadevice.c +++ b/drivers/mtd/nand/spi/gigadevice.c @@ -186,7 +186,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand, { u8 status2; struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2, - &status2); + spinand->scratchbuf); int ret;

switch (status & STATUS_ECC_MASK) { @@ -207,6 +207,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand, * report the maximum of 4 in this case */ /* bits sorted this way (3...0): ECCS1,ECCS0,ECCSE1,ECCSE0 */ + status2 = *(spinand->scratchbuf); return ((status & STATUS_ECC_MASK) >> 2) | ((status2 & STATUS_ECC_MASK) >> 4);

@@ -228,7 +229,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand, { u8 status2; struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2, - &status2); + spinand->scratchbuf); int ret;

switch (status & STATUS_ECC_MASK) { @@ -248,6 +249,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand, * 1 ... 4 bits are flipped (and corrected) */ /* bits sorted this way (1...0): ECCSE1, ECCSE0 */ + status2 = *(spinand->scratchbuf); return ((status2 & STATUS_ECC_MASK) >> 4) + 1;

case STATUS_ECC_UNCOR_ERROR: diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 1917da784191..5a274b99f299 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -84,7 +84,6 @@ source "drivers/net/ethernet/huawei/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" -source "drivers/net/ethernet/wangxun/Kconfig" source "drivers/net/ethernet/xscale/Kconfig"

config JME @@ -189,6 +188,7 @@ source "drivers/net/ethernet/toshiba/Kconfig" source "drivers/net/ethernet/tundra/Kconfig" source "drivers/net/ethernet/vertexcom/Kconfig" source "drivers/net/ethernet/via/Kconfig" +source "drivers/net/ethernet/wangxun/Kconfig" source "drivers/net/ethernet/wiznet/Kconfig" source "drivers/net/ethernet/xilinx/Kconfig" source "drivers/net/ethernet/xircom/Kconfig" diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 07171e574e7d..36e62197fba0 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -976,7 +976,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)

igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); /* adjust timestamp for the TX latency based on link speed */ - if (adapter->hw.mac.type == e1000_i210) { + if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) { switch (adapter->link_speed) { case SPEED_10: adjust = IGB_I210_TX_LATENCY_10; @@ -1022,6 +1022,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, ktime_t *timestamp) { struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; struct skb_shared_hwtstamps ts; __le64 *regval = (__le64 *)va; int adjust = 0; @@ -1041,7 +1042,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1]));

/* adjust timestamp for the RX latency based on link speed */ - if (adapter->hw.mac.type == e1000_i210) { + if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) { switch (adapter->link_speed) { case SPEED_10: adjust = IGB_I210_RX_LATENCY_10; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index dc2e204bcd72..41eac7dfb67e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -52,8 +52,10 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, max_regions = max_tcam_regions;

tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL); - if (!tcam->used_regions) - return -ENOMEM; + if (!tcam->used_regions) { + err = -ENOMEM; + goto err_alloc_used_regions; + } tcam->max_regions = max_regions;

max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS); @@ -78,6 +80,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, bitmap_free(tcam->used_groups); err_alloc_used_groups: bitmap_free(tcam->used_regions); +err_alloc_used_regions: + mutex_destroy(&tcam->lock); return err; }

@@ -86,10 +90,10 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;

- mutex_destroy(&tcam->lock); ops->fini(mlxsw_sp, tcam->priv); bitmap_free(tcam->used_groups); bitmap_free(tcam->used_regions); + mutex_destroy(&tcam->lock); }

int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 91b2aa81914b..e2d51014ab4b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3900,8 +3900,10 @@ static void stmmac_fpe_stop_wq(struct stmmac_priv *priv) { set_bit(__FPE_REMOVING, &priv->fpe_task_state);

- if (priv->fpe_wq) + if (priv->fpe_wq) { destroy_workqueue(priv->fpe_wq); + priv->fpe_wq = NULL; + }

netdev_info(priv->dev, "FPE workqueue stop"); } diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 937dd9cf4fba..7086acfed5b9 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1902,26 +1902,26 @@ static int __init gtp_init(void)

get_random_bytes(&gtp_h_initval, sizeof(gtp_h_initval));

- err = rtnl_link_register(&gtp_link_ops); + err = register_pernet_subsys(&gtp_net_ops); if (err < 0) goto error_out;

- err = register_pernet_subsys(&gtp_net_ops); + err = rtnl_link_register(&gtp_link_ops); if (err < 0) - goto unreg_rtnl_link; + goto unreg_pernet_subsys;

err = genl_register_family(&gtp_genl_family); if (err < 0) - goto unreg_pernet_subsys; + goto unreg_rtnl_link;

pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", sizeof(struct pdp_ctx)); return 0;

-unreg_pernet_subsys: - unregister_pernet_subsys(&gtp_net_ops); unreg_rtnl_link: rtnl_link_unregister(&gtp_link_ops); +unreg_pernet_subsys: + unregister_pernet_subsys(&gtp_net_ops); error_out: pr_err("error loading GTP module loaded\n"); return err; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 367255bb44cd..922d6f16d99d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -653,6 +653,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; + ntfile->xdp_rxq.queue_index = index; rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], NULL);

diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 99ec1d4a972d..8b6d6a1b3c2e 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -232,7 +232,7 @@ static int dm9601_mdio_read(struct net_device *netdev, int phy_id, int loc) err = dm_read_shared_word(dev, 1, loc, &res); if (err < 0) { netdev_err(dev->net, "MDIO read error: %d\n", err); - return err; + return 0; }

netdev_dbg(dev->net, diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index c458c030fadf..4fd456381129 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1501,7 +1501,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)

lan78xx_rx_urb_submit_all(dev);

+ local_bh_disable(); napi_schedule(&dev->napi); + local_bh_enable(); }

return 0; @@ -3035,7 +3037,8 @@ static int lan78xx_reset(struct lan78xx_net *dev) if (dev->chipid == ID_REV_CHIP_ID_7801_) buf &= ~MAC_CR_GMII_EN_;

- if (dev->chipid == ID_REV_CHIP_ID_7800_) { + if (dev->chipid == ID_REV_CHIP_ID_7800_ || + dev->chipid == ID_REV_CHIP_ID_7850_) { ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig); if (!ret && sig != EEPROM_INDICATOR) { /* Implies there is no external eeprom. Set mac speed */ diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 36c5a41f84e4..dd9f5f146192 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1135,14 +1135,6 @@ static int veth_enable_xdp(struct net_device *dev) veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true); return err; } - - if (!veth_gro_requested(dev)) { - /* user-space did not require GRO, but adding XDP - * is supposed to get GRO working - */ - dev->features |= NETIF_F_GRO; - netdev_features_change(dev); - } } }

@@ -1162,18 +1154,9 @@ static void veth_disable_xdp(struct net_device *dev) for (i = 0; i < dev->real_num_rx_queues; i++) rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);

- if (!netif_running(dev) || !veth_gro_requested(dev)) { + if (!netif_running(dev) || !veth_gro_requested(dev)) veth_napi_del(dev);

- /* if user-space did not require GRO, since adding XDP - * enabled it, clear it now - */ - if (!veth_gro_requested(dev) && netif_running(dev)) { - dev->features &= ~NETIF_F_GRO; - netdev_features_change(dev); - } - } - veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false); }

@@ -1376,7 +1359,8 @@ static int veth_alloc_queues(struct net_device *dev) struct veth_priv *priv = netdev_priv(dev); int i;

- priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT); + priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq), + GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!priv->rq) return -ENOMEM;

@@ -1392,7 +1376,7 @@ static void veth_free_queues(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev);

- kfree(priv->rq); + kvfree(priv->rq); }

static int veth_dev_init(struct net_device *dev) @@ -1558,6 +1542,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, }

if (!old_prog) { + if (!veth_gro_requested(dev)) { + /* user-space did not require GRO, but adding + * XDP is supposed to get GRO working + */ + dev->features |= NETIF_F_GRO; + netdev_features_change(dev); + } + peer->hw_features &= ~NETIF_F_GSO_SOFTWARE; peer->max_mtu = max_mtu; } @@ -1568,6 +1560,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (dev->flags & IFF_UP) veth_disable_xdp(dev);

+ /* if user-space did not require GRO, since adding XDP + * enabled it, clear it now + */ + if (!veth_gro_requested(dev)) { + dev->features &= ~NETIF_F_GRO; + netdev_features_change(dev); + } + if (peer) { peer->hw_features |= NETIF_F_GSO_SOFTWARE; peer->max_mtu = ETH_MAX_MTU; diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 4402871b5c0c..e663d5585a05 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -45,8 +45,8 @@ struct target {

/** * struct fragment - info about fragment nodes in overlay expanded device tree - * @target: target of the overlay operation * @overlay: pointer to the __overlay__ node + * @target: target of the overlay operation */ struct fragment { struct device_node *overlay; diff --git a/drivers/of/property.c b/drivers/of/property.c index 33d5f16c8120..da5d71219770 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1332,7 +1332,7 @@ static struct device_node *parse_remote_endpoint(struct device_node *np, int index) { /* Return NULL for index > 0 to signify end of remote-endpoints. */ - if (!index || strcmp(prop_name, "remote-endpoint")) + if (index > 0 || strcmp(prop_name, "remote-endpoint")) return NULL;

return of_graph_get_remote_port_parent(np); diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c index ad99707b3b99..dd7d74fecc48 100644 --- a/drivers/pci/controller/dwc/pci-layerscape-ep.c +++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c @@ -18,6 +18,20 @@

#include "pcie-designware.h"

+#define PEX_PF0_CONFIG 0xC0014 +#define PEX_PF0_CFG_READY BIT(0) + +/* PEX PFa PCIE PME and message interrupt registers*/ +#define PEX_PF0_PME_MES_DR 0xC0020 +#define PEX_PF0_PME_MES_DR_LUD BIT(7) +#define PEX_PF0_PME_MES_DR_LDD BIT(9) +#define PEX_PF0_PME_MES_DR_HRD BIT(10) + +#define PEX_PF0_PME_MES_IER 0xC0028 +#define PEX_PF0_PME_MES_IER_LUDIE BIT(7) +#define PEX_PF0_PME_MES_IER_LDDIE BIT(9) +#define PEX_PF0_PME_MES_IER_HRDIE BIT(10) + #define to_ls_pcie_ep(x) dev_get_drvdata((x)->dev)

struct ls_pcie_ep_drvdata { @@ -30,8 +44,99 @@ struct ls_pcie_ep { struct dw_pcie *pci; struct pci_epc_features *ls_epc; const struct ls_pcie_ep_drvdata *drvdata; + int irq; + u32 lnkcap; + bool big_endian; };

+static u32 ls_lut_readl(struct ls_pcie_ep *pcie, u32 offset) +{ + struct dw_pcie *pci = pcie->pci; + + if (pcie->big_endian) + return ioread32be(pci->dbi_base + offset); + else + return ioread32(pci->dbi_base + offset); +} + +static void ls_lut_writel(struct ls_pcie_ep *pcie, u32 offset, u32 value) +{ + struct dw_pcie *pci = pcie->pci; + + if (pcie->big_endian) + iowrite32be(value, pci->dbi_base + offset); + else + iowrite32(value, pci->dbi_base + offset); +} + +static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id) +{ + struct ls_pcie_ep *pcie = dev_id; + struct dw_pcie *pci = pcie->pci; + u32 val, cfg; + u8 offset; + + val = ls_lut_readl(pcie, PEX_PF0_PME_MES_DR); + ls_lut_writel(pcie, PEX_PF0_PME_MES_DR, val); + + if (!val) + return IRQ_NONE; + + if (val & PEX_PF0_PME_MES_DR_LUD) { + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + /* + * The values of the Maximum Link Width and Supported Link + * Speed from the Link Capabilities Register will be lost + * during link down or hot reset. Restore initial value + * that configured by the Reset Configuration Word (RCW). + */ + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, pcie->lnkcap); + dw_pcie_dbi_ro_wr_dis(pci); + + cfg = ls_lut_readl(pcie, PEX_PF0_CONFIG); + cfg |= PEX_PF0_CFG_READY; + ls_lut_writel(pcie, PEX_PF0_CONFIG, cfg); + dw_pcie_ep_linkup(&pci->ep); + + dev_dbg(pci->dev, "Link up\n"); + } else if (val & PEX_PF0_PME_MES_DR_LDD) { + dev_dbg(pci->dev, "Link down\n"); + } else if (val & PEX_PF0_PME_MES_DR_HRD) { + dev_dbg(pci->dev, "Hot reset\n"); + } + + return IRQ_HANDLED; +} + +static int ls_pcie_ep_interrupt_init(struct ls_pcie_ep *pcie, + struct platform_device *pdev) +{ + u32 val; + int ret; + + pcie->irq = platform_get_irq_byname(pdev, "pme"); + if (pcie->irq < 0) + return pcie->irq; + + ret = devm_request_irq(&pdev->dev, pcie->irq, ls_pcie_ep_event_handler, + IRQF_SHARED, pdev->name, pcie); + if (ret) { + dev_err(&pdev->dev, "Can't register PCIe IRQ\n"); + return ret; + } + + /* Enable interrupts */ + val = ls_lut_readl(pcie, PEX_PF0_PME_MES_IER); + val |= PEX_PF0_PME_MES_IER_LDDIE | PEX_PF0_PME_MES_IER_HRDIE | + PEX_PF0_PME_MES_IER_LUDIE; + ls_lut_writel(pcie, PEX_PF0_PME_MES_IER, val); + + return 0; +} + static const struct pci_epc_features* ls_pcie_ep_get_features(struct dw_pcie_ep *ep) { @@ -124,6 +229,8 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev) struct ls_pcie_ep *pcie; struct pci_epc_features *ls_epc; struct resource *dbi_base; + u8 offset; + int ret;

pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); if (!pcie) @@ -143,6 +250,7 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev) pci->ops = pcie->drvdata->dw_pcie_ops;

ls_epc->bar_fixed_64bit = (1 << BAR_2) | (1 << BAR_4); + ls_epc->linkup_notifier = true;

pcie->pci = pci; pcie->ls_epc = ls_epc; @@ -154,9 +262,18 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev)

pci->ep.ops = &ls_pcie_ep_ops;

+ pcie->big_endian = of_property_read_bool(dev->of_node, "big-endian"); + platform_set_drvdata(pdev, pcie);

- return dw_pcie_ep_init(&pci->ep); + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + pcie->lnkcap = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + + ret = dw_pcie_ep_init(&pci->ep); + if (ret) + return ret; + + return ls_pcie_ep_interrupt_init(pcie, pdev); }

static struct platform_driver ls_pcie_ep_driver = { diff --git a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c index e625b32889bf..0928a526e2ab 100644 --- a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c +++ b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c @@ -706,7 +706,7 @@ static int mixel_dphy_probe(struct platform_device *pdev) return ret; }

- priv->id = of_alias_get_id(np, "mipi_dphy"); + priv->id = of_alias_get_id(np, "mipi-dphy"); if (priv->id < 0) { dev_err(dev, "Failed to get phy node alias id: %d\n", priv->id); diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index 0713a52a2510..17b37354e32c 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -209,7 +209,9 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client) { struct bq27xxx_device_info *di = i2c_get_clientdata(client);

- free_irq(client->irq, di); + if (client->irq) + free_irq(client->irq, di); + bq27xxx_battery_teardown(di);

mutex_lock(&battery_mutex); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 5c5954b78585..edd296f950a3 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -185,39 +185,37 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason) __scsi_queue_insert(cmd, reason, true); }

- /** - * __scsi_execute - insert request and wait for the result - * @sdev: scsi device + * scsi_execute_cmd - insert request and wait for the result + * @sdev: scsi_device * @cmd: scsi command - * @data_direction: data direction + * @opf: block layer request cmd_flags * @buffer: data buffer * @bufflen: len of buffer - * @sense: optional sense buffer - * @sshdr: optional decoded sense header * @timeout: request timeout in HZ * @retries: number of times to retry request - * @flags: flags for ->cmd_flags - * @rq_flags: flags for ->rq_flags - * @resid: optional residual length + * @args: Optional args. See struct definition for field descriptions * * Returns the scsi_cmnd result field if a command was executed, or a negative * Linux error code if we didn't get that far. */ -int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, - int data_direction, void *buffer, unsigned bufflen, - unsigned char *sense, struct scsi_sense_hdr *sshdr, - int timeout, int retries, blk_opf_t flags, - req_flags_t rq_flags, int *resid) +int scsi_execute_cmd(struct scsi_device *sdev, const unsigned char *cmd, + blk_opf_t opf, void *buffer, unsigned int bufflen, + int timeout, int retries, + const struct scsi_exec_args *args) { + static const struct scsi_exec_args default_args; struct request *req; struct scsi_cmnd *scmd; int ret;

- req = scsi_alloc_request(sdev->request_queue, - data_direction == DMA_TO_DEVICE ? - REQ_OP_DRV_OUT : REQ_OP_DRV_IN, - rq_flags & RQF_PM ? BLK_MQ_REQ_PM : 0); + if (!args) + args = &default_args; + else if (WARN_ON_ONCE(args->sense && + args->sense_len != SCSI_SENSE_BUFFERSIZE)) + return -EINVAL; + + req = scsi_alloc_request(sdev->request_queue, opf, args->req_flags); if (IS_ERR(req)) return PTR_ERR(req);

@@ -232,8 +230,7 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, memcpy(scmd->cmnd, cmd, scmd->cmd_len); scmd->allowed = retries; req->timeout = timeout; - req->cmd_flags |= flags; - req->rq_flags |= rq_flags | RQF_QUIET; + req->rq_flags |= RQF_QUIET;

/* * head injection *required* here otherwise quiesce won't work @@ -249,20 +246,21 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, if (unlikely(scmd->resid_len > 0 && scmd->resid_len <= bufflen)) memset(buffer + bufflen - scmd->resid_len, 0, scmd->resid_len);

- if (resid) - *resid = scmd->resid_len; - if (sense && scmd->sense_len) - memcpy(sense, scmd->sense_buffer, SCSI_SENSE_BUFFERSIZE); - if (sshdr) + if (args->resid) + *args->resid = scmd->resid_len; + if (args->sense) + memcpy(args->sense, scmd->sense_buffer, SCSI_SENSE_BUFFERSIZE); + if (args->sshdr) scsi_normalize_sense(scmd->sense_buffer, scmd->sense_len, - sshdr); + args->sshdr); + ret = scmd->result; out: blk_mq_free_request(req);

return ret; } -EXPORT_SYMBOL(__scsi_execute); +EXPORT_SYMBOL(scsi_execute_cmd);

/* * Wake up the error handler if necessary. Avoid as follows that the error diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 31b5273f43a7..4433b02c8935 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3284,6 +3284,24 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, return true; }

+static void sd_read_block_zero(struct scsi_disk *sdkp) +{ + unsigned int buf_len = sdkp->device->sector_size; + char *buffer, cmd[10] = { }; + + buffer = kmalloc(buf_len, GFP_KERNEL); + if (!buffer) + return; + + cmd[0] = READ_10; + put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + + scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len, + SD_TIMEOUT, sdkp->max_retries, NULL); + kfree(buffer); +} + /** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. @@ -3323,7 +3341,13 @@ static int sd_revalidate_disk(struct gendisk *disk) */ if (sdkp->media_present) { sd_read_capacity(sdkp, buffer); - + /* + * Some USB/UAS devices return generic values for mode pages + * until the media has been accessed. Trigger a READ operation + * to force the device to populate mode pages. + */ + if (sdp->read_before_ms) + sd_read_block_zero(sdkp); /* * set the default to rotational. All non-rotational devices * support the block characteristics VPD page, which will diff --git a/drivers/soc/qcom/rpmhpd.c b/drivers/soc/qcom/rpmhpd.c index 092f6ab09acf..9a90f241bb97 100644 --- a/drivers/soc/qcom/rpmhpd.c +++ b/drivers/soc/qcom/rpmhpd.c @@ -492,12 +492,15 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner) unsigned int active_corner, sleep_corner; unsigned int this_active_corner = 0, this_sleep_corner = 0; unsigned int peer_active_corner = 0, peer_sleep_corner = 0; + unsigned int peer_enabled_corner;

to_active_sleep(pd, corner, &this_active_corner, &this_sleep_corner);

- if (peer && peer->enabled) - to_active_sleep(peer, peer->corner, &peer_active_corner, + if (peer && peer->enabled) { + peer_enabled_corner = max(peer->corner, peer->enable_corner); + to_active_sleep(peer, peer_enabled_corner, &peer_active_corner, &peer_sleep_corner); + }

active_corner = max(this_active_corner, peer_active_corner);

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index cb0a4e2cdbb7..247cca46cdfa 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -511,6 +511,19 @@ static u8 encode_bMaxPower(enum usb_device_speed speed, return min(val, 900U) / 8; }

+void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c) +{ + if (USB_CONFIG_ATT_WAKEUP & c->bmAttributes) { + /* Reset the rw bit if gadget is not capable of it */ + if (!g->wakeup_capable && g->ops->set_remote_wakeup) { + WARN(c->cdev, "Clearing wakeup bit for config c.%d\n", + c->bConfigurationValue); + c->bmAttributes &= ~USB_CONFIG_ATT_WAKEUP; + } + } +} + static int config_buf(struct usb_configuration *config, enum usb_device_speed speed, void *buf, u8 type) { @@ -959,6 +972,11 @@ static int set_config(struct usb_composite_dev *cdev, power = min(power, 500U); else power = min(power, 900U); + + if (USB_CONFIG_ATT_WAKEUP & c->bmAttributes) + usb_gadget_set_remote_wakeup(gadget, 1); + else + usb_gadget_set_remote_wakeup(gadget, 0); done: if (power <= USB_SELF_POWER_VBUS_MAX_DRAW) usb_gadget_set_selfpowered(gadget); diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 4dcf29577f8f..b94aec6227c5 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1376,6 +1376,9 @@ static int configfs_composite_bind(struct usb_gadget *gadget, if (gadget_is_otg(gadget)) c->descriptors = otg_desc;

+ /* Properly configure the bmAttributes wakeup bit */ + check_remote_wakeup_config(gadget, c); + cfg = container_of(c, struct config_usb_cfg, c); if (!list_empty(&cfg->string_list)) { i = 0; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index c40f2ecbe1b8..0edd9e53fc5a 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -525,6 +525,33 @@ int usb_gadget_wakeup(struct usb_gadget *gadget) } EXPORT_SYMBOL_GPL(usb_gadget_wakeup);

+/** + * usb_gadget_set_remote_wakeup - configures the device remote wakeup feature. + * @gadget:the device being configured for remote wakeup + * @set:value to be configured. + * + * set to one to enable remote wakeup feature and zero to disable it. + * + * returns zero on success, else negative errno. + */ +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ + int ret = 0; + + if (!gadget->ops->set_remote_wakeup) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->set_remote_wakeup(gadget, set); + +out: + trace_usb_gadget_set_remote_wakeup(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_set_remote_wakeup); + /** * usb_gadget_set_selfpowered - sets the device selfpowered feature. * @gadget:the device being declared as self-powered diff --git a/drivers/usb/gadget/udc/trace.h b/drivers/usb/gadget/udc/trace.h index abdbcb1bacb0..a5ed26fbc2da 100644 --- a/drivers/usb/gadget/udc/trace.h +++ b/drivers/usb/gadget/udc/trace.h @@ -91,6 +91,11 @@ DEFINE_EVENT(udc_log_gadget, usb_gadget_wakeup, TP_ARGS(g, ret) );

+DEFINE_EVENT(udc_log_gadget, usb_gadget_set_remote_wakeup, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + DEFINE_EVENT(udc_log_gadget, usb_gadget_set_selfpowered, TP_PROTO(struct usb_gadget *g, int ret), TP_ARGS(g, ret) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index c54e9805da53..12cf9940e5b6 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -179,6 +179,13 @@ static int slave_configure(struct scsi_device *sdev) */ sdev->use_192_bytes_for_3f = 1;

+ /* + * Some devices report generic values until the media has been + * accessed. Force a READ(10) prior to querying device + * characteristics. + */ + sdev->read_before_ms = 1; + /* * Some devices don't like MODE SENSE with page=0x3f, * which is the command used for checking if a device diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index de3836412bf3..ed22053b3252 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -878,6 +878,13 @@ static int uas_slave_configure(struct scsi_device *sdev) if (devinfo->flags & US_FL_CAPACITY_HEURISTICS) sdev->guess_capacity = 1;

+ /* + * Some devices report generic values until the media has been + * accessed. Force a READ(10) prior to querying device + * characteristics. + */ + sdev->read_before_ms = 1; + /* * Some devices don't like MODE SENSE with page=0x3f, * which is the command used for checking if a device diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index fa205be94a4b..14498a0d13e0 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2397,11 +2397,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; int resize, ret, old_userfont, old_width, old_height, old_charcount; - char *old_data = NULL; + u8 *old_data = vc->vc_font.data;

resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); - if (p->userfont) - old_data = vc->vc_font.data; vc->vc_font.data = (void *)(p->fontdata = data); old_userfont = p->userfont; if ((p->userfont = userfont)) @@ -2435,13 +2433,13 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, update_screen(vc); }

- if (old_data && (--REFCOUNT(old_data) == 0)) + if (old_userfont && (--REFCOUNT(old_data) == 0)) kfree(old_data - FONT_EXTRA_WORDS * sizeof(int)); return 0;

err_out: p->fontdata = old_data; - vc->vc_font.data = (void *)old_data; + vc->vc_font.data = old_data;

if (userfont) { p->userfont = old_userfont; diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 00f8e349921d..96b96516c980 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -937,8 +937,8 @@ static void shutdown_pirq(struct irq_data *data) return;

do_mask(info, EVT_MASK_REASON_EXPLICIT); - xen_evtchn_close(evtchn); xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); }

static void enable_pirq(struct irq_data *data) @@ -982,8 +982,6 @@ static void __unbind_from_irq(unsigned int irq) unsigned int cpu = cpu_from_irq(irq); struct xenbus_device *dev;

- xen_evtchn_close(evtchn); - switch (type_from_irq(irq)) { case IRQT_VIRQ: per_cpu(virq_to_irq, cpu)[virq_from_irq(irq)] = -1; @@ -1001,6 +999,7 @@ static void __unbind_from_irq(unsigned int irq) }

xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); }

xen_free_irq(irq); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index cf811b77ee67..6e2c967fae6f 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -478,8 +478,10 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, dire->u.name[0] == '.' && ctx->actor != afs_lookup_filldir && ctx->actor != afs_lookup_one_filldir && - memcmp(dire->u.name, ".__afs", 6) == 0) + memcmp(dire->u.name, ".__afs", 6) == 0) { + ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); continue; + }

/* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 61e58066b5fd..9c856a73d533 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -740,6 +740,23 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, return ret; }

+static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args) +{ + if (args->start.srcdevid == 0) { + if (memchr(args->start.srcdev_name, 0, + sizeof(args->start.srcdev_name)) == NULL) + return -ENAMETOOLONG; + } else { + args->start.srcdev_name[0] = 0; + } + + if (memchr(args->start.tgtdev_name, 0, + sizeof(args->start.tgtdev_name)) == NULL) + return -ENAMETOOLONG; + + return 0; +} + int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { @@ -752,10 +769,9 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, default: return -EINVAL; } - - if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') || - args->start.tgtdev_name[0] == '\0') - return -EINVAL; + ret = btrfs_check_replace_dev_names(args); + if (ret < 0) + return ret;

ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name, args->start.srcdevid, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0d1b05ded1e3..5756edb37c61 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1643,12 +1643,12 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) * * @objectid: root id * @anon_dev: preallocated anonymous block device number for new roots, - * pass 0 for new allocation. + * pass NULL for a new allocation. * @check_ref: whether to check root item references, If true, return -ENOENT * for orphan roots */ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev, + u64 objectid, dev_t *anon_dev, bool check_ref) { struct btrfs_root *root; @@ -1668,9 +1668,9 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, * that common but still possible. In that case, we just need * to free the anon_dev. */ - if (unlikely(anon_dev)) { - free_anon_bdev(anon_dev); - anon_dev = 0; + if (unlikely(anon_dev && *anon_dev)) { + free_anon_bdev(*anon_dev); + *anon_dev = 0; }

if (check_ref && btrfs_root_refs(&root->root_item) == 0) { @@ -1692,7 +1692,7 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, goto fail; }

- ret = btrfs_init_fs_root(root, anon_dev); + ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0); if (ret) goto fail;

@@ -1728,7 +1728,7 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() * and once again by our caller. */ - if (anon_dev) + if (anon_dev && *anon_dev) root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); @@ -1744,7 +1744,7 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref) { - return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); + return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref); }

/* @@ -1752,11 +1752,11 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, * the anonymous block device id * * @objectid: tree objectid - * @anon_dev: if zero, allocate a new anonymous block device or use the - * parameter value + * @anon_dev: if NULL, allocate a new anonymous block device or use the + * parameter value if not NULL */ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev) + u64 objectid, dev_t *anon_dev) { return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 7322af63c0cc..24bddca86e9c 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -65,7 +65,7 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev); + u64 objectid, dev_t *anon_dev); struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 objectid); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 196e222749cc..64b37afb7c87 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -708,7 +708,7 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, free_extent_buffer(leaf); leaf = NULL;

- new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); + new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev); if (IS_ERR(new_root)) { ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index a75669972dc7..9f7ffd9ef6fd 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6462,11 +6462,20 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (ret) goto out; } - if (sctx->cur_inode_last_extent < - sctx->cur_inode_size) { - ret = send_hole(sctx, sctx->cur_inode_size); - if (ret) + if (sctx->cur_inode_last_extent < sctx->cur_inode_size) { + ret = range_is_hole_in_parent(sctx, + sctx->cur_inode_last_extent, + sctx->cur_inode_size); + if (ret < 0) { goto out; + } else if (ret == 0) { + ret = send_hole(sctx, sctx->cur_inode_size); + if (ret < 0) + goto out; + } else { + /* Range is already a hole, skip. */ + ret = 0; + } } } if (need_truncate) { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 60db4c3b82fa..b172091f4261 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1809,7 +1809,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, }

key.offset = (u64)-1; - pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, &pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); pending->snap = NULL; diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index 9e4f47808bd5..13bc60698955 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -372,7 +372,7 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), void *data, bool duplicates, struct list_head *head) { - unsigned long variable_name_size = 1024; + unsigned long variable_name_size = 512; efi_char16_t *variable_name; efi_status_t status; efi_guid_t vendor_guid; @@ -389,12 +389,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), goto free;

/* - * Per EFI spec, the maximum storage allocated for both - * the variable name and variable data is 1024 bytes. + * A small set of old UEFI implementations reject sizes + * above a certain threshold, the lowest seen in the wild + * is 512. */

do { - variable_name_size = 1024; + variable_name_size = 512;

status = efivar_get_next_variable(&variable_name_size, variable_name, @@ -431,9 +432,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), break; case EFI_NOT_FOUND: break; + case EFI_BUFFER_TOO_SMALL: + pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n", + variable_name_size); + status = EFI_NOT_FOUND; + break; default: - printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n", - status); + pr_warn("efivars: get_next_variable: status=%lx\n", status); status = EFI_NOT_FOUND; break; } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index c648a493faf2..3204bd33e4e8 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -18,7 +18,7 @@ #include <linux/sched.h> #include <linux/cred.h>

-#define dprintk(fmt, args...) do{}while(0) +#define dprintk(fmt, args...) pr_debug(fmt, ##args)

static int get_name(const struct path *path, char *name, struct dentry *child); @@ -132,8 +132,8 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, inode_unlock(dentry->d_inode);

if (IS_ERR(parent)) { - dprintk("%s: get_parent of %ld failed, err %d\n", - __func__, dentry->d_inode->i_ino, PTR_ERR(parent)); + dprintk("get_parent of %lu failed, err %ld\n", + dentry->d_inode->i_ino, PTR_ERR(parent)); return parent; }

@@ -147,7 +147,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, dprintk("%s: found name: %s\n", __func__, nbuf); tmp = lookup_one_unlocked(mnt_user_ns(mnt), nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { - dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp)); + dprintk("lookup failed: %ld\n", PTR_ERR(tmp)); err = PTR_ERR(tmp); goto out_err; } diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 284b019cb652..b72023a6b4c1 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -52,6 +52,7 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, *filp = file;

/* Set up the missing parts of the file_lock structure */ + lock->fl.fl_flags = FL_POSIX; lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_start = (loff_t)lock->lock_start; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 9c1aa75441e1..4e30f3c50970 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -659,11 +659,13 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock) nlmsvc_cancel_blocked(net, file, lock);

lock->fl.fl_type = F_UNLCK; - if (file->f_file[O_RDONLY]) - error = vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, + lock->fl.fl_file = file->f_file[O_RDONLY]; + if (lock->fl.fl_file) + error = vfs_lock_file(lock->fl.fl_file, F_SETLK, &lock->fl, NULL); - if (file->f_file[O_WRONLY]) - error = vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, + lock->fl.fl_file = file->f_file[O_WRONLY]; + if (lock->fl.fl_file) + error |= vfs_lock_file(lock->fl.fl_file, F_SETLK, &lock->fl, NULL);

return (error < 0)? nlm_lck_denied_nolocks : nlm_granted; @@ -697,9 +699,10 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l block = nlmsvc_lookup_block(file, lock); mutex_unlock(&file->f_mutex); if (block != NULL) { - mode = lock_to_openmode(&lock->fl); - vfs_cancel_lock(block->b_file->f_file[mode], - &block->b_call->a_args.lock.fl); + struct file_lock *fl = &block->b_call->a_args.lock.fl; + + mode = lock_to_openmode(fl); + vfs_cancel_lock(block->b_file->f_file[mode], fl); status = nlmsvc_unlink_block(block); nlmsvc_release_block(block); } diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index e35c05e27806..32784f508c81 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -77,6 +77,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,

/* Set up the missing parts of the file_lock structure */ mode = lock_to_openmode(&lock->fl); + lock->fl.fl_flags = FL_POSIX; lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_lmops = &nlmsvc_lock_operations; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 3515f17eaf3f..e3b6229e7ae5 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -210,7 +210,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; - struct file_lock_context *flctx = inode->i_flctx; + struct file_lock_context *flctx = locks_inode_context(inode); struct nlm_host *lockhost;

if (!flctx || list_empty_careful(&flctx->flc_posix)) @@ -265,7 +265,7 @@ nlm_file_inuse(struct nlm_file *file) { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; - struct file_lock_context *flctx = inode->i_flctx; + struct file_lock_context *flctx = locks_inode_context(inode);

if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; diff --git a/fs/locks.c b/fs/locks.c index 1047ab2b15e9..7d0918b8fe5d 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -175,7 +175,7 @@ locks_get_lock_context(struct inode *inode, int type) struct file_lock_context *ctx;

/* paired with cmpxchg() below */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out;

@@ -194,7 +194,7 @@ locks_get_lock_context(struct inode *inode, int type) */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); @@ -247,7 +247,7 @@ locks_check_ctx_file_list(struct file *filp, struct list_head *list, void locks_free_lock_context(struct inode *inode) { - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx = locks_inode_context(inode);

if (unlikely(ctx)) { locks_check_ctx_lists(inode); @@ -891,7 +891,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) void *owner; void (*func)(void);

- ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; return; @@ -1483,7 +1483,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) new_fl->fl_flags = type;

/* typically we will check that ctx is non-NULL before calling */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; @@ -1588,7 +1588,7 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time) struct file_lock_context *ctx; struct file_lock *fl;

- ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); fl = list_first_entry_or_null(&ctx->flc_lease, @@ -1634,7 +1634,7 @@ int fcntl_getlease(struct file *filp) int type = F_UNLCK; LIST_HEAD(dispose);

- ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); @@ -1823,7 +1823,7 @@ static int generic_delete_lease(struct file *filp, void *owner) struct file_lock_context *ctx; LIST_HEAD(dispose);

- ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; @@ -2562,7 +2562,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return;

@@ -2635,7 +2635,7 @@ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx;

- ctx = smp_load_acquire(&locks_inode(filp)->i_flctx); + ctx = locks_inode_context(locks_inode(filp)); if (!ctx) return;

@@ -2682,7 +2682,7 @@ bool vfs_inode_has_locks(struct inode *inode) struct file_lock_context *ctx; bool ret;

- ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return false;

@@ -2863,7 +2863,7 @@ void show_fd_locks(struct seq_file *f, struct file_lock_context *ctx; int id = 0;

- ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return;

diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 3fa77ad7258f..c8a57cfde64b 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -9,10 +9,10 @@ #define _TRACE_NFS4_H

#include <linux/tracepoint.h> -#include <trace/events/sunrpc_base.h> +#include <trace/misc/sunrpc.h>

-#include <trace/events/fs.h> -#include <trace/events/nfs.h> +#include <trace/misc/fs.h> +#include <trace/misc/nfs.h>

#define show_nfs_fattr_flags(valid) \ __print_flags((unsigned long)valid, "|", \ diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 8c6cc58679ff..642f6921852f 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -11,9 +11,9 @@ #include <linux/tracepoint.h> #include <linux/iversion.h>

-#include <trace/events/fs.h> -#include <trace/events/nfs.h> -#include <trace/events/sunrpc_base.h> +#include <trace/misc/fs.h> +#include <trace/misc/nfs.h> +#include <trace/misc/sunrpc.h>

#define nfs_show_cache_validity(v) \ __print_flags(v, "|", \ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f41d24b54fd1..6a0606668417 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -667,8 +667,10 @@ static int nfs_writepage_locked(struct page *page, int err;

if (wbc->sync_mode == WB_SYNC_NONE && - NFS_SERVER(inode)->write_congested) + NFS_SERVER(inode)->write_congested) { + redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; + }

nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_pageio_init_write(&pgio, inode, 0, diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index f6a2fd3015e7..7c441f2bd444 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -8,6 +8,7 @@ config NFSD select SUNRPC select EXPORTFS select NFS_ACL_SUPPORT if NFSD_V2_ACL + select NFS_ACL_SUPPORT if NFSD_V3_ACL depends on MULTIUSER help Choose Y here if you want to allow other computers to access @@ -26,19 +27,29 @@ config NFSD

Below you can choose which versions of the NFS protocol are available to clients mounting the NFS server on this system. - Support for NFS version 2 (RFC 1094) is always available when + Support for NFS version 3 (RFC 1813) is always available when CONFIG_NFSD is selected.

If unsure, say N.

-config NFSD_V2_ACL - bool +config NFSD_V2 + bool "NFS server support for NFS version 2 (DEPRECATED)" depends on NFSD + default n + help + NFSv2 (RFC 1094) was the first publicly-released version of NFS. + Unless you are hosting ancient (1990's era) NFS clients, you don't + need this. + + If unsure, say N. + +config NFSD_V2_ACL + bool "NFS server support for the NFSv2 ACL protocol extension" + depends on NFSD_V2

config NFSD_V3_ACL bool "NFS server support for the NFSv3 ACL protocol extension" depends on NFSD - select NFSD_V2_ACL help Solaris NFS servers support an auxiliary NFSv3 ACL protocol that never became an official part of the NFS version 3 protocol. diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 805c06d5f1b4..6fffc8f03f74 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -10,9 +10,10 @@ obj-$(CONFIG_NFSD) += nfsd.o # this one should be compiled first, as the tracing macros can easily blow up nfsd-y += trace.o

-nfsd-y += nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \ - export.o auth.o lockd.o nfscache.o nfsxdr.o \ +nfsd-y += nfssvc.o nfsctl.o nfsfh.o vfs.o \ + export.o auth.o lockd.o nfscache.o \ stats.o filecache.o nfs3proc.o nfs3xdr.o +nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index e7e6e78d965d..01d7fd108cf3 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -12,6 +12,7 @@ #include "blocklayoutxdr.h" #include "pnfs.h" #include "filecache.h" +#include "vfs.h"

#define NFSDDBG_FACILITY NFSDDBG_PNFS

diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 2455dc8be18a..1ed2f691ebb9 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -9,6 +9,7 @@

#include "nfsd.h" #include "blocklayoutxdr.h" +#include "vfs.h"

#define NFSDDBG_FACILITY NFSDDBG_PNFS

diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index ee0e3aba4a6e..d03f7f6a8642 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -115,7 +115,6 @@ struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *); int exp_rootfh(struct net *, struct auth_domain *, char *path, struct knfsd_fh *, int maxsize); __be32 exp_pseudoroot(struct svc_rqst *, struct svc_fh *); -__be32 nfserrno(int errno);

static inline void exp_put(struct svc_export *exp) { diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 5cb8cce153a5..697acf5c3c68 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1,7 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * Open file cache. + * The NFSD open file cache. * * (c) 2015 - Jeff Layton jeff.layton@primarydata.com + * + * An nfsd_file object is a per-file collection of open state that binds + * together: + * - a struct file * + * - a user credential + * - a network namespace + * - a read-ahead context + * - monitoring for writeback errors + * + * nfsd_file objects are reference-counted. Consumers acquire a new + * object via the nfsd_file_acquire API. They manage their interest in + * the acquired object, and hence the object's reference count, via + * nfsd_file_get and nfsd_file_put. There are two varieties of nfsd_file + * object: + * + * * non-garbage-collected: When a consumer wants to precisely control + * the lifetime of a file's open state, it acquires a non-garbage- + * collected nfsd_file. The final nfsd_file_put releases the open + * state immediately. + * + * * garbage-collected: When a consumer does not control the lifetime + * of open state, it acquires a garbage-collected nfsd_file. The + * final nfsd_file_put allows the open state to linger for a period + * during which it may be re-used. */

#include <linux/hash.h> @@ -186,12 +211,9 @@ static const struct rhashtable_params nfsd_file_rhash_params = { static void nfsd_file_schedule_laundrette(void) { - if ((atomic_read(&nfsd_file_rhash_tbl.nelems) == 0) || - test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) - return; - - queue_delayed_work(system_wq, &nfsd_filecache_laundrette, - NFSD_LAUNDRETTE_DELAY); + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags)) + queue_delayed_work(system_wq, &nfsd_filecache_laundrette, + NFSD_LAUNDRETTE_DELAY); }

static void @@ -589,7 +611,8 @@ static void nfsd_file_gc_worker(struct work_struct *work) { nfsd_file_gc(); - nfsd_file_schedule_laundrette(); + if (list_lru_count(&nfsd_file_lru)) + nfsd_file_schedule_laundrette(); }

static unsigned long diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c index 070f90ed09b6..3ca5304440ff 100644 --- a/fs/nfsd/flexfilelayout.c +++ b/fs/nfsd/flexfilelayout.c @@ -15,6 +15,7 @@

#include "flexfilelayoutxdr.h" #include "pnfs.h" +#include "vfs.h"

#define NFSDDBG_FACILITY NFSDDBG_PNFS

diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 8c854ba3285b..51a4b7885cae 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -195,7 +195,7 @@ struct nfsd_net {

atomic_t nfsd_courtesy_clients; struct shrinker nfsd_client_shrinker; - struct delayed_work nfsd_shrinker_work; + struct work_struct nfsd_shrinker_work; };

/* Simple check to find out if a given net was properly initialized */ diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 39989c14c8a1..4eae2c5af2ed 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -76,6 +76,17 @@ static __be32 *xdr_encode_empty_array(__be32 *p) * 1 Protocol" */

+static void encode_uint32(struct xdr_stream *xdr, u32 n) +{ + WARN_ON_ONCE(xdr_stream_encode_u32(xdr, n) < 0); +} + +static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, + size_t len) +{ + WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0); +} + /* * nfs_cb_opnum4 * @@ -328,6 +339,24 @@ static void encode_cb_recall4args(struct xdr_stream *xdr, hdr->nops++; }

+/* + * CB_RECALLANY4args + * + * struct CB_RECALLANY4args { + * uint32_t craa_objects_to_keep; + * bitmap4 craa_type_mask; + * }; + */ +static void +encode_cb_recallany4args(struct xdr_stream *xdr, + struct nfs4_cb_compound_hdr *hdr, struct nfsd4_cb_recall_any *ra) +{ + encode_nfs_cb_opnum4(xdr, OP_CB_RECALL_ANY); + encode_uint32(xdr, ra->ra_keep); + encode_bitmap4(xdr, ra->ra_bmval, ARRAY_SIZE(ra->ra_bmval)); + hdr->nops++; +} + /* * CB_SEQUENCE4args * @@ -482,6 +511,26 @@ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, encode_cb_nops(&hdr); }

+/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static void +nfs4_xdr_enc_cb_recall_any(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfsd4_cb_recall_any *ra; + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + ra = container_of(cb, struct nfsd4_cb_recall_any, ra_cb); + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_recallany4args(xdr, &hdr, ra); + encode_cb_nops(&hdr); +}

/* * NFSv4.0 and NFSv4.1 XDR decode functions @@ -520,6 +569,28 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status); }

+/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static int +nfs4_xdr_dec_cb_recall_any(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + status = decode_cb_op_status(xdr, OP_CB_RECALL_ANY, &cb->cb_status); + return status; +} + #ifdef CONFIG_NFSD_PNFS /* * CB_LAYOUTRECALL4args @@ -783,6 +854,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { #endif PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), + PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), };

static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index e70a1a2999b7..5e9809aff37e 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -41,6 +41,7 @@ #include "idmap.h" #include "nfsd.h" #include "netns.h" +#include "vfs.h"

/* * Turn off idmapping when using AUTH_SYS. diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a9105e95b59c..ba53cd89ec62 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -943,12 +943,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &read->rd_stateid, RD_STATE, &read->rd_nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); - goto out; - } - status = nfs_ok; -out: + read->rd_rqstp = rqstp; read->rd_fhp = &cstate->current_fh; return status; @@ -1117,10 +1112,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &setattr->sa_stateid, WR_STATE, NULL, NULL); - if (status) { - dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); + if (status) return status; - } } err = fh_want_write(&cstate->current_fh); if (err) @@ -1170,10 +1163,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, write->wr_offset, cnt); status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, stateid, WR_STATE, &nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); + if (status) return status; - }

write->wr_how_written = write->wr_stable_how;

@@ -1204,17 +1195,13 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,

status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, src_stateid, RD_STATE, src, NULL); - if (status) { - dprintk("NFSD: %s: couldn't process src stateid!\n", __func__); + if (status) goto out; - }

status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, dst_stateid, WR_STATE, dst, NULL); - if (status) { - dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__); + if (status) goto out_put_src; - }

/* fix up for NFS-specific error code */ if (!S_ISREG(file_inode((*src)->nf_file)->i_mode) || @@ -1935,10 +1922,8 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &fallocate->falloc_stateid, WR_STATE, &nf, NULL); - if (status != nfs_ok) { - dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); + if (status != nfs_ok) return status; - }

status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file, fallocate->falloc_offset, @@ -1994,10 +1979,8 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &seek->seek_stateid, RD_STATE, &nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); + if (status) return status; - }

switch (seek->seek_whence) { case NFS4_CONTENT_DATA: diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index b3f6dda930d8..b9d694ec25d1 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -44,7 +44,9 @@ #include <linux/jhash.h> #include <linux/string_helpers.h> #include <linux/fsnotify.h> +#include <linux/rhashtable.h> #include <linux/nfs_ssc.h> + #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" @@ -84,6 +86,7 @@ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); +static void nfsd4_file_hash_remove(struct nfs4_file *fi);

/* Locking: */

@@ -588,11 +591,8 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu) void put_nfs4_file(struct nfs4_file *fi) { - might_lock(&state_lock); - - if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) { - hlist_del_rcu(&fi->fi_hash); - spin_unlock(&state_lock); + if (refcount_dec_and_test(&fi->fi_ref)) { + nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); @@ -717,19 +717,20 @@ static unsigned int ownerstr_hashval(struct xdr_netobj *ownername) return ret & OWNER_HASH_MASK; }

-/* hash table for nfs4_file */ -#define FILE_HASH_BITS 8 -#define FILE_HASH_SIZE (1 << FILE_HASH_BITS) - -static unsigned int file_hashval(struct svc_fh *fh) -{ - struct inode *inode = d_inode(fh->fh_dentry); +static struct rhltable nfs4_file_rhltable ____cacheline_aligned_in_smp;

- /* XXX: why not (here & in file cache) use inode? */ - return (unsigned int)hash_long(inode->i_ino, FILE_HASH_BITS); -} +static const struct rhashtable_params nfs4_file_rhash_params = { + .key_len = sizeof_field(struct nfs4_file, fi_inode), + .key_offset = offsetof(struct nfs4_file, fi_inode), + .head_offset = offsetof(struct nfs4_file, fi_rlist),

-static struct hlist_head file_hashtbl[FILE_HASH_SIZE]; + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, + .automatic_shrinking = true, +};

/* * Check if courtesy clients have conflicting access and resolve it if possible @@ -1367,6 +1368,8 @@ static void revoke_delegation(struct nfs4_delegation *dp)

WARN_ON(!list_empty(&dp->dl_recall_lru));

+ trace_nfsd_stid_revoke(&dp->dl_stid); + if (clp->cl_minorversion) { spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; @@ -1831,13 +1834,12 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, int numslots = fattrs->maxreqs; int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; - int mem, i; + int i;

- BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *) - + sizeof(struct nfsd4_session) > PAGE_SIZE); - mem = numslots * sizeof(struct nfsd4_slot *); + BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION) + > PAGE_SIZE);

- new = kzalloc(sizeof(*new) + mem, GFP_KERNEL); + new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL); if (!new) return NULL; /* allocate each struct nfsd4_slot and data cache in one piece */ @@ -2143,6 +2145,7 @@ static void __free_client(struct kref *k) kfree(clp->cl_nii_domain.data); kfree(clp->cl_nii_name.data); idr_destroy(&clp->cl_stateids); + kfree(clp->cl_ra); kmem_cache_free(client_slab, clp); }

@@ -2870,6 +2873,37 @@ static const struct tree_descr client_files[] = { [3] = {""}, };

+static int +nfsd4_cb_recall_any_done(struct nfsd4_callback *cb, + struct rpc_task *task) +{ + trace_nfsd_cb_recall_any_done(cb, task); + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + spin_lock(&nn->client_lock); + clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + put_client_renew_locked(clp); + spin_unlock(&nn->client_lock); +} + +static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { + .done = nfsd4_cb_recall_any_done, + .release = nfsd4_cb_recall_any_release, +}; + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -2907,6 +2941,14 @@ static struct nfs4_client *create_client(struct xdr_netobj name, free_client(clp); return NULL; } + clp->cl_ra = kzalloc(sizeof(*clp->cl_ra), GFP_KERNEL); + if (!clp->cl_ra) { + free_client(clp); + return NULL; + } + clp->cl_ra_time = 0; + nfsd4_init_cb(&clp->cl_ra->ra_cb, clp, &nfsd4_cb_recall_any_ops, + NFSPROC4_CLNT_CB_RECALL_ANY); return clp; }

@@ -4276,11 +4318,9 @@ static struct nfs4_file *nfsd4_alloc_file(void) }

/* OPEN Share state helper functions */ -static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval, - struct nfs4_file *fp) -{ - lockdep_assert_held(&state_lock);

+static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) +{ refcount_set(&fp->fi_ref, 1); spin_lock_init(&fp->fi_lock); INIT_LIST_HEAD(&fp->fi_stateids); @@ -4298,7 +4338,6 @@ static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval, INIT_LIST_HEAD(&fp->fi_lo_states); atomic_set(&fp->fi_lo_recalls, 0); #endif - hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); }

void @@ -4363,25 +4402,27 @@ nfsd4_init_slabs(void) }

static unsigned long -nfsd_courtesy_client_count(struct shrinker *shrink, struct shrink_control *sc) +nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { - int cnt; + int count; struct nfsd_net *nn = container_of(shrink, struct nfsd_net, nfsd_client_shrinker);

- cnt = atomic_read(&nn->nfsd_courtesy_clients); - if (cnt > 0) - mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0); - return (unsigned long)cnt; + count = atomic_read(&nn->nfsd_courtesy_clients); + if (!count) + count = atomic_long_read(&num_delegations); + if (count) + queue_work(laundry_wq, &nn->nfsd_shrinker_work); + return (unsigned long)count; }

static unsigned long -nfsd_courtesy_client_scan(struct shrinker *shrink, struct shrink_control *sc) +nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) { return SHRINK_STOP; }

-int +void nfsd4_init_leases_net(struct nfsd_net *nn) { struct sysinfo si; @@ -4403,16 +4444,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn) nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);

atomic_set(&nn->nfsd_courtesy_clients, 0); - nn->nfsd_client_shrinker.scan_objects = nfsd_courtesy_client_scan; - nn->nfsd_client_shrinker.count_objects = nfsd_courtesy_client_count; - nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"); -} - -void -nfsd4_leases_net_shutdown(struct nfsd_net *nn) -{ - unregister_shrinker(&nn->nfsd_client_shrinker); }

static void init_nfs4_replay(struct nfs4_replay *rp) @@ -4683,71 +4714,80 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) nfs4_put_stid(&last->st_stid); }

-/* search file_hashtbl[] for file */ -static struct nfs4_file * -find_file_locked(struct svc_fh *fh, unsigned int hashval) +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_lookup(const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; + struct nfs4_file *fi;

- hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash, - lockdep_is_held(&state_lock)) { - if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - return fp; + rcu_read_lock(); + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) { + rcu_read_unlock(); + return fi; + } } } + rcu_read_unlock(); return NULL; }

-static struct nfs4_file *insert_file(struct nfs4_file *new, struct svc_fh *fh, - unsigned int hashval) +/* + * On hash insertion, identify entries with the same inode but + * distinct filehandles. They will all be on the list returned + * by rhltable_lookup(). + * + * inode->i_lock prevents racing insertions from adding an entry + * for the same inode/fhp pair twice. + */ +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_insert(struct nfs4_file *new, const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; struct nfs4_file *ret = NULL; bool alias_found = false; + struct nfs4_file *fi; + int err;

- spin_lock(&state_lock); - hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash, - lockdep_is_held(&state_lock)) { - if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - ret = fp; - } else if (d_inode(fh->fh_dentry) == fp->fi_inode) - fp->fi_aliased = alias_found = true; - } - if (likely(ret == NULL)) { - nfsd4_init_file(fh, hashval, new); - new->fi_aliased = alias_found; - ret = new; + rcu_read_lock(); + spin_lock(&inode->i_lock); + + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) + ret = fi; + } else + fi->fi_aliased = alias_found = true; } - spin_unlock(&state_lock); - return ret; -} + if (ret) + goto out_unlock;

-static struct nfs4_file * find_file(struct svc_fh *fh) -{ - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); + nfsd4_file_init(fhp, new); + err = rhltable_insert(&nfs4_file_rhltable, &new->fi_rlist, + nfs4_file_rhash_params); + if (err) + goto out_unlock;

- rcu_read_lock(); - fp = find_file_locked(fh, hashval); + new->fi_aliased = alias_found; + ret = new; + +out_unlock: + spin_unlock(&inode->i_lock); rcu_read_unlock(); - return fp; + return ret; }

-static struct nfs4_file * -find_or_add_file(struct nfs4_file *new, struct svc_fh *fh) +static noinline_for_stack void nfsd4_file_hash_remove(struct nfs4_file *fi) { - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); - - rcu_read_lock(); - fp = find_file_locked(fh, hashval); - rcu_read_unlock(); - if (fp) - return fp; - - return insert_file(new, fh, hashval); + rhltable_remove(&nfs4_file_rhltable, &fi->fi_rlist, + nfs4_file_rhash_params); }

/* @@ -4760,9 +4800,10 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) struct nfs4_file *fp; __be32 ret = nfs_ok;

- fp = find_file(current_fh); + fp = nfsd4_file_hash_lookup(current_fh); if (!fp) return ret; + /* Check for conflicting share reservations */ spin_lock(&fp->fi_lock); if (fp->fi_share_deny & deny_type) @@ -4774,7 +4815,7 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)

static bool nfsd4_deleg_present(const struct inode *inode) { - struct file_lock_context *ctx = smp_load_acquire(&inode->i_flctx); + struct file_lock_context *ctx = locks_inode_context(inode);

return ctx && !list_empty_careful(&ctx->flc_lease); } @@ -5655,7 +5696,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * and check for delegations in the process of being recalled. * If not found, create the nfs4_file struct */ - fp = find_or_add_file(open->op_file, current_fh); + fp = nfsd4_file_hash_insert(open->op_file, current_fh); + if (unlikely(!fp)) + return nfserr_jukebox; if (fp != open->op_file) { status = nfs4_check_deleg(cl, open, &dp); if (status) @@ -5932,7 +5975,7 @@ nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo)

list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { nf = stp->st_stid.sc_file; - ctx = nf->fi_inode->i_flctx; + ctx = locks_inode_context(nf->fi_inode); if (!ctx) continue; if (locks_owner_has_blockers(ctx, lo)) @@ -6160,17 +6203,63 @@ laundromat_main(struct work_struct *laundry) }

static void -courtesy_client_reaper(struct work_struct *reaper) +courtesy_client_reaper(struct nfsd_net *nn) { struct list_head reaplist; - struct delayed_work *dwork = to_delayed_work(reaper); - struct nfsd_net *nn = container_of(dwork, struct nfsd_net, - nfsd_shrinker_work);

nfs4_get_courtesy_client_reaplist(nn, &reaplist); nfs4_process_client_reaplist(&reaplist); }

+static void +deleg_reaper(struct nfsd_net *nn) +{ + struct list_head *pos, *next; + struct nfs4_client *clp; + struct list_head cblist; + + INIT_LIST_HEAD(&cblist); + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + if (clp->cl_state != NFSD4_ACTIVE || + list_empty(&clp->cl_delegations) || + atomic_read(&clp->cl_delegs_in_recall) || + test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || + (ktime_get_boottime_seconds() - + clp->cl_ra_time < 5)) { + continue; + } + list_add(&clp->cl_ra_cblist, &cblist); + + /* release in nfsd4_cb_recall_any_release */ + atomic_inc(&clp->cl_rpc_users); + set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + clp->cl_ra_time = ktime_get_boottime_seconds(); + } + spin_unlock(&nn->client_lock); + + while (!list_empty(&cblist)) { + clp = list_first_entry(&cblist, struct nfs4_client, + cl_ra_cblist); + list_del_init(&clp->cl_ra_cblist); + clp->cl_ra->ra_keep = 0; + clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG); + trace_nfsd_cb_recall_any(clp->cl_ra); + nfsd4_run_cb(&clp->cl_ra->ra_cb); + } +} + +static void +nfsd4_state_shrinker_worker(struct work_struct *work) +{ + struct nfsd_net *nn = container_of(work, struct nfsd_net, + nfsd_shrinker_work); + + courtesy_client_reaper(nn); + deleg_reaper(nn); +} + static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) @@ -6935,6 +7024,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto put_stateid;

+ trace_nfsd_deleg_return(stateid); wake_up_var(d_inode(cstate->current_fh.fh_dentry)); destroy_delegation(dp); put_stateid: @@ -7748,7 +7838,7 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) }

inode = locks_inode(nf->nf_file); - flctx = inode->i_flctx; + flctx = locks_inode_context(inode);

if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); @@ -7995,11 +8085,20 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->blocked_locks_lru);

INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); - INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, courtesy_client_reaper); + INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net);

+ nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; + + if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client")) + goto err_shrinker; return 0;

+err_shrinker: + put_net(net); + kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: @@ -8071,10 +8170,16 @@ nfs4_state_start(void) { int ret;

- ret = nfsd4_create_callback_queue(); + ret = rhltable_init(&nfs4_file_rhltable, &nfs4_file_rhash_params); if (ret) return ret;

+ ret = nfsd4_create_callback_queue(); + if (ret) { + rhltable_destroy(&nfs4_file_rhltable); + return ret; + } + set_max_delegations(); return 0; } @@ -8086,6 +8191,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id);

+ unregister_shrinker(&nn->nfsd_client_shrinker); + cancel_work(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager);

@@ -8114,6 +8221,7 @@ void nfs4_state_shutdown(void) { nfsd4_destroy_callback_queue(); + rhltable_destroy(&nfs4_file_rhltable); }

static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 89a579be042e..597f14a80512 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -770,16 +770,18 @@ nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs)

static __be32 nfsd4_decode_access(struct nfsd4_compoundargs *argp, - struct nfsd4_access *access) + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; if (xdr_stream_decode_u32(argp->xdr, &access->ac_req_access) < 0) return nfserr_bad_xdr; return nfs_ok; }

static __be32 -nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) +nfsd4_decode_close(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; if (xdr_stream_decode_u32(argp->xdr, &close->cl_seqid) < 0) return nfserr_bad_xdr; return nfsd4_decode_stateid4(argp, &close->cl_stateid); @@ -787,8 +789,9 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close)

static __be32 -nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit) +nfsd4_decode_commit(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; if (xdr_stream_decode_u64(argp->xdr, &commit->co_offset) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &commit->co_count) < 0) @@ -798,8 +801,9 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit }

static __be32 -nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create) +nfsd4_decode_create(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; __be32 *p, status;

memset(create, 0, sizeof(*create)); @@ -844,22 +848,25 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create }

static inline __be32 -nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegreturn *dr) +nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_delegreturn *dr = &u->delegreturn; return nfsd4_decode_stateid4(argp, &dr->dr_stateid); }

static inline __be32 -nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *getattr) +nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; memset(getattr, 0, sizeof(*getattr)); return nfsd4_decode_bitmap4(argp, getattr->ga_bmval, ARRAY_SIZE(getattr->ga_bmval)); }

static __be32 -nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link) +nfsd4_decode_link(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; memset(link, 0, sizeof(*link)); return nfsd4_decode_component4(argp, &link->li_name, &link->li_namelen); } @@ -907,8 +914,9 @@ nfsd4_decode_locker4(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) }

static __be32 -nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) +nfsd4_decode_lock(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; memset(lock, 0, sizeof(*lock)); if (xdr_stream_decode_u32(argp->xdr, &lock->lk_type) < 0) return nfserr_bad_xdr; @@ -924,8 +932,9 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) }

static __be32 -nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) +nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; memset(lockt, 0, sizeof(*lockt)); if (xdr_stream_decode_u32(argp->xdr, &lockt->lt_type) < 0) return nfserr_bad_xdr; @@ -940,8 +949,9 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) }

static __be32 -nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) +nfsd4_decode_locku(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; __be32 status;

if (xdr_stream_decode_u32(argp->xdr, &locku->lu_type) < 0) @@ -962,8 +972,9 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) }

static __be32 -nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup) +nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lookup *lookup = &u->lookup; return nfsd4_decode_component4(argp, &lookup->lo_name, &lookup->lo_len); }

@@ -1143,8 +1154,9 @@ nfsd4_decode_open_claim4(struct nfsd4_compoundargs *argp, }

static __be32 -nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) +nfsd4_decode_open(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; __be32 status; u32 dummy;

@@ -1171,8 +1183,10 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) }

static __be32 -nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_confirm *open_conf) +nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *open_conf = &u->open_confirm; __be32 status;

if (argp->minorversion >= 1) @@ -1190,8 +1204,10 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con }

static __be32 -nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_downgrade *open_down) +nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *open_down = &u->open_downgrade; __be32 status;

memset(open_down, 0, sizeof(*open_down)); @@ -1209,8 +1225,9 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d }

static __be32 -nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) +nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_putfh *putfh = &u->putfh; __be32 *p;

if (xdr_stream_decode_u32(argp->xdr, &putfh->pf_fhlen) < 0) @@ -1229,7 +1246,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) }

static __be32 -nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { if (argp->minorversion == 0) return nfs_ok; @@ -1237,8 +1254,9 @@ nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) }

static __be32 -nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) +nfsd4_decode_read(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; __be32 status;

memset(read, 0, sizeof(*read)); @@ -1254,8 +1272,9 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) }

static __be32 -nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *readdir) +nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; __be32 status;

memset(readdir, 0, sizeof(*readdir)); @@ -1276,15 +1295,17 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read }

static __be32 -nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove) +nfsd4_decode_remove(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; memset(&remove->rm_cinfo, 0, sizeof(remove->rm_cinfo)); return nfsd4_decode_component4(argp, &remove->rm_name, &remove->rm_namelen); }

static __be32 -nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename) +nfsd4_decode_rename(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; __be32 status;

memset(rename, 0, sizeof(*rename)); @@ -1295,22 +1316,25 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename }

static __be32 -nfsd4_decode_renew(struct nfsd4_compoundargs *argp, clientid_t *clientid) +nfsd4_decode_renew(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + clientid_t *clientid = &u->renew; return nfsd4_decode_clientid4(argp, clientid); }

static __be32 nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; secinfo->si_exp = NULL; return nfsd4_decode_component4(argp, &secinfo->si_name, &secinfo->si_namelen); }

static __be32 -nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr) +nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; __be32 status;

memset(setattr, 0, sizeof(*setattr)); @@ -1324,8 +1348,9 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta }

static __be32 -nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid *setclientid) +nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_setclientid *setclientid = &u->setclientid; __be32 *p, status;

memset(setclientid, 0, sizeof(*setclientid)); @@ -1367,8 +1392,10 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient }

static __be32 -nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid_confirm *scd_c) +nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_setclientid_confirm *scd_c = &u->setclientid_confirm; __be32 status;

if (argp->minorversion >= 1) @@ -1382,8 +1409,9 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s

/* Also used for NVERIFY */ static __be32 -nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify) +nfsd4_decode_verify(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_verify *verify = &u->verify; __be32 *p, status;

memset(verify, 0, sizeof(*verify)); @@ -1409,8 +1437,9 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify }

static __be32 -nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) +nfsd4_decode_write(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; __be32 status;

status = nfsd4_decode_stateid4(argp, &write->wr_stateid); @@ -1434,8 +1463,10 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) }

static __be32 -nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_release_lockowner *rlockowner) +nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; __be32 status;

if (argp->minorversion >= 1) @@ -1452,16 +1483,20 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel return nfs_ok; }

-static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc) +static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; memset(bc, 0, sizeof(*bc)); if (xdr_stream_decode_u32(argp->xdr, &bc->bc_cb_program) < 0) return nfserr_bad_xdr; return nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); }

-static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts) +static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; u32 use_conn_in_rdma_mode; __be32 status;

@@ -1603,8 +1638,9 @@ nfsd4_decode_nfs_impl_id4(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, - struct nfsd4_exchange_id *exid) + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; __be32 status;

memset(exid, 0, sizeof(*exid)); @@ -1656,8 +1692,9 @@ nfsd4_decode_channel_attrs4(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, - struct nfsd4_create_session *sess) + union nfsd4_op_u *u) { + struct nfsd4_create_session *sess = &u->create_session; __be32 status;

memset(sess, 0, sizeof(*sess)); @@ -1681,23 +1718,26 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_destroy_session(struct nfsd4_compoundargs *argp, - struct nfsd4_destroy_session *destroy_session) + union nfsd4_op_u *u) { + struct nfsd4_destroy_session *destroy_session = &u->destroy_session; return nfsd4_decode_sessionid4(argp, &destroy_session->sessionid); }

static __be32 nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp, - struct nfsd4_free_stateid *free_stateid) + union nfsd4_op_u *u) { + struct nfsd4_free_stateid *free_stateid = &u->free_stateid; return nfsd4_decode_stateid4(argp, &free_stateid->fr_stateid); }

#ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, - struct nfsd4_getdeviceinfo *gdev) + union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; __be32 status;

memset(gdev, 0, sizeof(*gdev)); @@ -1717,8 +1757,9 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutcommit *lcp) + union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; __be32 *p, status;

memset(lcp, 0, sizeof(*lcp)); @@ -1753,8 +1794,9 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutget *lgp) + union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; __be32 status;

memset(lgp, 0, sizeof(*lgp)); @@ -1781,8 +1823,9 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutreturn *lrp) + union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; memset(lrp, 0, sizeof(*lrp)); if (xdr_stream_decode_bool(argp->xdr, &lrp->lr_reclaim) < 0) return nfserr_bad_xdr; @@ -1795,8 +1838,9 @@ nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, #endif /* CONFIG_NFSD_PNFS */

static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, - struct nfsd4_secinfo_no_name *sin) + union nfsd4_op_u *u) { + struct nfsd4_secinfo_no_name *sin = &u->secinfo_no_name; if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0) return nfserr_bad_xdr;

@@ -1806,8 +1850,9 @@ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, - struct nfsd4_sequence *seq) + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; __be32 *p, status;

status = nfsd4_decode_sessionid4(argp, &seq->sessionid); @@ -1826,8 +1871,10 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, }

static __be32 -nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_stateid *test_stateid) +nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; __be32 status; u32 i; @@ -1852,14 +1899,16 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta }

static __be32 nfsd4_decode_destroy_clientid(struct nfsd4_compoundargs *argp, - struct nfsd4_destroy_clientid *dc) + union nfsd4_op_u *u) { + struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; return nfsd4_decode_clientid4(argp, &dc->clientid); }

static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, - struct nfsd4_reclaim_complete *rc) + union nfsd4_op_u *u) { + struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; if (xdr_stream_decode_bool(argp->xdr, &rc->rca_one_fs) < 0) return nfserr_bad_xdr; return nfs_ok; @@ -1867,8 +1916,9 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { + struct nfsd4_fallocate *fallocate = &u->allocate; __be32 status;

status = nfsd4_decode_stateid4(argp, &fallocate->falloc_stateid); @@ -1924,8 +1974,9 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, }

static __be32 -nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) +nfsd4_decode_copy(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; u32 consecutive, i, count, sync; struct nl4_server *ns_dummy; __be32 status; @@ -1982,8 +2033,9 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy)

static __be32 nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, - struct nfsd4_copy_notify *cn) + union nfsd4_op_u *u) { + struct nfsd4_copy_notify *cn = &u->copy_notify; __be32 status;

memset(cn, 0, sizeof(*cn)); @@ -2002,16 +2054,18 @@ nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp, - struct nfsd4_offload_status *os) + union nfsd4_op_u *u) { + struct nfsd4_offload_status *os = &u->offload_status; os->count = 0; os->status = 0; return nfsd4_decode_stateid4(argp, &os->stateid); }

static __be32 -nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) +nfsd4_decode_seek(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; __be32 status;

status = nfsd4_decode_stateid4(argp, &seek->seek_stateid); @@ -2028,8 +2082,9 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) }

static __be32 -nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone) +nfsd4_decode_clone(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_clone *clone = &u->clone; __be32 status;

status = nfsd4_decode_stateid4(argp, &clone->cl_src_stateid); @@ -2154,8 +2209,9 @@ nfsd4_decode_xattr_name(struct nfsd4_compoundargs *argp, char **namep) */ static __be32 nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, - struct nfsd4_getxattr *getxattr) + union nfsd4_op_u *u) { + struct nfsd4_getxattr *getxattr = &u->getxattr; __be32 status; u32 maxcount;

@@ -2173,8 +2229,9 @@ nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, - struct nfsd4_setxattr *setxattr) + union nfsd4_op_u *u) { + struct nfsd4_setxattr *setxattr = &u->setxattr; u32 flags, maxcount, size; __be32 status;

@@ -2214,8 +2271,9 @@ nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, - struct nfsd4_listxattrs *listxattrs) + union nfsd4_op_u *u) { + struct nfsd4_listxattrs *listxattrs = &u->listxattrs; u32 maxcount;

memset(listxattrs, 0, sizeof(*listxattrs)); @@ -2245,113 +2303,114 @@ nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp,

static __be32 nfsd4_decode_removexattr(struct nfsd4_compoundargs *argp, - struct nfsd4_removexattr *removexattr) + union nfsd4_op_u *u) { + struct nfsd4_removexattr *removexattr = &u->removexattr; memset(removexattr, 0, sizeof(*removexattr)); return nfsd4_decode_xattr_name(argp, &removexattr->rmxa_name); }

static __be32 -nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_noop(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { return nfs_ok; }

static __be32 -nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { return nfserr_notsupp; }

-typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); +typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u);

static const nfsd4_dec nfsd4_dec_ops[] = { - [OP_ACCESS] = (nfsd4_dec)nfsd4_decode_access, - [OP_CLOSE] = (nfsd4_dec)nfsd4_decode_close, - [OP_COMMIT] = (nfsd4_dec)nfsd4_decode_commit, - [OP_CREATE] = (nfsd4_dec)nfsd4_decode_create, - [OP_DELEGPURGE] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DELEGRETURN] = (nfsd4_dec)nfsd4_decode_delegreturn, - [OP_GETATTR] = (nfsd4_dec)nfsd4_decode_getattr, - [OP_GETFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_LINK] = (nfsd4_dec)nfsd4_decode_link, - [OP_LOCK] = (nfsd4_dec)nfsd4_decode_lock, - [OP_LOCKT] = (nfsd4_dec)nfsd4_decode_lockt, - [OP_LOCKU] = (nfsd4_dec)nfsd4_decode_locku, - [OP_LOOKUP] = (nfsd4_dec)nfsd4_decode_lookup, - [OP_LOOKUPP] = (nfsd4_dec)nfsd4_decode_noop, - [OP_NVERIFY] = (nfsd4_dec)nfsd4_decode_verify, - [OP_OPEN] = (nfsd4_dec)nfsd4_decode_open, - [OP_OPENATTR] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OPEN_CONFIRM] = (nfsd4_dec)nfsd4_decode_open_confirm, - [OP_OPEN_DOWNGRADE] = (nfsd4_dec)nfsd4_decode_open_downgrade, - [OP_PUTFH] = (nfsd4_dec)nfsd4_decode_putfh, - [OP_PUTPUBFH] = (nfsd4_dec)nfsd4_decode_putpubfh, - [OP_PUTROOTFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_READ] = (nfsd4_dec)nfsd4_decode_read, - [OP_READDIR] = (nfsd4_dec)nfsd4_decode_readdir, - [OP_READLINK] = (nfsd4_dec)nfsd4_decode_noop, - [OP_REMOVE] = (nfsd4_dec)nfsd4_decode_remove, - [OP_RENAME] = (nfsd4_dec)nfsd4_decode_rename, - [OP_RENEW] = (nfsd4_dec)nfsd4_decode_renew, - [OP_RESTOREFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_SAVEFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_SECINFO] = (nfsd4_dec)nfsd4_decode_secinfo, - [OP_SETATTR] = (nfsd4_dec)nfsd4_decode_setattr, - [OP_SETCLIENTID] = (nfsd4_dec)nfsd4_decode_setclientid, - [OP_SETCLIENTID_CONFIRM] = (nfsd4_dec)nfsd4_decode_setclientid_confirm, - [OP_VERIFY] = (nfsd4_dec)nfsd4_decode_verify, - [OP_WRITE] = (nfsd4_dec)nfsd4_decode_write, - [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_release_lockowner, + [OP_ACCESS] = nfsd4_decode_access, + [OP_CLOSE] = nfsd4_decode_close, + [OP_COMMIT] = nfsd4_decode_commit, + [OP_CREATE] = nfsd4_decode_create, + [OP_DELEGPURGE] = nfsd4_decode_notsupp, + [OP_DELEGRETURN] = nfsd4_decode_delegreturn, + [OP_GETATTR] = nfsd4_decode_getattr, + [OP_GETFH] = nfsd4_decode_noop, + [OP_LINK] = nfsd4_decode_link, + [OP_LOCK] = nfsd4_decode_lock, + [OP_LOCKT] = nfsd4_decode_lockt, + [OP_LOCKU] = nfsd4_decode_locku, + [OP_LOOKUP] = nfsd4_decode_lookup, + [OP_LOOKUPP] = nfsd4_decode_noop, + [OP_NVERIFY] = nfsd4_decode_verify, + [OP_OPEN] = nfsd4_decode_open, + [OP_OPENATTR] = nfsd4_decode_notsupp, + [OP_OPEN_CONFIRM] = nfsd4_decode_open_confirm, + [OP_OPEN_DOWNGRADE] = nfsd4_decode_open_downgrade, + [OP_PUTFH] = nfsd4_decode_putfh, + [OP_PUTPUBFH] = nfsd4_decode_putpubfh, + [OP_PUTROOTFH] = nfsd4_decode_noop, + [OP_READ] = nfsd4_decode_read, + [OP_READDIR] = nfsd4_decode_readdir, + [OP_READLINK] = nfsd4_decode_noop, + [OP_REMOVE] = nfsd4_decode_remove, + [OP_RENAME] = nfsd4_decode_rename, + [OP_RENEW] = nfsd4_decode_renew, + [OP_RESTOREFH] = nfsd4_decode_noop, + [OP_SAVEFH] = nfsd4_decode_noop, + [OP_SECINFO] = nfsd4_decode_secinfo, + [OP_SETATTR] = nfsd4_decode_setattr, + [OP_SETCLIENTID] = nfsd4_decode_setclientid, + [OP_SETCLIENTID_CONFIRM] = nfsd4_decode_setclientid_confirm, + [OP_VERIFY] = nfsd4_decode_verify, + [OP_WRITE] = nfsd4_decode_write, + [OP_RELEASE_LOCKOWNER] = nfsd4_decode_release_lockowner,

/* new operations for NFSv4.1 */ - [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_backchannel_ctl, - [OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session, - [OP_EXCHANGE_ID] = (nfsd4_dec)nfsd4_decode_exchange_id, - [OP_CREATE_SESSION] = (nfsd4_dec)nfsd4_decode_create_session, - [OP_DESTROY_SESSION] = (nfsd4_dec)nfsd4_decode_destroy_session, - [OP_FREE_STATEID] = (nfsd4_dec)nfsd4_decode_free_stateid, - [OP_GET_DIR_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_BACKCHANNEL_CTL] = nfsd4_decode_backchannel_ctl, + [OP_BIND_CONN_TO_SESSION] = nfsd4_decode_bind_conn_to_session, + [OP_EXCHANGE_ID] = nfsd4_decode_exchange_id, + [OP_CREATE_SESSION] = nfsd4_decode_create_session, + [OP_DESTROY_SESSION] = nfsd4_decode_destroy_session, + [OP_FREE_STATEID] = nfsd4_decode_free_stateid, + [OP_GET_DIR_DELEGATION] = nfsd4_decode_notsupp, #ifdef CONFIG_NFSD_PNFS - [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_getdeviceinfo, - [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_layoutcommit, - [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_layoutget, - [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_layoutreturn, + [OP_GETDEVICEINFO] = nfsd4_decode_getdeviceinfo, + [OP_GETDEVICELIST] = nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = nfsd4_decode_layoutcommit, + [OP_LAYOUTGET] = nfsd4_decode_layoutget, + [OP_LAYOUTRETURN] = nfsd4_decode_layoutreturn, #else - [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GETDEVICEINFO] = nfsd4_decode_notsupp, + [OP_GETDEVICELIST] = nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = nfsd4_decode_notsupp, + [OP_LAYOUTGET] = nfsd4_decode_notsupp, + [OP_LAYOUTRETURN] = nfsd4_decode_notsupp, #endif - [OP_SECINFO_NO_NAME] = (nfsd4_dec)nfsd4_decode_secinfo_no_name, - [OP_SEQUENCE] = (nfsd4_dec)nfsd4_decode_sequence, - [OP_SET_SSV] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_TEST_STATEID] = (nfsd4_dec)nfsd4_decode_test_stateid, - [OP_WANT_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DESTROY_CLIENTID] = (nfsd4_dec)nfsd4_decode_destroy_clientid, - [OP_RECLAIM_COMPLETE] = (nfsd4_dec)nfsd4_decode_reclaim_complete, + [OP_SECINFO_NO_NAME] = nfsd4_decode_secinfo_no_name, + [OP_SEQUENCE] = nfsd4_decode_sequence, + [OP_SET_SSV] = nfsd4_decode_notsupp, + [OP_TEST_STATEID] = nfsd4_decode_test_stateid, + [OP_WANT_DELEGATION] = nfsd4_decode_notsupp, + [OP_DESTROY_CLIENTID] = nfsd4_decode_destroy_clientid, + [OP_RECLAIM_COMPLETE] = nfsd4_decode_reclaim_complete,

/* new operations for NFSv4.2 */ - [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, - [OP_COPY] = (nfsd4_dec)nfsd4_decode_copy, - [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_copy_notify, - [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, - [OP_IO_ADVISE] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTERROR] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTSTATS] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OFFLOAD_CANCEL] = (nfsd4_dec)nfsd4_decode_offload_status, - [OP_OFFLOAD_STATUS] = (nfsd4_dec)nfsd4_decode_offload_status, - [OP_READ_PLUS] = (nfsd4_dec)nfsd4_decode_read, - [OP_SEEK] = (nfsd4_dec)nfsd4_decode_seek, - [OP_WRITE_SAME] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_CLONE] = (nfsd4_dec)nfsd4_decode_clone, + [OP_ALLOCATE] = nfsd4_decode_fallocate, + [OP_COPY] = nfsd4_decode_copy, + [OP_COPY_NOTIFY] = nfsd4_decode_copy_notify, + [OP_DEALLOCATE] = nfsd4_decode_fallocate, + [OP_IO_ADVISE] = nfsd4_decode_notsupp, + [OP_LAYOUTERROR] = nfsd4_decode_notsupp, + [OP_LAYOUTSTATS] = nfsd4_decode_notsupp, + [OP_OFFLOAD_CANCEL] = nfsd4_decode_offload_status, + [OP_OFFLOAD_STATUS] = nfsd4_decode_offload_status, + [OP_READ_PLUS] = nfsd4_decode_read, + [OP_SEEK] = nfsd4_decode_seek, + [OP_WRITE_SAME] = nfsd4_decode_notsupp, + [OP_CLONE] = nfsd4_decode_clone, /* RFC 8276 extended atributes operations */ - [OP_GETXATTR] = (nfsd4_dec)nfsd4_decode_getxattr, - [OP_SETXATTR] = (nfsd4_dec)nfsd4_decode_setxattr, - [OP_LISTXATTRS] = (nfsd4_dec)nfsd4_decode_listxattrs, - [OP_REMOVEXATTR] = (nfsd4_dec)nfsd4_decode_removexattr, + [OP_GETXATTR] = nfsd4_decode_getxattr, + [OP_SETXATTR] = nfsd4_decode_setxattr, + [OP_LISTXATTRS] = nfsd4_decode_listxattrs, + [OP_REMOVEXATTR] = nfsd4_decode_removexattr, };

static inline bool @@ -3643,8 +3702,10 @@ nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) }

static __be32 -nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access) +nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -3656,8 +3717,10 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ return 0; }

-static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts) +static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -3673,8 +3736,10 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, }

static __be32 -nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) +nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; struct xdr_stream *xdr = resp->xdr;

return nfsd4_encode_stateid(xdr, &close->cl_stateid); @@ -3682,8 +3747,10 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c

static __be32 -nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit) +nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -3696,8 +3763,10 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ }

static __be32 -nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create) +nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -3710,8 +3779,10 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ }

static __be32 -nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr) +nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; struct svc_fh *fhp = getattr->ga_fhp; struct xdr_stream *xdr = resp->xdr;

@@ -3720,8 +3791,10 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 }

static __be32 -nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp) +nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct svc_fh **fhpp = &u->getfh; struct xdr_stream *xdr = resp->xdr; struct svc_fh *fhp = *fhpp; unsigned int len; @@ -3775,8 +3848,10 @@ nfsd4_encode_lock_denied(struct xdr_stream *xdr, struct nfsd4_lock_denied *ld) }

static __be32 -nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock) +nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; struct xdr_stream *xdr = resp->xdr;

if (!nfserr) @@ -3788,8 +3863,10 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo }

static __be32 -nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt) +nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; struct xdr_stream *xdr = resp->xdr;

if (nfserr == nfserr_denied) @@ -3798,8 +3875,10 @@ nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l }

static __be32 -nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku) +nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; struct xdr_stream *xdr = resp->xdr;

return nfsd4_encode_stateid(xdr, &locku->lu_stateid); @@ -3807,8 +3886,10 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l

static __be32 -nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link) +nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -3821,8 +3902,10 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li

static __be32 -nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) +nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -3915,16 +3998,20 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op }

static __be32 -nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) +nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *oc = &u->open_confirm; struct xdr_stream *xdr = resp->xdr;

return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); }

static __be32 -nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) +nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *od = &u->open_downgrade; struct xdr_stream *xdr = resp->xdr;

return nfsd4_encode_stateid(xdr, &od->od_stateid); @@ -4023,8 +4110,9 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,

static __be32 nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) + union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); unsigned long maxcount; struct xdr_stream *xdr = resp->xdr; @@ -4065,8 +4153,10 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, }

static __be32 -nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) +nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_readlink *readlink = &u->readlink; __be32 *p, *maxcount_p, zero = xdr_zero; struct xdr_stream *xdr = resp->xdr; int length_offset = xdr->buf->len; @@ -4110,8 +4200,10 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd }

static __be32 -nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir) +nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; int maxcount; int bytes_left; loff_t offset; @@ -4201,8 +4293,10 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 }

static __be32 -nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove) +nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4214,8 +4308,10 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ }

static __be32 -nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename) +nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4297,8 +4393,9 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp)

static __be32 nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; struct xdr_stream *xdr = resp->xdr;

return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp); @@ -4306,8 +4403,9 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo_no_name *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo_no_name *secinfo = &u->secinfo_no_name; struct xdr_stream *xdr = resp->xdr;

return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp); @@ -4318,8 +4416,10 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, * regardless of the error status. */ static __be32 -nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr) +nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4342,8 +4442,10 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 }

static __be32 -nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd) +nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_setclientid *scd = &u->setclientid; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4366,8 +4468,10 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n }

static __be32 -nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write) +nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4383,8 +4487,9 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w

static __be32 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_exchange_id *exid) + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; struct xdr_stream *xdr = resp->xdr; __be32 *p; char *major_id; @@ -4461,8 +4566,9 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_create_session *sess) + union nfsd4_op_u *u) { + struct nfsd4_create_session *sess = &u->create_session; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4514,8 +4620,9 @@ nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_sequence *seq) + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4537,8 +4644,9 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_test_stateid *test_stateid) + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct xdr_stream *xdr = resp->xdr; struct nfsd4_test_stateid_id *stateid, *next; __be32 *p; @@ -4558,8 +4666,9 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, #ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_getdeviceinfo *gdev) + union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; struct xdr_stream *xdr = resp->xdr; const struct nfsd4_layout_ops *ops; u32 starting_len = xdr->buf->len, needed_len; @@ -4611,8 +4720,9 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutget *lgp) + union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; struct xdr_stream *xdr = resp->xdr; const struct nfsd4_layout_ops *ops; __be32 *p; @@ -4638,8 +4748,9 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutcommit *lcp) + union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4659,8 +4770,9 @@ nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutreturn *lrp) + union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4745,8 +4857,9 @@ nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns)

static __be32 nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_copy *copy) + union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; __be32 *p;

nfserr = nfsd42_encode_write_res(resp, &copy->cp_res, @@ -4762,8 +4875,9 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_offload_status *os) + union nfsd4_op_u *u) { + struct nfsd4_offload_status *os = &u->offload_status; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4777,156 +4891,83 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, - struct nfsd4_read *read, - unsigned long *maxcount, u32 *eof, - loff_t *pos) + struct nfsd4_read *read) { - struct xdr_stream *xdr = resp->xdr; + bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); struct file *file = read->rd_nf->nf_file; - int starting_len = xdr->buf->len; - loff_t hole_pos; - __be32 nfserr; - __be32 *p, tmp; - __be64 tmp64; - - hole_pos = pos ? *pos : vfs_llseek(file, read->rd_offset, SEEK_HOLE); - if (hole_pos > read->rd_offset) - *maxcount = min_t(unsigned long, *maxcount, hole_pos - read->rd_offset); - *maxcount = min_t(unsigned long, *maxcount, (xdr->buf->buflen - xdr->buf->len)); + struct xdr_stream *xdr = resp->xdr; + unsigned long maxcount; + __be32 nfserr, *p;

/* Content type, offset, byte count */ p = xdr_reserve_space(xdr, 4 + 8 + 4); if (!p) - return nfserr_resource; + return nfserr_io; + if (resp->xdr->buf->page_len && splice_ok) { + WARN_ON_ONCE(splice_ok); + return nfserr_serverfault; + }

- read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, *maxcount); - if (read->rd_vlen < 0) - return nfserr_resource; + maxcount = min_t(unsigned long, read->rd_length, + (xdr->buf->buflen - xdr->buf->len));

- nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, - resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof); + if (file->f_op->splice_read && splice_ok) + nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); + else + nfserr = nfsd4_encode_readv(resp, read, file, maxcount); if (nfserr) return nfserr; - xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount)); - - tmp = htonl(NFS4_CONTENT_DATA); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp64 = cpu_to_be64(read->rd_offset); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp64, 8); - tmp = htonl(*maxcount); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp, 4); - - tmp = xdr_zero; - write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp, - xdr_pad_size(*maxcount)); - return nfs_ok; -} - -static __be32 -nfsd4_encode_read_plus_hole(struct nfsd4_compoundres *resp, - struct nfsd4_read *read, - unsigned long *maxcount, u32 *eof) -{ - struct file *file = read->rd_nf->nf_file; - loff_t data_pos = vfs_llseek(file, read->rd_offset, SEEK_DATA); - loff_t f_size = i_size_read(file_inode(file)); - unsigned long count; - __be32 *p; - - if (data_pos == -ENXIO) - data_pos = f_size; - else if (data_pos <= read->rd_offset || (data_pos < f_size && data_pos % PAGE_SIZE)) - return nfsd4_encode_read_plus_data(resp, read, maxcount, eof, &f_size); - count = data_pos - read->rd_offset;

- /* Content type, offset, byte count */ - p = xdr_reserve_space(resp->xdr, 4 + 8 + 8); - if (!p) - return nfserr_resource; - - *p++ = htonl(NFS4_CONTENT_HOLE); + *p++ = cpu_to_be32(NFS4_CONTENT_DATA); p = xdr_encode_hyper(p, read->rd_offset); - p = xdr_encode_hyper(p, count); + *p = cpu_to_be32(read->rd_length);

- *eof = (read->rd_offset + count) >= f_size; - *maxcount = min_t(unsigned long, count, *maxcount); return nfs_ok; }

static __be32 nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) + union nfsd4_op_u *u) { - unsigned long maxcount, count; + struct nfsd4_read *read = &u->read; + struct file *file = read->rd_nf->nf_file; struct xdr_stream *xdr = resp->xdr; - struct file *file; int starting_len = xdr->buf->len; - int last_segment = xdr->buf->len; - int segments = 0; - __be32 *p, tmp; - bool is_data; - loff_t pos; - u32 eof; + u32 segments = 0; + __be32 *p;

if (nfserr) return nfserr; - file = read->rd_nf->nf_file;

/* eof flag, segment count */ p = xdr_reserve_space(xdr, 4 + 4); if (!p) - return nfserr_resource; + return nfserr_io; xdr_commit_encode(xdr);

- maxcount = min_t(unsigned long, read->rd_length, - (xdr->buf->buflen - xdr->buf->len)); - count = maxcount; - - eof = read->rd_offset >= i_size_read(file_inode(file)); - if (eof) + read->rd_eof = read->rd_offset >= i_size_read(file_inode(file)); + if (read->rd_eof) goto out;

- pos = vfs_llseek(file, read->rd_offset, SEEK_HOLE); - is_data = pos > read->rd_offset; - - while (count > 0 && !eof) { - maxcount = count; - if (is_data) - nfserr = nfsd4_encode_read_plus_data(resp, read, &maxcount, &eof, - segments == 0 ? &pos : NULL); - else - nfserr = nfsd4_encode_read_plus_hole(resp, read, &maxcount, &eof); - if (nfserr) - goto out; - count -= maxcount; - read->rd_offset += maxcount; - is_data = !is_data; - last_segment = xdr->buf->len; - segments++; - } - -out: - if (nfserr && segments == 0) + nfserr = nfsd4_encode_read_plus_data(resp, read); + if (nfserr) { xdr_truncate_encode(xdr, starting_len); - else { - if (nfserr) { - xdr_truncate_encode(xdr, last_segment); - nfserr = nfs_ok; - eof = 0; - } - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp = htonl(segments); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); + return nfserr; }

+ segments++; + +out: + p = xdr_encode_bool(p, read->rd_eof); + *p = cpu_to_be32(segments); return nfserr; }

static __be32 nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_copy_notify *cn) + union nfsd4_op_u *u) { + struct nfsd4_copy_notify *cn = &u->copy_notify; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -4960,8 +5001,9 @@ nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_seek *seek) + union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; __be32 *p;

p = xdr_reserve_space(resp->xdr, 4 + 8); @@ -4972,7 +5014,8 @@ nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, }

static __be32 -nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) +nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *p) { return nfserr; } @@ -5023,8 +5066,9 @@ nfsd4_vbuf_to_stream(struct xdr_stream *xdr, char *buf, u32 buflen)

static __be32 nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_getxattr *getxattr) + union nfsd4_op_u *u) { + struct nfsd4_getxattr *getxattr = &u->getxattr; struct xdr_stream *xdr = resp->xdr; __be32 *p, err;

@@ -5047,8 +5091,9 @@ nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_setxattr *setxattr) + union nfsd4_op_u *u) { + struct nfsd4_setxattr *setxattr = &u->setxattr; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -5088,8 +5133,9 @@ nfsd4_listxattr_validate_cookie(struct nfsd4_listxattrs *listxattrs,

static __be32 nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_listxattrs *listxattrs) + union nfsd4_op_u *u) { + struct nfsd4_listxattrs *listxattrs = &u->listxattrs; struct xdr_stream *xdr = resp->xdr; u32 cookie_offset, count_offset, eof; u32 left, xdrleft, slen, count; @@ -5199,8 +5245,9 @@ nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr,

static __be32 nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_removexattr *removexattr) + union nfsd4_op_u *u) { + struct nfsd4_removexattr *removexattr = &u->removexattr; struct xdr_stream *xdr = resp->xdr; __be32 *p;

@@ -5212,7 +5259,7 @@ nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, return 0; }

-typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); +typedef __be32(*nfsd4_enc)(struct nfsd4_compoundres *, __be32, union nfsd4_op_u *u);

/* * Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1 @@ -5220,93 +5267,93 @@ typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); * done in the decoding phase. */ static const nfsd4_enc nfsd4_enc_ops[] = { - [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access, - [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close, - [OP_COMMIT] = (nfsd4_enc)nfsd4_encode_commit, - [OP_CREATE] = (nfsd4_enc)nfsd4_encode_create, - [OP_DELEGPURGE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_DELEGRETURN] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GETATTR] = (nfsd4_enc)nfsd4_encode_getattr, - [OP_GETFH] = (nfsd4_enc)nfsd4_encode_getfh, - [OP_LINK] = (nfsd4_enc)nfsd4_encode_link, - [OP_LOCK] = (nfsd4_enc)nfsd4_encode_lock, - [OP_LOCKT] = (nfsd4_enc)nfsd4_encode_lockt, - [OP_LOCKU] = (nfsd4_enc)nfsd4_encode_locku, - [OP_LOOKUP] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop, - [OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN] = (nfsd4_enc)nfsd4_encode_open, - [OP_OPENATTR] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm, - [OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade, - [OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTPUBFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTROOTFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_READ] = (nfsd4_enc)nfsd4_encode_read, - [OP_READDIR] = (nfsd4_enc)nfsd4_encode_readdir, - [OP_READLINK] = (nfsd4_enc)nfsd4_encode_readlink, - [OP_REMOVE] = (nfsd4_enc)nfsd4_encode_remove, - [OP_RENAME] = (nfsd4_enc)nfsd4_encode_rename, - [OP_RENEW] = (nfsd4_enc)nfsd4_encode_noop, - [OP_RESTOREFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_SAVEFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_SECINFO] = (nfsd4_enc)nfsd4_encode_secinfo, - [OP_SETATTR] = (nfsd4_enc)nfsd4_encode_setattr, - [OP_SETCLIENTID] = (nfsd4_enc)nfsd4_encode_setclientid, - [OP_SETCLIENTID_CONFIRM] = (nfsd4_enc)nfsd4_encode_noop, - [OP_VERIFY] = (nfsd4_enc)nfsd4_encode_noop, - [OP_WRITE] = (nfsd4_enc)nfsd4_encode_write, - [OP_RELEASE_LOCKOWNER] = (nfsd4_enc)nfsd4_encode_noop, + [OP_ACCESS] = nfsd4_encode_access, + [OP_CLOSE] = nfsd4_encode_close, + [OP_COMMIT] = nfsd4_encode_commit, + [OP_CREATE] = nfsd4_encode_create, + [OP_DELEGPURGE] = nfsd4_encode_noop, + [OP_DELEGRETURN] = nfsd4_encode_noop, + [OP_GETATTR] = nfsd4_encode_getattr, + [OP_GETFH] = nfsd4_encode_getfh, + [OP_LINK] = nfsd4_encode_link, + [OP_LOCK] = nfsd4_encode_lock, + [OP_LOCKT] = nfsd4_encode_lockt, + [OP_LOCKU] = nfsd4_encode_locku, + [OP_LOOKUP] = nfsd4_encode_noop, + [OP_LOOKUPP] = nfsd4_encode_noop, + [OP_NVERIFY] = nfsd4_encode_noop, + [OP_OPEN] = nfsd4_encode_open, + [OP_OPENATTR] = nfsd4_encode_noop, + [OP_OPEN_CONFIRM] = nfsd4_encode_open_confirm, + [OP_OPEN_DOWNGRADE] = nfsd4_encode_open_downgrade, + [OP_PUTFH] = nfsd4_encode_noop, + [OP_PUTPUBFH] = nfsd4_encode_noop, + [OP_PUTROOTFH] = nfsd4_encode_noop, + [OP_READ] = nfsd4_encode_read, + [OP_READDIR] = nfsd4_encode_readdir, + [OP_READLINK] = nfsd4_encode_readlink, + [OP_REMOVE] = nfsd4_encode_remove, + [OP_RENAME] = nfsd4_encode_rename, + [OP_RENEW] = nfsd4_encode_noop, + [OP_RESTOREFH] = nfsd4_encode_noop, + [OP_SAVEFH] = nfsd4_encode_noop, + [OP_SECINFO] = nfsd4_encode_secinfo, + [OP_SETATTR] = nfsd4_encode_setattr, + [OP_SETCLIENTID] = nfsd4_encode_setclientid, + [OP_SETCLIENTID_CONFIRM] = nfsd4_encode_noop, + [OP_VERIFY] = nfsd4_encode_noop, + [OP_WRITE] = nfsd4_encode_write, + [OP_RELEASE_LOCKOWNER] = nfsd4_encode_noop,

/* NFSv4.1 operations */ - [OP_BACKCHANNEL_CTL] = (nfsd4_enc)nfsd4_encode_noop, - [OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_bind_conn_to_session, - [OP_EXCHANGE_ID] = (nfsd4_enc)nfsd4_encode_exchange_id, - [OP_CREATE_SESSION] = (nfsd4_enc)nfsd4_encode_create_session, - [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_noop, - [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_BACKCHANNEL_CTL] = nfsd4_encode_noop, + [OP_BIND_CONN_TO_SESSION] = nfsd4_encode_bind_conn_to_session, + [OP_EXCHANGE_ID] = nfsd4_encode_exchange_id, + [OP_CREATE_SESSION] = nfsd4_encode_create_session, + [OP_DESTROY_SESSION] = nfsd4_encode_noop, + [OP_FREE_STATEID] = nfsd4_encode_noop, + [OP_GET_DIR_DELEGATION] = nfsd4_encode_noop, #ifdef CONFIG_NFSD_PNFS - [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_getdeviceinfo, - [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_layoutcommit, - [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_layoutget, - [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_layoutreturn, + [OP_GETDEVICEINFO] = nfsd4_encode_getdeviceinfo, + [OP_GETDEVICELIST] = nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = nfsd4_encode_layoutcommit, + [OP_LAYOUTGET] = nfsd4_encode_layoutget, + [OP_LAYOUTRETURN] = nfsd4_encode_layoutreturn, #else - [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETDEVICEINFO] = nfsd4_encode_noop, + [OP_GETDEVICELIST] = nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = nfsd4_encode_noop, + [OP_LAYOUTGET] = nfsd4_encode_noop, + [OP_LAYOUTRETURN] = nfsd4_encode_noop, #endif - [OP_SECINFO_NO_NAME] = (nfsd4_enc)nfsd4_encode_secinfo_no_name, - [OP_SEQUENCE] = (nfsd4_enc)nfsd4_encode_sequence, - [OP_SET_SSV] = (nfsd4_enc)nfsd4_encode_noop, - [OP_TEST_STATEID] = (nfsd4_enc)nfsd4_encode_test_stateid, - [OP_WANT_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, - [OP_DESTROY_CLIENTID] = (nfsd4_enc)nfsd4_encode_noop, - [OP_RECLAIM_COMPLETE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO_NO_NAME] = nfsd4_encode_secinfo_no_name, + [OP_SEQUENCE] = nfsd4_encode_sequence, + [OP_SET_SSV] = nfsd4_encode_noop, + [OP_TEST_STATEID] = nfsd4_encode_test_stateid, + [OP_WANT_DELEGATION] = nfsd4_encode_noop, + [OP_DESTROY_CLIENTID] = nfsd4_encode_noop, + [OP_RECLAIM_COMPLETE] = nfsd4_encode_noop,

/* NFSv4.2 operations */ - [OP_ALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_COPY] = (nfsd4_enc)nfsd4_encode_copy, - [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_copy_notify, - [OP_DEALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_IO_ADVISE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTERROR] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTSTATS] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OFFLOAD_CANCEL] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OFFLOAD_STATUS] = (nfsd4_enc)nfsd4_encode_offload_status, - [OP_READ_PLUS] = (nfsd4_enc)nfsd4_encode_read_plus, - [OP_SEEK] = (nfsd4_enc)nfsd4_encode_seek, - [OP_WRITE_SAME] = (nfsd4_enc)nfsd4_encode_noop, - [OP_CLONE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_ALLOCATE] = nfsd4_encode_noop, + [OP_COPY] = nfsd4_encode_copy, + [OP_COPY_NOTIFY] = nfsd4_encode_copy_notify, + [OP_DEALLOCATE] = nfsd4_encode_noop, + [OP_IO_ADVISE] = nfsd4_encode_noop, + [OP_LAYOUTERROR] = nfsd4_encode_noop, + [OP_LAYOUTSTATS] = nfsd4_encode_noop, + [OP_OFFLOAD_CANCEL] = nfsd4_encode_noop, + [OP_OFFLOAD_STATUS] = nfsd4_encode_offload_status, + [OP_READ_PLUS] = nfsd4_encode_read_plus, + [OP_SEEK] = nfsd4_encode_seek, + [OP_WRITE_SAME] = nfsd4_encode_noop, + [OP_CLONE] = nfsd4_encode_noop,

/* RFC 8276 extended atributes operations */ - [OP_GETXATTR] = (nfsd4_enc)nfsd4_encode_getxattr, - [OP_SETXATTR] = (nfsd4_enc)nfsd4_encode_setxattr, - [OP_LISTXATTRS] = (nfsd4_enc)nfsd4_encode_listxattrs, - [OP_REMOVEXATTR] = (nfsd4_enc)nfsd4_encode_removexattr, + [OP_GETXATTR] = nfsd4_encode_getxattr, + [OP_SETXATTR] = nfsd4_encode_setxattr, + [OP_LISTXATTRS] = nfsd4_encode_listxattrs, + [OP_REMOVEXATTR] = nfsd4_encode_removexattr, };

/* diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 573de0d49e17..76a60e7a7509 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -581,7 +581,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)

cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET; switch(num) { +#ifdef CONFIG_NFSD_V2 case 2: +#endif case 3: nfsd_vers(nn, num, cmd); break; @@ -601,7 +603,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) } break; default: - return -EINVAL; + /* Ignore requests to disable non-existent versions */ + if (cmd == NFSD_SET) + return -EINVAL; } vers += len + 1; } while ((len = qword_get(&mesg, vers, size)) > 0); @@ -1448,9 +1452,7 @@ static __net_init int nfsd_init_net(struct net *net) goto out_idmap_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; - retval = nfsd4_init_leases_net(nn); - if (retval) - goto out_drc_error; + nfsd4_init_leases_net(nn); retval = nfsd_reply_cache_init(nn); if (retval) goto out_cache_error; @@ -1460,8 +1462,6 @@ static __net_init int nfsd_init_net(struct net *net) return 0;

out_cache_error: - nfsd4_leases_net_shutdown(nn); -out_drc_error: nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); @@ -1477,7 +1477,6 @@ static __net_exit void nfsd_exit_net(struct net *net) nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); - nfsd4_leases_net_shutdown(nn); }

static struct pernet_operations nfsd_net_ops = { diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 09726c5b9a31..fa0144a74267 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -64,8 +64,7 @@ struct readdir_cd {

extern struct svc_program nfsd_program; -extern const struct svc_version nfsd_version2, nfsd_version3, - nfsd_version4; +extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; extern unsigned long nfsd_drc_max_mem; @@ -505,8 +504,7 @@ extern void unregister_cld_notifier(void); extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn); #endif

-extern int nfsd4_init_leases_net(struct nfsd_net *nn); -extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn); +extern void nfsd4_init_leases_net(struct nfsd_net *nn);

#else /* CONFIG_NFSD_V4 */ static inline int nfsd4_is_junction(struct dentry *dentry) @@ -514,8 +512,7 @@ static inline int nfsd4_is_junction(struct dentry *dentry) return 0; }

-static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; }; -static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {}; +static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { };

#define register_cld_notifier() 0 #define unregister_cld_notifier() do { } while(0) diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index c3ae6414fc5c..513e028b0bbe 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -220,7 +220,7 @@ __be32 fh_update(struct svc_fh *); void fh_put(struct svc_fh *);

static __inline__ struct svc_fh * -fh_copy(struct svc_fh *dst, struct svc_fh *src) +fh_copy(struct svc_fh *dst, const struct svc_fh *src) { WARN_ON(src->fh_dentry);

@@ -229,7 +229,7 @@ fh_copy(struct svc_fh *dst, struct svc_fh *src) }

static inline void -fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) +fh_copy_shallow(struct knfsd_fh *dst, const struct knfsd_fh *src) { dst->fh_size = src->fh_size; memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size); @@ -243,7 +243,8 @@ fh_init(struct svc_fh *fhp, int maxsize) return fhp; }

-static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +static inline bool fh_match(const struct knfsd_fh *fh1, + const struct knfsd_fh *fh2) { if (fh1->fh_size != fh2->fh_size) return false; @@ -252,7 +253,8 @@ static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) return true; }

-static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +static inline bool fh_fsid_match(const struct knfsd_fh *fh1, + const struct knfsd_fh *fh2) { if (fh1->fh_fsid_type != fh2->fh_fsid_type) return false; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 82b3ddeacc33..9744443c3965 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - return rpc_drop_reply; + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; }

@@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - return rpc_drop_reply; + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; }

@@ -848,65 +848,3 @@ const struct svc_version nfsd_version2 = { .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS2_SVC_XDRSIZE, }; - -/* - * Map errnos to NFS errnos. - */ -__be32 -nfserrno (int errno) -{ - static struct { - __be32 nfserr; - int syserr; - } nfs_errtbl[] = { - { nfs_ok, 0 }, - { nfserr_perm, -EPERM }, - { nfserr_noent, -ENOENT }, - { nfserr_io, -EIO }, - { nfserr_nxio, -ENXIO }, - { nfserr_fbig, -E2BIG }, - { nfserr_stale, -EBADF }, - { nfserr_acces, -EACCES }, - { nfserr_exist, -EEXIST }, - { nfserr_xdev, -EXDEV }, - { nfserr_mlink, -EMLINK }, - { nfserr_nodev, -ENODEV }, - { nfserr_notdir, -ENOTDIR }, - { nfserr_isdir, -EISDIR }, - { nfserr_inval, -EINVAL }, - { nfserr_fbig, -EFBIG }, - { nfserr_nospc, -ENOSPC }, - { nfserr_rofs, -EROFS }, - { nfserr_mlink, -EMLINK }, - { nfserr_nametoolong, -ENAMETOOLONG }, - { nfserr_notempty, -ENOTEMPTY }, -#ifdef EDQUOT - { nfserr_dquot, -EDQUOT }, -#endif - { nfserr_stale, -ESTALE }, - { nfserr_jukebox, -ETIMEDOUT }, - { nfserr_jukebox, -ERESTARTSYS }, - { nfserr_jukebox, -EAGAIN }, - { nfserr_jukebox, -EWOULDBLOCK }, - { nfserr_jukebox, -ENOMEM }, - { nfserr_io, -ETXTBSY }, - { nfserr_notsupp, -EOPNOTSUPP }, - { nfserr_toosmall, -ETOOSMALL }, - { nfserr_serverfault, -ESERVERFAULT }, - { nfserr_serverfault, -ENFILE }, - { nfserr_io, -EREMOTEIO }, - { nfserr_stale, -EOPENSTALE }, - { nfserr_io, -EUCLEAN }, - { nfserr_perm, -ENOKEY }, - { nfserr_no_grace, -ENOGRACE}, - }; - int i; - - for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { - if (nfs_errtbl[i].syserr == errno) - return nfs_errtbl[i].nfserr; - } - WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno); - return nfserr_io; -} - diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index c7695ebd28dc..0c75636054a5 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -91,8 +91,12 @@ unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; static const struct svc_version *nfsd_acl_version[] = { +# if defined(CONFIG_NFSD_V2_ACL) [2] = &nfsd_acl_version2, +# endif +# if defined(CONFIG_NFSD_V3_ACL) [3] = &nfsd_acl_version3, +# endif };

#define NFSD_ACL_MINVERS 2 @@ -116,7 +120,9 @@ static struct svc_stat nfsd_acl_svcstats = { #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */

static const struct svc_version *nfsd_version[] = { +#if defined(CONFIG_NFSD_V2) [2] = &nfsd_version2, +#endif [3] = &nfsd_version3, #if defined(CONFIG_NFSD_V4) [4] = &nfsd_version4, @@ -1065,7 +1071,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)

nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0); *statp = proc->pc_func(rqstp); - if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) + if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop;

if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e2daef3cc003..e94634d30591 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -368,6 +368,7 @@ struct nfs4_client { #define NFSD4_CLIENT_UPCALL_LOCK (5) /* upcall serialization */ #define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \ 1 << NFSD4_CLIENT_CB_KILL) +#define NFSD4_CLIENT_CB_RECALL_ANY (6) unsigned long cl_flags; const struct cred *cl_cb_cred; struct rpc_clnt *cl_cb_client; @@ -411,6 +412,10 @@ struct nfs4_client {

unsigned int cl_state; atomic_t cl_delegs_in_recall; + + struct nfsd4_cb_recall_any *cl_ra; + time64_t cl_ra_time; + struct list_head cl_ra_cblist; };

/* struct nfs4_client_reset @@ -536,16 +541,13 @@ struct nfs4_clnt_odstate { * inode can have multiple filehandles associated with it, so there is * (potentially) a many to one relationship between this struct and struct * inode. - * - * These are hashed by filehandle in the file_hashtbl, which is protected by - * the global state_lock spinlock. */ struct nfs4_file { refcount_t fi_ref; struct inode * fi_inode; bool fi_aliased; spinlock_t fi_lock; - struct hlist_node fi_hash; /* hash on fi_fhandle */ + struct rhlist_head fi_rlist; struct list_head fi_stateids; union { struct list_head fi_delegations; @@ -639,6 +641,7 @@ enum nfsd4_cb_op { NFSPROC4_CLNT_CB_OFFLOAD, NFSPROC4_CLNT_CB_SEQUENCE, NFSPROC4_CLNT_CB_NOTIFY_LOCK, + NFSPROC4_CLNT_CB_RECALL_ANY, };

/* Returns true iff a is later than b: */ diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 132335011cca..4183819ea082 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,9 +9,12 @@ #define _NFSD_TRACE_H

#include <linux/tracepoint.h> +#include <linux/sunrpc/xprt.h> +#include <trace/misc/nfs.h>

#include "export.h" #include "nfsfh.h" +#include "xdr4.h"

#define NFSD_TRACE_PROC_RES_FIELDS \ __field(unsigned int, netns_ino) \ @@ -604,6 +607,7 @@ DEFINE_STATEID_EVENT(layout_recall_release);

DEFINE_STATEID_EVENT(open); DEFINE_STATEID_EVENT(deleg_read); +DEFINE_STATEID_EVENT(deleg_return); DEFINE_STATEID_EVENT(deleg_recall);

DECLARE_EVENT_CLASS(nfsd_stateseqid_class, @@ -636,6 +640,61 @@ DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \ DEFINE_STATESEQID_EVENT(preprocess); DEFINE_STATESEQID_EVENT(open_confirm);

+TRACE_DEFINE_ENUM(NFS4_OPEN_STID); +TRACE_DEFINE_ENUM(NFS4_LOCK_STID); +TRACE_DEFINE_ENUM(NFS4_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_CLOSED_STID); +TRACE_DEFINE_ENUM(NFS4_REVOKED_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_CLOSED_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_LAYOUT_STID); + +#define show_stid_type(x) \ + __print_flags(x, "|", \ + { NFS4_OPEN_STID, "OPEN" }, \ + { NFS4_LOCK_STID, "LOCK" }, \ + { NFS4_DELEG_STID, "DELEG" }, \ + { NFS4_CLOSED_STID, "CLOSED" }, \ + { NFS4_REVOKED_DELEG_STID, "REVOKED" }, \ + { NFS4_CLOSED_DELEG_STID, "CLOSED_DELEG" }, \ + { NFS4_LAYOUT_STID, "LAYOUT" }) + +DECLARE_EVENT_CLASS(nfsd_stid_class, + TP_PROTO( + const struct nfs4_stid *stid + ), + TP_ARGS(stid), + TP_STRUCT__entry( + __field(unsigned long, sc_type) + __field(int, sc_count) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + ), + TP_fast_assign( + const stateid_t *stp = &stid->sc_stateid; + + __entry->sc_type = stid->sc_type; + __entry->sc_count = refcount_read(&stid->sc_count); + __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; + __entry->cl_id = stp->si_opaque.so_clid.cl_id; + __entry->si_id = stp->si_opaque.so_id; + __entry->si_generation = stp->si_generation; + ), + TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s", + __entry->cl_boot, __entry->cl_id, + __entry->si_id, __entry->si_generation, + __entry->sc_count, show_stid_type(__entry->sc_type) + ) +); + +#define DEFINE_STID_EVENT(name) \ +DEFINE_EVENT(nfsd_stid_class, nfsd_stid_##name, \ + TP_PROTO(const struct nfs4_stid *stid), \ + TP_ARGS(stid)) + +DEFINE_STID_EVENT(revoke); + DECLARE_EVENT_CLASS(nfsd_clientid_class, TP_PROTO(const clientid_t *clid), TP_ARGS(clid), @@ -1436,6 +1495,32 @@ TRACE_EVENT(nfsd_cb_offload, __entry->fh_hash, __entry->count, __entry->status) );

+TRACE_EVENT(nfsd_cb_recall_any, + TP_PROTO( + const struct nfsd4_cb_recall_any *ra + ), + TP_ARGS(ra), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, keep) + __field(unsigned long, bmval0) + __sockaddr(addr, ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen) + ), + TP_fast_assign( + __entry->cl_boot = ra->ra_cb.cb_clp->cl_clientid.cl_boot; + __entry->cl_id = ra->ra_cb.cb_clp->cl_clientid.cl_id; + __entry->keep = ra->ra_keep; + __entry->bmval0 = ra->ra_bmval[0]; + __assign_sockaddr(addr, &ra->ra_cb.cb_clp->cl_addr, + ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen); + ), + TP_printk("addr=%pISpc client %08x:%08x keep=%u bmval0=%s", + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, + __entry->keep, show_rca_mask(__entry->bmval0) + ) +); + DECLARE_EVENT_CLASS(nfsd_cb_done_class, TP_PROTO( const stateid_t *stp, @@ -1475,6 +1560,27 @@ DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_notify_lock_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_layout_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_offload_done);

+TRACE_EVENT(nfsd_cb_recall_any_done, + TP_PROTO( + const struct nfsd4_callback *cb, + const struct rpc_task *task + ), + TP_ARGS(cb, task), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(int, status) + ), + TP_fast_assign( + __entry->status = task->tk_status; + __entry->cl_boot = cb->cb_clp->cl_clientid.cl_boot; + __entry->cl_id = cb->cb_clp->cl_clientid.cl_id; + ), + TP_printk("client %08x:%08x status=%d", + __entry->cl_boot, __entry->cl_id, __entry->status + ) +); + #endif /* _NFSD_TRACE_H */

#undef TRACE_INCLUDE_PATH diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eccc6ce55a63..5d6a61d47a90 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -49,6 +49,69 @@

#define NFSDDBG_FACILITY NFSDDBG_FILEOP

+/** + * nfserrno - Map Linux errnos to NFS errnos + * @errno: POSIX(-ish) error code to be mapped + * + * Returns the appropriate (net-endian) nfserr_* (or nfs_ok if errno is 0). If + * it's an error we don't expect, log it once and return nfserr_io. + */ +__be32 +nfserrno (int errno) +{ + static struct { + __be32 nfserr; + int syserr; + } nfs_errtbl[] = { + { nfs_ok, 0 }, + { nfserr_perm, -EPERM }, + { nfserr_noent, -ENOENT }, + { nfserr_io, -EIO }, + { nfserr_nxio, -ENXIO }, + { nfserr_fbig, -E2BIG }, + { nfserr_stale, -EBADF }, + { nfserr_acces, -EACCES }, + { nfserr_exist, -EEXIST }, + { nfserr_xdev, -EXDEV }, + { nfserr_mlink, -EMLINK }, + { nfserr_nodev, -ENODEV }, + { nfserr_notdir, -ENOTDIR }, + { nfserr_isdir, -EISDIR }, + { nfserr_inval, -EINVAL }, + { nfserr_fbig, -EFBIG }, + { nfserr_nospc, -ENOSPC }, + { nfserr_rofs, -EROFS }, + { nfserr_mlink, -EMLINK }, + { nfserr_nametoolong, -ENAMETOOLONG }, + { nfserr_notempty, -ENOTEMPTY }, + { nfserr_dquot, -EDQUOT }, + { nfserr_stale, -ESTALE }, + { nfserr_jukebox, -ETIMEDOUT }, + { nfserr_jukebox, -ERESTARTSYS }, + { nfserr_jukebox, -EAGAIN }, + { nfserr_jukebox, -EWOULDBLOCK }, + { nfserr_jukebox, -ENOMEM }, + { nfserr_io, -ETXTBSY }, + { nfserr_notsupp, -EOPNOTSUPP }, + { nfserr_toosmall, -ETOOSMALL }, + { nfserr_serverfault, -ESERVERFAULT }, + { nfserr_serverfault, -ENFILE }, + { nfserr_io, -EREMOTEIO }, + { nfserr_stale, -EOPENSTALE }, + { nfserr_io, -EUCLEAN }, + { nfserr_perm, -ENOKEY }, + { nfserr_no_grace, -ENOGRACE}, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { + if (nfs_errtbl[i].syserr == errno) + return nfs_errtbl[i].nfserr; + } + WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno); + return nfserr_io; +} + /* * Called from nfsd_lookup and encode_dirent. Check if we have crossed * a mount point. @@ -1317,7 +1380,6 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode &= ~current_umask();

err = 0; - host_err = 0; switch (type) { case S_IFREG: host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 9744b041105b..dbdfef7ae85b 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -60,6 +60,7 @@ static inline void nfsd_attrs_free(struct nfsd_attrs *attrs) posix_acl_release(attrs->na_dpacl); }

+__be32 nfserrno (int errno); int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); __be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 36c3340c1d54..510978e602da 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -896,5 +896,10 @@ struct nfsd4_operation { union nfsd4_op_u *); };

+struct nfsd4_cb_recall_any { + struct nfsd4_callback ra_cb; + u32 ra_keep; + u32 ra_bmval[1]; +};

#endif diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index 547cf07cf4e0..0d39af1b00a0 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -48,3 +48,9 @@ #define NFS4_dec_cb_offload_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) +#define NFS4_enc_cb_recall_any_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ + 1 + 1 + 1) +#define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + \ + op_dec_sz) diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index bb7e33c24073..d26026090024 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -102,7 +102,7 @@ void ni_clear(struct ntfs_inode *ni) { struct rb_node *node;

- if (!ni->vfs_inode.i_nlink && is_rec_inuse(ni->mi.mrec)) + if (!ni->vfs_inode.i_nlink && ni->mi.mrec && is_rec_inuse(ni->mi.mrec)) ni_delete_all(ni);

al_destroy(ni); @@ -3255,6 +3255,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) return 0; }

+ if (!ni->mi.mrec) + goto out; + if (is_rec_inuse(ni->mi.mrec) && !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING) && inode->i_nlink) { bool modified = false; diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 1eac80d55b55..4c2d079b3d49 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -1674,6 +1674,7 @@ struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir)

out: if (err) { + make_bad_inode(inode); iput(inode); ni = ERR_PTR(err); } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 7371f7855e4c..eee01db6e0cc 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -998,6 +998,7 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le = NULL; struct ATTRIB *a; const struct INDEX_NAMES *in = &s_index_names[indx->type]; + struct INDEX_ROOT *root = NULL;

a = ni_find_attr(ni, NULL, &le, ATTR_ROOT, in->name, in->name_len, NULL, mi); @@ -1007,7 +1008,15 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, if (attr) *attr = a;

- return resident_data_ex(a, sizeof(struct INDEX_ROOT)); + root = resident_data_ex(a, sizeof(struct INDEX_ROOT)); + + /* length check */ + if (root && offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root->ihdr.used) > + le32_to_cpu(a->res.data_size)) { + return NULL; + } + + return root; }

static int indx_write(struct ntfs_index *indx, struct ntfs_inode *ni, diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 9e3dac51eb26..d4dbaae8b521 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -59,7 +59,7 @@ struct bvec_iter {

unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ -} __packed; +} __packed __aligned(4);

struct bvec_iter_all { struct bio_vec bv; diff --git a/include/linux/decompress/mm.h b/include/linux/decompress/mm.h index 9192986b1a73..ac862422df15 100644 --- a/include/linux/decompress/mm.h +++ b/include/linux/decompress/mm.h @@ -48,7 +48,7 @@ MALLOC_VISIBLE void *malloc(int size) if (!malloc_ptr) malloc_ptr = free_mem_ptr;

- malloc_ptr = (malloc_ptr + 3) & ~3; /* Align */ + malloc_ptr = (malloc_ptr + 7) & ~7; /* Align */

p = (void *)malloc_ptr; malloc_ptr += size; diff --git a/include/linux/efi.h b/include/linux/efi.h index 4e1bfee9675d..de6d6558a4d3 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -390,6 +390,7 @@ void efi_native_runtime_setup(void); #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) #define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_SMBIOS_PROTOCOL_GUID EFI_GUID(0x03583ff6, 0xcb36, 0x4940, 0x94, 0x7e, 0xb9, 0xb3, 0x9f, 0x4a, 0xfa, 0xf7) +#define EFI_MEMORY_ATTRIBUTE_PROTOCOL_GUID EFI_GUID(0xf4560cf6, 0x40ec, 0x4b4a, 0xa1, 0x92, 0xbf, 0x1d, 0x57, 0xd0, 0xb1, 0x89)

#define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) diff --git a/include/linux/fs.h b/include/linux/fs.h index 67313881f8ac..092d8fa10153 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1189,6 +1189,13 @@ extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); extern bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return smp_load_acquire(&inode->i_flctx); +} + #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1334,6 +1341,13 @@ static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, { return false; } + +static inline struct file_lock_context * +locks_inode_context(const struct inode *inode) +{ + return NULL; +} + #endif /* !CONFIG_FILE_LOCKING */

static inline struct inode *file_inode(const struct file *f) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index bef8db9d6c08..e5f4b6f8d1c0 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -437,11 +437,13 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #include <linux/netfilter/nf_conntrack_zones_common.h>

void nf_ct_attach(struct sk_buff *, const struct sk_buff *); +void nf_ct_set_closing(struct nf_conntrack *nfct); struct nf_conntrack_tuple; bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb); #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} +static inline void nf_ct_set_closing(struct nf_conntrack *nfct) {} struct nf_conntrack_tuple; static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) @@ -459,6 +461,8 @@ struct nf_ct_hook { bool (*get_tuple_skb)(struct nf_conntrack_tuple *, const struct sk_buff *); void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); + void (*set_closing)(struct nf_conntrack *nfct); + int (*confirm)(struct sk_buff *skb); }; extern const struct nf_ct_hook __rcu *nf_ct_hook;

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 8d04b6a5964c..730003c4f4af 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -732,4 +732,17 @@ enum nfs4_setxattr_options { SETXATTR4_CREATE = 1, SETXATTR4_REPLACE = 2, }; + +enum { + RCA4_TYPE_MASK_RDATA_DLG = 0, + RCA4_TYPE_MASK_WDATA_DLG = 1, + RCA4_TYPE_MASK_DIR_DLG = 2, + RCA4_TYPE_MASK_FILE_LAYOUT = 3, + RCA4_TYPE_MASK_BLK_LAYOUT = 4, + RCA4_TYPE_MASK_OBJ_LAYOUT_MIN = 8, + RCA4_TYPE_MASK_OBJ_LAYOUT_MAX = 9, + RCA4_TYPE_MASK_OTHER_LAYOUT_MIN = 12, + RCA4_TYPE_MASK_OTHER_LAYOUT_MAX = 15, +}; + #endif diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 43ac3fa760db..9783b9107d76 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -412,6 +412,8 @@ extern int composite_dev_prepare(struct usb_composite_driver *composite, extern int composite_os_desc_req_prepare(struct usb_composite_dev *cdev, struct usb_ep *ep0); void composite_dev_cleanup(struct usb_composite_dev *cdev); +void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c);

static inline struct usb_composite_driver *to_cdriver( struct usb_gadget_driver *gdrv) diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index dc3092cea99e..5bec668b41dc 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -309,6 +309,7 @@ struct usb_udc; struct usb_gadget_ops { int (*get_frame)(struct usb_gadget *); int (*wakeup)(struct usb_gadget *); + int (*set_remote_wakeup)(struct usb_gadget *, int set); int (*set_selfpowered) (struct usb_gadget *, int is_selfpowered); int (*vbus_session) (struct usb_gadget *, int is_active); int (*vbus_draw) (struct usb_gadget *, unsigned mA); @@ -383,6 +384,8 @@ struct usb_gadget_ops { * @connected: True if gadget is connected. * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. + * @wakeup_capable: True if gadget is capable of sending remote wakeup. + * @wakeup_armed: True if gadget is armed by the host for remote wakeup. * @irq: the interrupt number for device controller. * @id_number: a unique ID number for ensuring that gadget names are distinct * @@ -444,6 +447,8 @@ struct usb_gadget { unsigned deactivated:1; unsigned connected:1; unsigned lpm_capable:1; + unsigned wakeup_capable:1; + unsigned wakeup_armed:1; int irq; int id_number; }; @@ -600,6 +605,7 @@ static inline int gadget_is_otg(struct usb_gadget *g) #if IS_ENABLED(CONFIG_USB_GADGET) int usb_gadget_frame_number(struct usb_gadget *gadget); int usb_gadget_wakeup(struct usb_gadget *gadget); +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set); int usb_gadget_set_selfpowered(struct usb_gadget *gadget); int usb_gadget_clear_selfpowered(struct usb_gadget *gadget); int usb_gadget_vbus_connect(struct usb_gadget *gadget); @@ -615,6 +621,8 @@ static inline int usb_gadget_frame_number(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_wakeup(struct usb_gadget *gadget) { return 0; } +static inline int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ return 0; } static inline int usb_gadget_set_selfpowered(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index c48186bf4737..21da31e1dff5 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -85,6 +85,11 @@ struct ipv6_bpf_stub { sockptr_t optval, unsigned int optlen); int (*ipv6_getsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); + int (*ipv6_dev_get_saddr)(struct net *net, + const struct net_device *dst_dev, + const struct in6_addr *daddr, + unsigned int prefs, + struct in6_addr *saddr); }; extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;

diff --git a/include/net/mctp.h b/include/net/mctp.h index 82800d521c3d..7ed84054f462 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -249,6 +249,7 @@ struct mctp_route { struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, mctp_eid_t daddr);

+/* always takes ownership of skb */ int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag);

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 6a2019aaa464..3dbf947285be 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -125,6 +125,12 @@ struct nf_conn { union nf_conntrack_proto proto; };

+static inline struct nf_conn * +nf_ct_to_nf_conn(const struct nf_conntrack *nfct) +{ + return container_of(nfct, struct nf_conn, ct_general); +} + static inline struct nf_conn * nf_ct_tuplehash_to_ctrack(const struct nf_conntrack_tuple_hash *hash) { @@ -175,6 +181,8 @@ nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo)

void nf_ct_destroy(struct nf_conntrack *nfct);

+void nf_conntrack_tcp_set_closing(struct nf_conn *ct); + /* decrement reference count on a conntrack */ static inline void nf_ct_put(struct nf_conn *ct) { diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index d2751ed536df..a64713fe5264 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -204,6 +204,7 @@ struct scsi_device { unsigned use_10_for_rw:1; /* first try 10-byte read / write */ unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */ unsigned set_dbd_for_ms:1; /* Set "DBD" field in mode sense */ + unsigned read_before_ms:1; /* perform a READ before MODE SENSE */ unsigned no_report_opcodes:1; /* no REPORT SUPPORTED OPERATION CODES */ unsigned no_write_same:1; /* no WRITE SAME command */ unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */ @@ -479,28 +480,51 @@ extern const char *scsi_device_state_name(enum scsi_device_state); extern int scsi_is_sdev_device(const struct device *); extern int scsi_is_target_device(const struct device *); extern void scsi_sanitize_inquiry_string(unsigned char *s, int len); -extern int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, - int data_direction, void *buffer, unsigned bufflen, - unsigned char *sense, struct scsi_sense_hdr *sshdr, - int timeout, int retries, blk_opf_t flags, - req_flags_t rq_flags, int *resid); + +/* Optional arguments to scsi_execute_cmd */ +struct scsi_exec_args { + unsigned char *sense; /* sense buffer */ + unsigned int sense_len; /* sense buffer len */ + struct scsi_sense_hdr *sshdr; /* decoded sense header */ + blk_mq_req_flags_t req_flags; /* BLK_MQ_REQ flags */ + int *resid; /* residual length */ +}; + +int scsi_execute_cmd(struct scsi_device *sdev, const unsigned char *cmd, + blk_opf_t opf, void *buffer, unsigned int bufflen, + int timeout, int retries, + const struct scsi_exec_args *args); + /* Make sure any sense buffer is the correct size. */ -#define scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense, \ - sshdr, timeout, retries, flags, rq_flags, resid) \ +#define scsi_execute(_sdev, _cmd, _data_dir, _buffer, _bufflen, _sense, \ + _sshdr, _timeout, _retries, _flags, _rq_flags, \ + _resid) \ ({ \ - BUILD_BUG_ON((sense) != NULL && \ - sizeof(sense) != SCSI_SENSE_BUFFERSIZE); \ - __scsi_execute(sdev, cmd, data_direction, buffer, bufflen, \ - sense, sshdr, timeout, retries, flags, rq_flags, \ - resid); \ + scsi_execute_cmd(_sdev, _cmd, (_data_dir == DMA_TO_DEVICE ? \ + REQ_OP_DRV_OUT : REQ_OP_DRV_IN) | _flags, \ + _buffer, _bufflen, _timeout, _retries, \ + &(struct scsi_exec_args) { \ + .sense = _sense, \ + .sshdr = _sshdr, \ + .req_flags = _rq_flags & RQF_PM ? \ + BLK_MQ_REQ_PM : 0, \ + .resid = _resid, \ + }); \ }) + static inline int scsi_execute_req(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout, int retries, int *resid) { - return scsi_execute(sdev, cmd, data_direction, buffer, - bufflen, NULL, sshdr, timeout, retries, 0, 0, resid); + return scsi_execute_cmd(sdev, cmd, + data_direction == DMA_TO_DEVICE ? + REQ_OP_DRV_OUT : REQ_OP_DRV_IN, buffer, + bufflen, timeout, retries, + &(struct scsi_exec_args) { + .sshdr = sshdr, + .resid = resid, + }); } extern void sdev_disable_disk_events(struct scsi_device *sdev); extern void sdev_enable_disk_events(struct scsi_device *sdev); diff --git a/include/trace/events/fs.h b/include/trace/events/fs.h deleted file mode 100644 index 738b97f22f36..000000000000 --- a/include/trace/events/fs.h +++ /dev/null @@ -1,122 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Display helpers for generic filesystem items - * - * Author: Chuck Lever chuck.lever@oracle.com - * - * Copyright (c) 2020, Oracle and/or its affiliates. - */ - -#include <linux/fs.h> - -#define show_fs_dirent_type(x) \ - __print_symbolic(x, \ - { DT_UNKNOWN, "UNKNOWN" }, \ - { DT_FIFO, "FIFO" }, \ - { DT_CHR, "CHR" }, \ - { DT_DIR, "DIR" }, \ - { DT_BLK, "BLK" }, \ - { DT_REG, "REG" }, \ - { DT_LNK, "LNK" }, \ - { DT_SOCK, "SOCK" }, \ - { DT_WHT, "WHT" }) - -#define show_fs_fcntl_open_flags(x) \ - __print_flags(x, "|", \ - { O_WRONLY, "O_WRONLY" }, \ - { O_RDWR, "O_RDWR" }, \ - { O_CREAT, "O_CREAT" }, \ - { O_EXCL, "O_EXCL" }, \ - { O_NOCTTY, "O_NOCTTY" }, \ - { O_TRUNC, "O_TRUNC" }, \ - { O_APPEND, "O_APPEND" }, \ - { O_NONBLOCK, "O_NONBLOCK" }, \ - { O_DSYNC, "O_DSYNC" }, \ - { O_DIRECT, "O_DIRECT" }, \ - { O_LARGEFILE, "O_LARGEFILE" }, \ - { O_DIRECTORY, "O_DIRECTORY" }, \ - { O_NOFOLLOW, "O_NOFOLLOW" }, \ - { O_NOATIME, "O_NOATIME" }, \ - { O_CLOEXEC, "O_CLOEXEC" }) - -#define __fmode_flag(x) { (__force unsigned long)FMODE_##x, #x } -#define show_fs_fmode_flags(x) \ - __print_flags(x, "|", \ - __fmode_flag(READ), \ - __fmode_flag(WRITE), \ - __fmode_flag(EXEC)) - -#ifdef CONFIG_64BIT -#define show_fs_fcntl_cmd(x) \ - __print_symbolic(x, \ - { F_DUPFD, "DUPFD" }, \ - { F_GETFD, "GETFD" }, \ - { F_SETFD, "SETFD" }, \ - { F_GETFL, "GETFL" }, \ - { F_SETFL, "SETFL" }, \ - { F_GETLK, "GETLK" }, \ - { F_SETLK, "SETLK" }, \ - { F_SETLKW, "SETLKW" }, \ - { F_SETOWN, "SETOWN" }, \ - { F_GETOWN, "GETOWN" }, \ - { F_SETSIG, "SETSIG" }, \ - { F_GETSIG, "GETSIG" }, \ - { F_SETOWN_EX, "SETOWN_EX" }, \ - { F_GETOWN_EX, "GETOWN_EX" }, \ - { F_GETOWNER_UIDS, "GETOWNER_UIDS" }, \ - { F_OFD_GETLK, "OFD_GETLK" }, \ - { F_OFD_SETLK, "OFD_SETLK" }, \ - { F_OFD_SETLKW, "OFD_SETLKW" }) -#else /* CONFIG_64BIT */ -#define show_fs_fcntl_cmd(x) \ - __print_symbolic(x, \ - { F_DUPFD, "DUPFD" }, \ - { F_GETFD, "GETFD" }, \ - { F_SETFD, "SETFD" }, \ - { F_GETFL, "GETFL" }, \ - { F_SETFL, "SETFL" }, \ - { F_GETLK, "GETLK" }, \ - { F_SETLK, "SETLK" }, \ - { F_SETLKW, "SETLKW" }, \ - { F_SETOWN, "SETOWN" }, \ - { F_GETOWN, "GETOWN" }, \ - { F_SETSIG, "SETSIG" }, \ - { F_GETSIG, "GETSIG" }, \ - { F_GETLK64, "GETLK64" }, \ - { F_SETLK64, "SETLK64" }, \ - { F_SETLKW64, "SETLKW64" }, \ - { F_SETOWN_EX, "SETOWN_EX" }, \ - { F_GETOWN_EX, "GETOWN_EX" }, \ - { F_GETOWNER_UIDS, "GETOWNER_UIDS" }, \ - { F_OFD_GETLK, "OFD_GETLK" }, \ - { F_OFD_SETLK, "OFD_SETLK" }, \ - { F_OFD_SETLKW, "OFD_SETLKW" }) -#endif /* CONFIG_64BIT */ - -#define show_fs_fcntl_lock_type(x) \ - __print_symbolic(x, \ - { F_RDLCK, "RDLCK" }, \ - { F_WRLCK, "WRLCK" }, \ - { F_UNLCK, "UNLCK" }) - -#define show_fs_lookup_flags(flags) \ - __print_flags(flags, "|", \ - { LOOKUP_FOLLOW, "FOLLOW" }, \ - { LOOKUP_DIRECTORY, "DIRECTORY" }, \ - { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \ - { LOOKUP_EMPTY, "EMPTY" }, \ - { LOOKUP_DOWN, "DOWN" }, \ - { LOOKUP_MOUNTPOINT, "MOUNTPOINT" }, \ - { LOOKUP_REVAL, "REVAL" }, \ - { LOOKUP_RCU, "RCU" }, \ - { LOOKUP_OPEN, "OPEN" }, \ - { LOOKUP_CREATE, "CREATE" }, \ - { LOOKUP_EXCL, "EXCL" }, \ - { LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \ - { LOOKUP_PARENT, "PARENT" }, \ - { LOOKUP_NO_SYMLINKS, "NO_SYMLINKS" }, \ - { LOOKUP_NO_MAGICLINKS, "NO_MAGICLINKS" }, \ - { LOOKUP_NO_XDEV, "NO_XDEV" }, \ - { LOOKUP_BENEATH, "BENEATH" }, \ - { LOOKUP_IN_ROOT, "IN_ROOT" }, \ - { LOOKUP_CACHED, "CACHED" }) diff --git a/include/trace/events/nfs.h b/include/trace/events/nfs.h deleted file mode 100644 index 09ffdbb04134..000000000000 --- a/include/trace/events/nfs.h +++ /dev/null @@ -1,375 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Display helpers for NFS protocol elements - * - * Author: Chuck Lever chuck.lever@oracle.com - * - * Copyright (c) 2020, Oracle and/or its affiliates. - */ - -#include <linux/nfs.h> -#include <linux/nfs4.h> -#include <uapi/linux/nfs.h> - -TRACE_DEFINE_ENUM(NFS_OK); -TRACE_DEFINE_ENUM(NFSERR_PERM); -TRACE_DEFINE_ENUM(NFSERR_NOENT); -TRACE_DEFINE_ENUM(NFSERR_IO); -TRACE_DEFINE_ENUM(NFSERR_NXIO); -TRACE_DEFINE_ENUM(NFSERR_EAGAIN); -TRACE_DEFINE_ENUM(NFSERR_ACCES); -TRACE_DEFINE_ENUM(NFSERR_EXIST); -TRACE_DEFINE_ENUM(NFSERR_XDEV); -TRACE_DEFINE_ENUM(NFSERR_NODEV); -TRACE_DEFINE_ENUM(NFSERR_NOTDIR); -TRACE_DEFINE_ENUM(NFSERR_ISDIR); -TRACE_DEFINE_ENUM(NFSERR_INVAL); -TRACE_DEFINE_ENUM(NFSERR_FBIG); -TRACE_DEFINE_ENUM(NFSERR_NOSPC); -TRACE_DEFINE_ENUM(NFSERR_ROFS); -TRACE_DEFINE_ENUM(NFSERR_MLINK); -TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); -TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); -TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); -TRACE_DEFINE_ENUM(NFSERR_DQUOT); -TRACE_DEFINE_ENUM(NFSERR_STALE); -TRACE_DEFINE_ENUM(NFSERR_REMOTE); -TRACE_DEFINE_ENUM(NFSERR_WFLUSH); -TRACE_DEFINE_ENUM(NFSERR_BADHANDLE); -TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC); -TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE); -TRACE_DEFINE_ENUM(NFSERR_NOTSUPP); -TRACE_DEFINE_ENUM(NFSERR_TOOSMALL); -TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT); -TRACE_DEFINE_ENUM(NFSERR_BADTYPE); -TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); - -#define show_nfs_status(x) \ - __print_symbolic(x, \ - { NFS_OK, "OK" }, \ - { NFSERR_PERM, "PERM" }, \ - { NFSERR_NOENT, "NOENT" }, \ - { NFSERR_IO, "IO" }, \ - { NFSERR_NXIO, "NXIO" }, \ - { ECHILD, "CHILD" }, \ - { NFSERR_EAGAIN, "AGAIN" }, \ - { NFSERR_ACCES, "ACCES" }, \ - { NFSERR_EXIST, "EXIST" }, \ - { NFSERR_XDEV, "XDEV" }, \ - { NFSERR_NODEV, "NODEV" }, \ - { NFSERR_NOTDIR, "NOTDIR" }, \ - { NFSERR_ISDIR, "ISDIR" }, \ - { NFSERR_INVAL, "INVAL" }, \ - { NFSERR_FBIG, "FBIG" }, \ - { NFSERR_NOSPC, "NOSPC" }, \ - { NFSERR_ROFS, "ROFS" }, \ - { NFSERR_MLINK, "MLINK" }, \ - { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ - { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ - { NFSERR_DQUOT, "DQUOT" }, \ - { NFSERR_STALE, "STALE" }, \ - { NFSERR_REMOTE, "REMOTE" }, \ - { NFSERR_WFLUSH, "WFLUSH" }, \ - { NFSERR_BADHANDLE, "BADHANDLE" }, \ - { NFSERR_NOT_SYNC, "NOTSYNC" }, \ - { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \ - { NFSERR_NOTSUPP, "NOTSUPP" }, \ - { NFSERR_TOOSMALL, "TOOSMALL" }, \ - { NFSERR_SERVERFAULT, "REMOTEIO" }, \ - { NFSERR_BADTYPE, "BADTYPE" }, \ - { NFSERR_JUKEBOX, "JUKEBOX" }) - -TRACE_DEFINE_ENUM(NFS_UNSTABLE); -TRACE_DEFINE_ENUM(NFS_DATA_SYNC); -TRACE_DEFINE_ENUM(NFS_FILE_SYNC); - -#define show_nfs_stable_how(x) \ - __print_symbolic(x, \ - { NFS_UNSTABLE, "UNSTABLE" }, \ - { NFS_DATA_SYNC, "DATA_SYNC" }, \ - { NFS_FILE_SYNC, "FILE_SYNC" }) - -TRACE_DEFINE_ENUM(NFS4_OK); -TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); -TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); -TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); -TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); -TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); -TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); -TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); -TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); -TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); -TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); -TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); -TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); -TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); -TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); -TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); -TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); -TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); -TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); -TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); -TRACE_DEFINE_ENUM(NFS4ERR_DELAY); -TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); -TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); -TRACE_DEFINE_ENUM(NFS4ERR_DENIED); -TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); -TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); -TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_EXIST); -TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); -TRACE_DEFINE_ENUM(NFS4ERR_FBIG); -TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); -TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); -TRACE_DEFINE_ENUM(NFS4ERR_GRACE); -TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_INVAL); -TRACE_DEFINE_ENUM(NFS4ERR_IO); -TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); -TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); -TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); -TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); -TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); -TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); -TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); -TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); -TRACE_DEFINE_ENUM(NFS4ERR_MLINK); -TRACE_DEFINE_ENUM(NFS4ERR_MOVED); -TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); -TRACE_DEFINE_ENUM(NFS4ERR_NOENT); -TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); -TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); -TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); -TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); -TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); -TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); -TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); -TRACE_DEFINE_ENUM(NFS4ERR_NXIO); -TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); -TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); -TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); -TRACE_DEFINE_ENUM(NFS4ERR_PERM); -TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); -TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); -TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); -TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); -TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); -TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); -TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); -TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); -TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); -TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_ROFS); -TRACE_DEFINE_ENUM(NFS4ERR_SAME); -TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); -TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); -TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); -TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); -TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); -TRACE_DEFINE_ENUM(NFS4ERR_STALE); -TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); -TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); -TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); -TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); -TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); -TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); -TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); -TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); -TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); -TRACE_DEFINE_ENUM(NFS4ERR_XDEV); - -TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); -TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); - -#define show_nfs4_status(x) \ - __print_symbolic(x, \ - { NFS4_OK, "OK" }, \ - { EPERM, "EPERM" }, \ - { ENOENT, "ENOENT" }, \ - { EIO, "EIO" }, \ - { ENXIO, "ENXIO" }, \ - { EACCES, "EACCES" }, \ - { EEXIST, "EEXIST" }, \ - { EXDEV, "EXDEV" }, \ - { ENOTDIR, "ENOTDIR" }, \ - { EISDIR, "EISDIR" }, \ - { EFBIG, "EFBIG" }, \ - { ENOSPC, "ENOSPC" }, \ - { EROFS, "EROFS" }, \ - { EMLINK, "EMLINK" }, \ - { ENAMETOOLONG, "ENAMETOOLONG" }, \ - { ENOTEMPTY, "ENOTEMPTY" }, \ - { EDQUOT, "EDQUOT" }, \ - { ESTALE, "ESTALE" }, \ - { EBADHANDLE, "EBADHANDLE" }, \ - { EBADCOOKIE, "EBADCOOKIE" }, \ - { ENOTSUPP, "ENOTSUPP" }, \ - { ETOOSMALL, "ETOOSMALL" }, \ - { EREMOTEIO, "EREMOTEIO" }, \ - { EBADTYPE, "EBADTYPE" }, \ - { EAGAIN, "EAGAIN" }, \ - { ELOOP, "ELOOP" }, \ - { EOPNOTSUPP, "EOPNOTSUPP" }, \ - { EDEADLK, "EDEADLK" }, \ - { ENOMEM, "ENOMEM" }, \ - { EKEYEXPIRED, "EKEYEXPIRED" }, \ - { ETIMEDOUT, "ETIMEDOUT" }, \ - { ERESTARTSYS, "ERESTARTSYS" }, \ - { ECONNREFUSED, "ECONNREFUSED" }, \ - { ECONNRESET, "ECONNRESET" }, \ - { ENETUNREACH, "ENETUNREACH" }, \ - { EHOSTUNREACH, "EHOSTUNREACH" }, \ - { EHOSTDOWN, "EHOSTDOWN" }, \ - { EPIPE, "EPIPE" }, \ - { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ - { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ - { NFS4ERR_ACCESS, "ACCESS" }, \ - { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ - { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ - { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ - { NFS4ERR_BADCHAR, "BADCHAR" }, \ - { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ - { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ - { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ - { NFS4ERR_BADLABEL, "BADLABEL" }, \ - { NFS4ERR_BADNAME, "BADNAME" }, \ - { NFS4ERR_BADOWNER, "BADOWNER" }, \ - { NFS4ERR_BADSESSION, "BADSESSION" }, \ - { NFS4ERR_BADSLOT, "BADSLOT" }, \ - { NFS4ERR_BADTYPE, "BADTYPE" }, \ - { NFS4ERR_BADXDR, "BADXDR" }, \ - { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ - { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ - { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ - { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ - { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ - { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ - { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ - { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ - { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ - { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, "CONN_NOT_BOUND_TO_SESSION" }, \ - { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ - { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ - { NFS4ERR_DELAY, "DELAY" }, \ - { NFS4ERR_DELEG_ALREADY_WANTED, "DELEG_ALREADY_WANTED" }, \ - { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ - { NFS4ERR_DENIED, "DENIED" }, \ - { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ - { NFS4ERR_DQUOT, "DQUOT" }, \ - { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ - { NFS4ERR_EXIST, "EXIST" }, \ - { NFS4ERR_EXPIRED, "EXPIRED" }, \ - { NFS4ERR_FBIG, "FBIG" }, \ - { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ - { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ - { NFS4ERR_GRACE, "GRACE" }, \ - { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ - { NFS4ERR_INVAL, "INVAL" }, \ - { NFS4ERR_IO, "IO" }, \ - { NFS4ERR_ISDIR, "ISDIR" }, \ - { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ - { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ - { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ - { NFS4ERR_LOCKED, "LOCKED" }, \ - { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ - { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ - { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ - { NFS4ERR_MLINK, "MLINK" }, \ - { NFS4ERR_MOVED, "MOVED" }, \ - { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { NFS4ERR_NOENT, "NOENT" }, \ - { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ - { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ - { NFS4ERR_NOSPC, "NOSPC" }, \ - { NFS4ERR_NOTDIR, "NOTDIR" }, \ - { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ - { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ - { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ - { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ - { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ - { NFS4ERR_NXIO, "NXIO" }, \ - { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ - { NFS4ERR_OPENMODE, "OPENMODE" }, \ - { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ - { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ - { NFS4ERR_PERM, "PERM" }, \ - { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ - { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ - { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ - { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ - { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ - { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ - { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ - { NFS4ERR_REP_TOO_BIG_TO_CACHE, "REP_TOO_BIG_TO_CACHE" }, \ - { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ - { NFS4ERR_RESOURCE, "RESOURCE" }, \ - { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ - { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ - { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ - { NFS4ERR_ROFS, "ROFS" }, \ - { NFS4ERR_SAME, "SAME" }, \ - { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ - { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ - { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ - { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ - { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ - { NFS4ERR_STALE, "STALE" }, \ - { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ - { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ - { NFS4ERR_SYMLINK, "SYMLINK" }, \ - { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ - { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ - { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ - { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ - { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ - { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ - { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ - { NFS4ERR_XDEV, "XDEV" }, \ - /* ***** Internal to Linux NFS client ***** */ \ - { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ - { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) - -#define show_nfs4_verifier(x) \ - __print_hex_str(x, NFS4_VERIFIER_SIZE) - -TRACE_DEFINE_ENUM(IOMODE_READ); -TRACE_DEFINE_ENUM(IOMODE_RW); -TRACE_DEFINE_ENUM(IOMODE_ANY); - -#define show_pnfs_layout_iomode(x) \ - __print_symbolic(x, \ - { IOMODE_READ, "READ" }, \ - { IOMODE_RW, "RW" }, \ - { IOMODE_ANY, "ANY" }) - -#define show_nfs4_seq4_status(x) \ - __print_flags(x, "|", \ - { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, "CB_GSS_CONTEXTS_EXPIRING" }, \ - { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, "CB_GSS_CONTEXTS_EXPIRED" }, \ - { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, "EXPIRED_ALL_STATE_REVOKED" }, \ - { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, "EXPIRED_SOME_STATE_REVOKED" }, \ - { SEQ4_STATUS_ADMIN_STATE_REVOKED, "ADMIN_STATE_REVOKED" }, \ - { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, "RECALLABLE_STATE_REVOKED" }, \ - { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ - { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, "RESTART_RECLAIM_NEEDED" }, \ - { SEQ4_STATUS_CB_PATH_DOWN_SESSION, "CB_PATH_DOWN_SESSION" }, \ - { SEQ4_STATUS_BACKCHANNEL_FAULT, "BACKCHANNEL_FAULT" }) diff --git a/include/trace/events/rdma.h b/include/trace/events/rdma.h deleted file mode 100644 index 81bb454fc288..000000000000 --- a/include/trace/events/rdma.h +++ /dev/null @@ -1,168 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (c) 2017 Oracle. All rights reserved. - */ - -/* - * enum ib_event_type, from include/rdma/ib_verbs.h - */ -#define IB_EVENT_LIST \ - ib_event(CQ_ERR) \ - ib_event(QP_FATAL) \ - ib_event(QP_REQ_ERR) \ - ib_event(QP_ACCESS_ERR) \ - ib_event(COMM_EST) \ - ib_event(SQ_DRAINED) \ - ib_event(PATH_MIG) \ - ib_event(PATH_MIG_ERR) \ - ib_event(DEVICE_FATAL) \ - ib_event(PORT_ACTIVE) \ - ib_event(PORT_ERR) \ - ib_event(LID_CHANGE) \ - ib_event(PKEY_CHANGE) \ - ib_event(SM_CHANGE) \ - ib_event(SRQ_ERR) \ - ib_event(SRQ_LIMIT_REACHED) \ - ib_event(QP_LAST_WQE_REACHED) \ - ib_event(CLIENT_REREGISTER) \ - ib_event(GID_CHANGE) \ - ib_event_end(WQ_FATAL) - -#undef ib_event -#undef ib_event_end - -#define ib_event(x) TRACE_DEFINE_ENUM(IB_EVENT_##x); -#define ib_event_end(x) TRACE_DEFINE_ENUM(IB_EVENT_##x); - -IB_EVENT_LIST - -#undef ib_event -#undef ib_event_end - -#define ib_event(x) { IB_EVENT_##x, #x }, -#define ib_event_end(x) { IB_EVENT_##x, #x } - -#define rdma_show_ib_event(x) \ - __print_symbolic(x, IB_EVENT_LIST) - -/* - * enum ib_wc_status type, from include/rdma/ib_verbs.h - */ -#define IB_WC_STATUS_LIST \ - ib_wc_status(SUCCESS) \ - ib_wc_status(LOC_LEN_ERR) \ - ib_wc_status(LOC_QP_OP_ERR) \ - ib_wc_status(LOC_EEC_OP_ERR) \ - ib_wc_status(LOC_PROT_ERR) \ - ib_wc_status(WR_FLUSH_ERR) \ - ib_wc_status(MW_BIND_ERR) \ - ib_wc_status(BAD_RESP_ERR) \ - ib_wc_status(LOC_ACCESS_ERR) \ - ib_wc_status(REM_INV_REQ_ERR) \ - ib_wc_status(REM_ACCESS_ERR) \ - ib_wc_status(REM_OP_ERR) \ - ib_wc_status(RETRY_EXC_ERR) \ - ib_wc_status(RNR_RETRY_EXC_ERR) \ - ib_wc_status(LOC_RDD_VIOL_ERR) \ - ib_wc_status(REM_INV_RD_REQ_ERR) \ - ib_wc_status(REM_ABORT_ERR) \ - ib_wc_status(INV_EECN_ERR) \ - ib_wc_status(INV_EEC_STATE_ERR) \ - ib_wc_status(FATAL_ERR) \ - ib_wc_status(RESP_TIMEOUT_ERR) \ - ib_wc_status_end(GENERAL_ERR) - -#undef ib_wc_status -#undef ib_wc_status_end - -#define ib_wc_status(x) TRACE_DEFINE_ENUM(IB_WC_##x); -#define ib_wc_status_end(x) TRACE_DEFINE_ENUM(IB_WC_##x); - -IB_WC_STATUS_LIST - -#undef ib_wc_status -#undef ib_wc_status_end - -#define ib_wc_status(x) { IB_WC_##x, #x }, -#define ib_wc_status_end(x) { IB_WC_##x, #x } - -#define rdma_show_wc_status(x) \ - __print_symbolic(x, IB_WC_STATUS_LIST) - -/* - * enum ib_cm_event_type, from include/rdma/ib_cm.h - */ -#define IB_CM_EVENT_LIST \ - ib_cm_event(REQ_ERROR) \ - ib_cm_event(REQ_RECEIVED) \ - ib_cm_event(REP_ERROR) \ - ib_cm_event(REP_RECEIVED) \ - ib_cm_event(RTU_RECEIVED) \ - ib_cm_event(USER_ESTABLISHED) \ - ib_cm_event(DREQ_ERROR) \ - ib_cm_event(DREQ_RECEIVED) \ - ib_cm_event(DREP_RECEIVED) \ - ib_cm_event(TIMEWAIT_EXIT) \ - ib_cm_event(MRA_RECEIVED) \ - ib_cm_event(REJ_RECEIVED) \ - ib_cm_event(LAP_ERROR) \ - ib_cm_event(LAP_RECEIVED) \ - ib_cm_event(APR_RECEIVED) \ - ib_cm_event(SIDR_REQ_ERROR) \ - ib_cm_event(SIDR_REQ_RECEIVED) \ - ib_cm_event_end(SIDR_REP_RECEIVED) - -#undef ib_cm_event -#undef ib_cm_event_end - -#define ib_cm_event(x) TRACE_DEFINE_ENUM(IB_CM_##x); -#define ib_cm_event_end(x) TRACE_DEFINE_ENUM(IB_CM_##x); - -IB_CM_EVENT_LIST - -#undef ib_cm_event -#undef ib_cm_event_end - -#define ib_cm_event(x) { IB_CM_##x, #x }, -#define ib_cm_event_end(x) { IB_CM_##x, #x } - -#define rdma_show_ib_cm_event(x) \ - __print_symbolic(x, IB_CM_EVENT_LIST) - -/* - * enum rdma_cm_event_type, from include/rdma/rdma_cm.h - */ -#define RDMA_CM_EVENT_LIST \ - rdma_cm_event(ADDR_RESOLVED) \ - rdma_cm_event(ADDR_ERROR) \ - rdma_cm_event(ROUTE_RESOLVED) \ - rdma_cm_event(ROUTE_ERROR) \ - rdma_cm_event(CONNECT_REQUEST) \ - rdma_cm_event(CONNECT_RESPONSE) \ - rdma_cm_event(CONNECT_ERROR) \ - rdma_cm_event(UNREACHABLE) \ - rdma_cm_event(REJECTED) \ - rdma_cm_event(ESTABLISHED) \ - rdma_cm_event(DISCONNECTED) \ - rdma_cm_event(DEVICE_REMOVAL) \ - rdma_cm_event(MULTICAST_JOIN) \ - rdma_cm_event(MULTICAST_ERROR) \ - rdma_cm_event(ADDR_CHANGE) \ - rdma_cm_event_end(TIMEWAIT_EXIT) - -#undef rdma_cm_event -#undef rdma_cm_event_end - -#define rdma_cm_event(x) TRACE_DEFINE_ENUM(RDMA_CM_EVENT_##x); -#define rdma_cm_event_end(x) TRACE_DEFINE_ENUM(RDMA_CM_EVENT_##x); - -RDMA_CM_EVENT_LIST - -#undef rdma_cm_event -#undef rdma_cm_event_end - -#define rdma_cm_event(x) { RDMA_CM_EVENT_##x, #x }, -#define rdma_cm_event_end(x) { RDMA_CM_EVENT_##x, #x } - -#define rdma_show_cm_event(x) \ - __print_symbolic(x, RDMA_CM_EVENT_LIST) diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index c9048f3e471b..3f121eed369e 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -13,7 +13,7 @@

#include <linux/tracepoint.h>

-#include <trace/events/sunrpc_base.h> +#include <trace/misc/sunrpc.h>

/** ** GSS-API related trace events diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index fcd3b3f1020a..8f461e04e5f0 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -15,8 +15,8 @@ #include <linux/tracepoint.h> #include <rdma/ib_cm.h>

-#include <trace/events/rdma.h> -#include <trace/events/sunrpc_base.h> +#include <trace/misc/rdma.h> +#include <trace/misc/sunrpc.h>

/** ** Event classes diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index f48f2ab9d238..ffe2679a13ce 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -14,7 +14,7 @@ #include <linux/net.h> #include <linux/tracepoint.h>

-#include <trace/events/sunrpc_base.h> +#include <trace/misc/sunrpc.h>

TRACE_DEFINE_ENUM(SOCK_STREAM); TRACE_DEFINE_ENUM(SOCK_DGRAM); diff --git a/include/trace/events/sunrpc_base.h b/include/trace/events/sunrpc_base.h deleted file mode 100644 index 588557d07ea8..000000000000 --- a/include/trace/events/sunrpc_base.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (c) 2021 Oracle and/or its affiliates. - * - * Common types and format specifiers for sunrpc. - */ - -#if !defined(_TRACE_SUNRPC_BASE_H) -#define _TRACE_SUNRPC_BASE_H - -#include <linux/tracepoint.h> - -#define SUNRPC_TRACE_PID_SPECIFIER "%08x" -#define SUNRPC_TRACE_CLID_SPECIFIER "%08x" -#define SUNRPC_TRACE_TASK_SPECIFIER \ - "task:" SUNRPC_TRACE_PID_SPECIFIER "@" SUNRPC_TRACE_CLID_SPECIFIER - -#endif /* _TRACE_SUNRPC_BASE_H */ diff --git a/include/trace/misc/fs.h b/include/trace/misc/fs.h new file mode 100644 index 000000000000..738b97f22f36 --- /dev/null +++ b/include/trace/misc/fs.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Display helpers for generic filesystem items + * + * Author: Chuck Lever chuck.lever@oracle.com + * + * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#include <linux/fs.h> + +#define show_fs_dirent_type(x) \ + __print_symbolic(x, \ + { DT_UNKNOWN, "UNKNOWN" }, \ + { DT_FIFO, "FIFO" }, \ + { DT_CHR, "CHR" }, \ + { DT_DIR, "DIR" }, \ + { DT_BLK, "BLK" }, \ + { DT_REG, "REG" }, \ + { DT_LNK, "LNK" }, \ + { DT_SOCK, "SOCK" }, \ + { DT_WHT, "WHT" }) + +#define show_fs_fcntl_open_flags(x) \ + __print_flags(x, "|", \ + { O_WRONLY, "O_WRONLY" }, \ + { O_RDWR, "O_RDWR" }, \ + { O_CREAT, "O_CREAT" }, \ + { O_EXCL, "O_EXCL" }, \ + { O_NOCTTY, "O_NOCTTY" }, \ + { O_TRUNC, "O_TRUNC" }, \ + { O_APPEND, "O_APPEND" }, \ + { O_NONBLOCK, "O_NONBLOCK" }, \ + { O_DSYNC, "O_DSYNC" }, \ + { O_DIRECT, "O_DIRECT" }, \ + { O_LARGEFILE, "O_LARGEFILE" }, \ + { O_DIRECTORY, "O_DIRECTORY" }, \ + { O_NOFOLLOW, "O_NOFOLLOW" }, \ + { O_NOATIME, "O_NOATIME" }, \ + { O_CLOEXEC, "O_CLOEXEC" }) + +#define __fmode_flag(x) { (__force unsigned long)FMODE_##x, #x } +#define show_fs_fmode_flags(x) \ + __print_flags(x, "|", \ + __fmode_flag(READ), \ + __fmode_flag(WRITE), \ + __fmode_flag(EXEC)) + +#ifdef CONFIG_64BIT +#define show_fs_fcntl_cmd(x) \ + __print_symbolic(x, \ + { F_DUPFD, "DUPFD" }, \ + { F_GETFD, "GETFD" }, \ + { F_SETFD, "SETFD" }, \ + { F_GETFL, "GETFL" }, \ + { F_SETFL, "SETFL" }, \ + { F_GETLK, "GETLK" }, \ + { F_SETLK, "SETLK" }, \ + { F_SETLKW, "SETLKW" }, \ + { F_SETOWN, "SETOWN" }, \ + { F_GETOWN, "GETOWN" }, \ + { F_SETSIG, "SETSIG" }, \ + { F_GETSIG, "GETSIG" }, \ + { F_SETOWN_EX, "SETOWN_EX" }, \ + { F_GETOWN_EX, "GETOWN_EX" }, \ + { F_GETOWNER_UIDS, "GETOWNER_UIDS" }, \ + { F_OFD_GETLK, "OFD_GETLK" }, \ + { F_OFD_SETLK, "OFD_SETLK" }, \ + { F_OFD_SETLKW, "OFD_SETLKW" }) +#else /* CONFIG_64BIT */ +#define show_fs_fcntl_cmd(x) \ + __print_symbolic(x, \ + { F_DUPFD, "DUPFD" }, \ + { F_GETFD, "GETFD" }, \ + { F_SETFD, "SETFD" }, \ + { F_GETFL, "GETFL" }, \ + { F_SETFL, "SETFL" }, \ + { F_GETLK, "GETLK" }, \ + { F_SETLK, "SETLK" }, \ + { F_SETLKW, "SETLKW" }, \ + { F_SETOWN, "SETOWN" }, \ + { F_GETOWN, "GETOWN" }, \ + { F_SETSIG, "SETSIG" }, \ + { F_GETSIG, "GETSIG" }, \ + { F_GETLK64, "GETLK64" }, \ + { F_SETLK64, "SETLK64" }, \ + { F_SETLKW64, "SETLKW64" }, \ + { F_SETOWN_EX, "SETOWN_EX" }, \ + { F_GETOWN_EX, "GETOWN_EX" }, \ + { F_GETOWNER_UIDS, "GETOWNER_UIDS" }, \ + { F_OFD_GETLK, "OFD_GETLK" }, \ + { F_OFD_SETLK, "OFD_SETLK" }, \ + { F_OFD_SETLKW, "OFD_SETLKW" }) +#endif /* CONFIG_64BIT */ + +#define show_fs_fcntl_lock_type(x) \ + __print_symbolic(x, \ + { F_RDLCK, "RDLCK" }, \ + { F_WRLCK, "WRLCK" }, \ + { F_UNLCK, "UNLCK" }) + +#define show_fs_lookup_flags(flags) \ + __print_flags(flags, "|", \ + { LOOKUP_FOLLOW, "FOLLOW" }, \ + { LOOKUP_DIRECTORY, "DIRECTORY" }, \ + { LOOKUP_AUTOMOUNT, "AUTOMOUNT" }, \ + { LOOKUP_EMPTY, "EMPTY" }, \ + { LOOKUP_DOWN, "DOWN" }, \ + { LOOKUP_MOUNTPOINT, "MOUNTPOINT" }, \ + { LOOKUP_REVAL, "REVAL" }, \ + { LOOKUP_RCU, "RCU" }, \ + { LOOKUP_OPEN, "OPEN" }, \ + { LOOKUP_CREATE, "CREATE" }, \ + { LOOKUP_EXCL, "EXCL" }, \ + { LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \ + { LOOKUP_PARENT, "PARENT" }, \ + { LOOKUP_NO_SYMLINKS, "NO_SYMLINKS" }, \ + { LOOKUP_NO_MAGICLINKS, "NO_MAGICLINKS" }, \ + { LOOKUP_NO_XDEV, "NO_XDEV" }, \ + { LOOKUP_BENEATH, "BENEATH" }, \ + { LOOKUP_IN_ROOT, "IN_ROOT" }, \ + { LOOKUP_CACHED, "CACHED" }) diff --git a/include/trace/misc/nfs.h b/include/trace/misc/nfs.h new file mode 100644 index 000000000000..0d9d48dca38a --- /dev/null +++ b/include/trace/misc/nfs.h @@ -0,0 +1,387 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Display helpers for NFS protocol elements + * + * Author: Chuck Lever chuck.lever@oracle.com + * + * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#include <linux/nfs.h> +#include <linux/nfs4.h> +#include <uapi/linux/nfs.h> + +TRACE_DEFINE_ENUM(NFS_OK); +TRACE_DEFINE_ENUM(NFSERR_PERM); +TRACE_DEFINE_ENUM(NFSERR_NOENT); +TRACE_DEFINE_ENUM(NFSERR_IO); +TRACE_DEFINE_ENUM(NFSERR_NXIO); +TRACE_DEFINE_ENUM(NFSERR_EAGAIN); +TRACE_DEFINE_ENUM(NFSERR_ACCES); +TRACE_DEFINE_ENUM(NFSERR_EXIST); +TRACE_DEFINE_ENUM(NFSERR_XDEV); +TRACE_DEFINE_ENUM(NFSERR_NODEV); +TRACE_DEFINE_ENUM(NFSERR_NOTDIR); +TRACE_DEFINE_ENUM(NFSERR_ISDIR); +TRACE_DEFINE_ENUM(NFSERR_INVAL); +TRACE_DEFINE_ENUM(NFSERR_FBIG); +TRACE_DEFINE_ENUM(NFSERR_NOSPC); +TRACE_DEFINE_ENUM(NFSERR_ROFS); +TRACE_DEFINE_ENUM(NFSERR_MLINK); +TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); +TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFSERR_DQUOT); +TRACE_DEFINE_ENUM(NFSERR_STALE); +TRACE_DEFINE_ENUM(NFSERR_REMOTE); +TRACE_DEFINE_ENUM(NFSERR_WFLUSH); +TRACE_DEFINE_ENUM(NFSERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC); +TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFSERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFSERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFSERR_BADTYPE); +TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); + +#define show_nfs_status(x) \ + __print_symbolic(x, \ + { NFS_OK, "OK" }, \ + { NFSERR_PERM, "PERM" }, \ + { NFSERR_NOENT, "NOENT" }, \ + { NFSERR_IO, "IO" }, \ + { NFSERR_NXIO, "NXIO" }, \ + { ECHILD, "CHILD" }, \ + { NFSERR_EAGAIN, "AGAIN" }, \ + { NFSERR_ACCES, "ACCES" }, \ + { NFSERR_EXIST, "EXIST" }, \ + { NFSERR_XDEV, "XDEV" }, \ + { NFSERR_NODEV, "NODEV" }, \ + { NFSERR_NOTDIR, "NOTDIR" }, \ + { NFSERR_ISDIR, "ISDIR" }, \ + { NFSERR_INVAL, "INVAL" }, \ + { NFSERR_FBIG, "FBIG" }, \ + { NFSERR_NOSPC, "NOSPC" }, \ + { NFSERR_ROFS, "ROFS" }, \ + { NFSERR_MLINK, "MLINK" }, \ + { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ + { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFSERR_DQUOT, "DQUOT" }, \ + { NFSERR_STALE, "STALE" }, \ + { NFSERR_REMOTE, "REMOTE" }, \ + { NFSERR_WFLUSH, "WFLUSH" }, \ + { NFSERR_BADHANDLE, "BADHANDLE" }, \ + { NFSERR_NOT_SYNC, "NOTSYNC" }, \ + { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \ + { NFSERR_NOTSUPP, "NOTSUPP" }, \ + { NFSERR_TOOSMALL, "TOOSMALL" }, \ + { NFSERR_SERVERFAULT, "REMOTEIO" }, \ + { NFSERR_BADTYPE, "BADTYPE" }, \ + { NFSERR_JUKEBOX, "JUKEBOX" }) + +TRACE_DEFINE_ENUM(NFS_UNSTABLE); +TRACE_DEFINE_ENUM(NFS_DATA_SYNC); +TRACE_DEFINE_ENUM(NFS_FILE_SYNC); + +#define show_nfs_stable_how(x) \ + __print_symbolic(x, \ + { NFS_UNSTABLE, "UNSTABLE" }, \ + { NFS_DATA_SYNC, "DATA_SYNC" }, \ + { NFS_FILE_SYNC, "FILE_SYNC" }) + +TRACE_DEFINE_ENUM(NFS4_OK); +TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); +TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); +TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); +TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); +TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); +TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); +TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); +TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); +TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); +TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); +TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DELAY); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); +TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); +TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_EXIST); +TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FBIG); +TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); +TRACE_DEFINE_ENUM(NFS4ERR_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_INVAL); +TRACE_DEFINE_ENUM(NFS4ERR_IO); +TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); +TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); +TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); +TRACE_DEFINE_ENUM(NFS4ERR_MLINK); +TRACE_DEFINE_ENUM(NFS4ERR_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFS4ERR_NOENT); +TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); +TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); +TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_NXIO); +TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); +TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); +TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_PERM); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); +TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); +TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); +TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); +TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_ROFS); +TRACE_DEFINE_ENUM(NFS4ERR_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); +TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFS4ERR_STALE); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); +TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); +TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); +TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); +TRACE_DEFINE_ENUM(NFS4ERR_XDEV); + +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); + +#define show_nfs4_status(x) \ + __print_symbolic(x, \ + { NFS4_OK, "OK" }, \ + { EPERM, "EPERM" }, \ + { ENOENT, "ENOENT" }, \ + { EIO, "EIO" }, \ + { ENXIO, "ENXIO" }, \ + { EACCES, "EACCES" }, \ + { EEXIST, "EEXIST" }, \ + { EXDEV, "EXDEV" }, \ + { ENOTDIR, "ENOTDIR" }, \ + { EISDIR, "EISDIR" }, \ + { EFBIG, "EFBIG" }, \ + { ENOSPC, "ENOSPC" }, \ + { EROFS, "EROFS" }, \ + { EMLINK, "EMLINK" }, \ + { ENAMETOOLONG, "ENAMETOOLONG" }, \ + { ENOTEMPTY, "ENOTEMPTY" }, \ + { EDQUOT, "EDQUOT" }, \ + { ESTALE, "ESTALE" }, \ + { EBADHANDLE, "EBADHANDLE" }, \ + { EBADCOOKIE, "EBADCOOKIE" }, \ + { ENOTSUPP, "ENOTSUPP" }, \ + { ETOOSMALL, "ETOOSMALL" }, \ + { EREMOTEIO, "EREMOTEIO" }, \ + { EBADTYPE, "EBADTYPE" }, \ + { EAGAIN, "EAGAIN" }, \ + { ELOOP, "ELOOP" }, \ + { EOPNOTSUPP, "EOPNOTSUPP" }, \ + { EDEADLK, "EDEADLK" }, \ + { ENOMEM, "ENOMEM" }, \ + { EKEYEXPIRED, "EKEYEXPIRED" }, \ + { ETIMEDOUT, "ETIMEDOUT" }, \ + { ERESTARTSYS, "ERESTARTSYS" }, \ + { ECONNREFUSED, "ECONNREFUSED" }, \ + { ECONNRESET, "ECONNRESET" }, \ + { ENETUNREACH, "ENETUNREACH" }, \ + { EHOSTUNREACH, "EHOSTUNREACH" }, \ + { EHOSTDOWN, "EHOSTDOWN" }, \ + { EPIPE, "EPIPE" }, \ + { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ + { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ + { NFS4ERR_ACCESS, "ACCESS" }, \ + { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ + { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ + { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ + { NFS4ERR_BADCHAR, "BADCHAR" }, \ + { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ + { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ + { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ + { NFS4ERR_BADLABEL, "BADLABEL" }, \ + { NFS4ERR_BADNAME, "BADNAME" }, \ + { NFS4ERR_BADOWNER, "BADOWNER" }, \ + { NFS4ERR_BADSESSION, "BADSESSION" }, \ + { NFS4ERR_BADSLOT, "BADSLOT" }, \ + { NFS4ERR_BADTYPE, "BADTYPE" }, \ + { NFS4ERR_BADXDR, "BADXDR" }, \ + { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ + { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ + { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ + { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ + { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ + { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ + { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ + { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ + { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ + { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, "CONN_NOT_BOUND_TO_SESSION" }, \ + { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ + { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ + { NFS4ERR_DELAY, "DELAY" }, \ + { NFS4ERR_DELEG_ALREADY_WANTED, "DELEG_ALREADY_WANTED" }, \ + { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ + { NFS4ERR_DENIED, "DENIED" }, \ + { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ + { NFS4ERR_DQUOT, "DQUOT" }, \ + { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ + { NFS4ERR_EXIST, "EXIST" }, \ + { NFS4ERR_EXPIRED, "EXPIRED" }, \ + { NFS4ERR_FBIG, "FBIG" }, \ + { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ + { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ + { NFS4ERR_GRACE, "GRACE" }, \ + { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ + { NFS4ERR_INVAL, "INVAL" }, \ + { NFS4ERR_IO, "IO" }, \ + { NFS4ERR_ISDIR, "ISDIR" }, \ + { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ + { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ + { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ + { NFS4ERR_LOCKED, "LOCKED" }, \ + { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ + { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ + { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ + { NFS4ERR_MLINK, "MLINK" }, \ + { NFS4ERR_MOVED, "MOVED" }, \ + { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFS4ERR_NOENT, "NOENT" }, \ + { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ + { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ + { NFS4ERR_NOSPC, "NOSPC" }, \ + { NFS4ERR_NOTDIR, "NOTDIR" }, \ + { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ + { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ + { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ + { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ + { NFS4ERR_NXIO, "NXIO" }, \ + { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ + { NFS4ERR_OPENMODE, "OPENMODE" }, \ + { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ + { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ + { NFS4ERR_PERM, "PERM" }, \ + { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ + { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ + { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ + { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ + { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ + { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ + { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ + { NFS4ERR_REP_TOO_BIG_TO_CACHE, "REP_TOO_BIG_TO_CACHE" }, \ + { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ + { NFS4ERR_RESOURCE, "RESOURCE" }, \ + { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ + { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ + { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ + { NFS4ERR_ROFS, "ROFS" }, \ + { NFS4ERR_SAME, "SAME" }, \ + { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ + { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ + { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ + { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ + { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ + { NFS4ERR_STALE, "STALE" }, \ + { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ + { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ + { NFS4ERR_SYMLINK, "SYMLINK" }, \ + { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ + { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ + { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ + { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ + { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ + { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ + { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ + { NFS4ERR_XDEV, "XDEV" }, \ + /* ***** Internal to Linux NFS client ***** */ \ + { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ + { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) + +#define show_nfs4_verifier(x) \ + __print_hex_str(x, NFS4_VERIFIER_SIZE) + +TRACE_DEFINE_ENUM(IOMODE_READ); +TRACE_DEFINE_ENUM(IOMODE_RW); +TRACE_DEFINE_ENUM(IOMODE_ANY); + +#define show_pnfs_layout_iomode(x) \ + __print_symbolic(x, \ + { IOMODE_READ, "READ" }, \ + { IOMODE_RW, "RW" }, \ + { IOMODE_ANY, "ANY" }) + +#define show_rca_mask(x) \ + __print_flags(x, "|", \ + { BIT(RCA4_TYPE_MASK_RDATA_DLG), "RDATA_DLG" }, \ + { BIT(RCA4_TYPE_MASK_WDATA_DLG), "WDATA_DLG" }, \ + { BIT(RCA4_TYPE_MASK_DIR_DLG), "DIR_DLG" }, \ + { BIT(RCA4_TYPE_MASK_FILE_LAYOUT), "FILE_LAYOUT" }, \ + { BIT(RCA4_TYPE_MASK_BLK_LAYOUT), "BLK_LAYOUT" }, \ + { BIT(RCA4_TYPE_MASK_OBJ_LAYOUT_MIN), "OBJ_LAYOUT_MIN" }, \ + { BIT(RCA4_TYPE_MASK_OBJ_LAYOUT_MAX), "OBJ_LAYOUT_MAX" }, \ + { BIT(RCA4_TYPE_MASK_OTHER_LAYOUT_MIN), "OTHER_LAYOUT_MIN" }, \ + { BIT(RCA4_TYPE_MASK_OTHER_LAYOUT_MAX), "OTHER_LAYOUT_MAX" }) + +#define show_nfs4_seq4_status(x) \ + __print_flags(x, "|", \ + { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, "CB_GSS_CONTEXTS_EXPIRING" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, "CB_GSS_CONTEXTS_EXPIRED" }, \ + { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, "EXPIRED_ALL_STATE_REVOKED" }, \ + { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, "EXPIRED_SOME_STATE_REVOKED" }, \ + { SEQ4_STATUS_ADMIN_STATE_REVOKED, "ADMIN_STATE_REVOKED" }, \ + { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, "RECALLABLE_STATE_REVOKED" }, \ + { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ + { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, "RESTART_RECLAIM_NEEDED" }, \ + { SEQ4_STATUS_CB_PATH_DOWN_SESSION, "CB_PATH_DOWN_SESSION" }, \ + { SEQ4_STATUS_BACKCHANNEL_FAULT, "BACKCHANNEL_FAULT" }) diff --git a/include/trace/misc/rdma.h b/include/trace/misc/rdma.h new file mode 100644 index 000000000000..81bb454fc288 --- /dev/null +++ b/include/trace/misc/rdma.h @@ -0,0 +1,168 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2017 Oracle. All rights reserved. + */ + +/* + * enum ib_event_type, from include/rdma/ib_verbs.h + */ +#define IB_EVENT_LIST \ + ib_event(CQ_ERR) \ + ib_event(QP_FATAL) \ + ib_event(QP_REQ_ERR) \ + ib_event(QP_ACCESS_ERR) \ + ib_event(COMM_EST) \ + ib_event(SQ_DRAINED) \ + ib_event(PATH_MIG) \ + ib_event(PATH_MIG_ERR) \ + ib_event(DEVICE_FATAL) \ + ib_event(PORT_ACTIVE) \ + ib_event(PORT_ERR) \ + ib_event(LID_CHANGE) \ + ib_event(PKEY_CHANGE) \ + ib_event(SM_CHANGE) \ + ib_event(SRQ_ERR) \ + ib_event(SRQ_LIMIT_REACHED) \ + ib_event(QP_LAST_WQE_REACHED) \ + ib_event(CLIENT_REREGISTER) \ + ib_event(GID_CHANGE) \ + ib_event_end(WQ_FATAL) + +#undef ib_event +#undef ib_event_end + +#define ib_event(x) TRACE_DEFINE_ENUM(IB_EVENT_##x); +#define ib_event_end(x) TRACE_DEFINE_ENUM(IB_EVENT_##x); + +IB_EVENT_LIST + +#undef ib_event +#undef ib_event_end + +#define ib_event(x) { IB_EVENT_##x, #x }, +#define ib_event_end(x) { IB_EVENT_##x, #x } + +#define rdma_show_ib_event(x) \ + __print_symbolic(x, IB_EVENT_LIST) + +/* + * enum ib_wc_status type, from include/rdma/ib_verbs.h + */ +#define IB_WC_STATUS_LIST \ + ib_wc_status(SUCCESS) \ + ib_wc_status(LOC_LEN_ERR) \ + ib_wc_status(LOC_QP_OP_ERR) \ + ib_wc_status(LOC_EEC_OP_ERR) \ + ib_wc_status(LOC_PROT_ERR) \ + ib_wc_status(WR_FLUSH_ERR) \ + ib_wc_status(MW_BIND_ERR) \ + ib_wc_status(BAD_RESP_ERR) \ + ib_wc_status(LOC_ACCESS_ERR) \ + ib_wc_status(REM_INV_REQ_ERR) \ + ib_wc_status(REM_ACCESS_ERR) \ + ib_wc_status(REM_OP_ERR) \ + ib_wc_status(RETRY_EXC_ERR) \ + ib_wc_status(RNR_RETRY_EXC_ERR) \ + ib_wc_status(LOC_RDD_VIOL_ERR) \ + ib_wc_status(REM_INV_RD_REQ_ERR) \ + ib_wc_status(REM_ABORT_ERR) \ + ib_wc_status(INV_EECN_ERR) \ + ib_wc_status(INV_EEC_STATE_ERR) \ + ib_wc_status(FATAL_ERR) \ + ib_wc_status(RESP_TIMEOUT_ERR) \ + ib_wc_status_end(GENERAL_ERR) + +#undef ib_wc_status +#undef ib_wc_status_end + +#define ib_wc_status(x) TRACE_DEFINE_ENUM(IB_WC_##x); +#define ib_wc_status_end(x) TRACE_DEFINE_ENUM(IB_WC_##x); + +IB_WC_STATUS_LIST + +#undef ib_wc_status +#undef ib_wc_status_end + +#define ib_wc_status(x) { IB_WC_##x, #x }, +#define ib_wc_status_end(x) { IB_WC_##x, #x } + +#define rdma_show_wc_status(x) \ + __print_symbolic(x, IB_WC_STATUS_LIST) + +/* + * enum ib_cm_event_type, from include/rdma/ib_cm.h + */ +#define IB_CM_EVENT_LIST \ + ib_cm_event(REQ_ERROR) \ + ib_cm_event(REQ_RECEIVED) \ + ib_cm_event(REP_ERROR) \ + ib_cm_event(REP_RECEIVED) \ + ib_cm_event(RTU_RECEIVED) \ + ib_cm_event(USER_ESTABLISHED) \ + ib_cm_event(DREQ_ERROR) \ + ib_cm_event(DREQ_RECEIVED) \ + ib_cm_event(DREP_RECEIVED) \ + ib_cm_event(TIMEWAIT_EXIT) \ + ib_cm_event(MRA_RECEIVED) \ + ib_cm_event(REJ_RECEIVED) \ + ib_cm_event(LAP_ERROR) \ + ib_cm_event(LAP_RECEIVED) \ + ib_cm_event(APR_RECEIVED) \ + ib_cm_event(SIDR_REQ_ERROR) \ + ib_cm_event(SIDR_REQ_RECEIVED) \ + ib_cm_event_end(SIDR_REP_RECEIVED) + +#undef ib_cm_event +#undef ib_cm_event_end + +#define ib_cm_event(x) TRACE_DEFINE_ENUM(IB_CM_##x); +#define ib_cm_event_end(x) TRACE_DEFINE_ENUM(IB_CM_##x); + +IB_CM_EVENT_LIST + +#undef ib_cm_event +#undef ib_cm_event_end + +#define ib_cm_event(x) { IB_CM_##x, #x }, +#define ib_cm_event_end(x) { IB_CM_##x, #x } + +#define rdma_show_ib_cm_event(x) \ + __print_symbolic(x, IB_CM_EVENT_LIST) + +/* + * enum rdma_cm_event_type, from include/rdma/rdma_cm.h + */ +#define RDMA_CM_EVENT_LIST \ + rdma_cm_event(ADDR_RESOLVED) \ + rdma_cm_event(ADDR_ERROR) \ + rdma_cm_event(ROUTE_RESOLVED) \ + rdma_cm_event(ROUTE_ERROR) \ + rdma_cm_event(CONNECT_REQUEST) \ + rdma_cm_event(CONNECT_RESPONSE) \ + rdma_cm_event(CONNECT_ERROR) \ + rdma_cm_event(UNREACHABLE) \ + rdma_cm_event(REJECTED) \ + rdma_cm_event(ESTABLISHED) \ + rdma_cm_event(DISCONNECTED) \ + rdma_cm_event(DEVICE_REMOVAL) \ + rdma_cm_event(MULTICAST_JOIN) \ + rdma_cm_event(MULTICAST_ERROR) \ + rdma_cm_event(ADDR_CHANGE) \ + rdma_cm_event_end(TIMEWAIT_EXIT) + +#undef rdma_cm_event +#undef rdma_cm_event_end + +#define rdma_cm_event(x) TRACE_DEFINE_ENUM(RDMA_CM_EVENT_##x); +#define rdma_cm_event_end(x) TRACE_DEFINE_ENUM(RDMA_CM_EVENT_##x); + +RDMA_CM_EVENT_LIST + +#undef rdma_cm_event +#undef rdma_cm_event_end + +#define rdma_cm_event(x) { RDMA_CM_EVENT_##x, #x }, +#define rdma_cm_event_end(x) { RDMA_CM_EVENT_##x, #x } + +#define rdma_show_cm_event(x) \ + __print_symbolic(x, RDMA_CM_EVENT_LIST) diff --git a/include/trace/misc/sunrpc.h b/include/trace/misc/sunrpc.h new file mode 100644 index 000000000000..588557d07ea8 --- /dev/null +++ b/include/trace/misc/sunrpc.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 Oracle and/or its affiliates. + * + * Common types and format specifiers for sunrpc. + */ + +#if !defined(_TRACE_SUNRPC_BASE_H) +#define _TRACE_SUNRPC_BASE_H + +#include <linux/tracepoint.h> + +#define SUNRPC_TRACE_PID_SPECIFIER "%08x" +#define SUNRPC_TRACE_CLID_SPECIFIER "%08x" +#define SUNRPC_TRACE_TASK_SPECIFIER \ + "task:" SUNRPC_TRACE_PID_SPECIFIER "@" SUNRPC_TRACE_CLID_SPECIFIER + +#endif /* _TRACE_SUNRPC_BASE_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 201dc77ebbd7..d5d2183730b9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3109,6 +3109,10 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). @@ -3117,6 +3121,11 @@ union bpf_attr { * and *params*->smac will not be set as output. A common * use case is to call **bpf_redirect_neigh**\ () after * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6687,6 +6696,8 @@ enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), + BPF_FIB_LOOKUP_SRC = (1U << 4), };

enum { @@ -6699,6 +6710,7 @@ enum { BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ };

struct bpf_fib_lookup { @@ -6733,6 +6745,9 @@ struct bpf_fib_lookup { __u32 rt_metric; };

+ /* input: source address to consider for lookup + * output: source address result from lookup + */ union { __be32 ipv4_src; __u32 ipv6_src[4]; /* in6_addr; network order */ @@ -6747,9 +6762,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ };

- /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index c4c53a9ab959..ff8d21f9e95b 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -145,7 +145,7 @@ struct in6_flowlabel_req { #define IPV6_TLV_PADN 1 #define IPV6_TLV_ROUTERALERT 5 #define IPV6_TLV_CALIPSO 7 /* RFC 5570 */ -#define IPV6_TLV_IOAM 49 /* TEMPORARY IANA allocation for IOAM */ +#define IPV6_TLV_IOAM 49 /* RFC 9486 */ #define IPV6_TLV_JUMBO 194 #define IPV6_TLV_HAO 201 /* home address option */

diff --git a/lib/nlattr.c b/lib/nlattr.c index dffd60e4065f..86344df0ccf7 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -30,6 +30,8 @@ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = { [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), + [NLA_BE16] = sizeof(__be16), + [NLA_BE32] = sizeof(__be32), };

static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { @@ -43,6 +45,8 @@ static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), + [NLA_BE16] = sizeof(__be16), + [NLA_BE32] = sizeof(__be32), };

/* diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 59577946735b..9736e762184b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -37,6 +37,7 @@ #include <linux/page_owner.h> #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> +#include <linux/compat.h>

#include <asm/tlb.h> #include <asm/pgalloc.h> @@ -607,6 +608,9 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, loff_t off_align = round_up(off, size); unsigned long len_pad, ret;

+ if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall()) + return 0; + if (off_end <= off_align || (off_end - off_align) < size) return 0;

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 6a1db678d032..a8932d449eb6 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1049,6 +1049,7 @@ static void hci_error_reset(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset);

+ hci_dev_hold(hdev); BT_DBG("%s", hdev->name);

if (hdev->hw_error) @@ -1056,10 +1057,10 @@ static void hci_error_reset(struct work_struct *work) else bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code);

- if (hci_dev_do_close(hdev)) - return; + if (!hci_dev_do_close(hdev)) + hci_dev_do_open(hdev);

- hci_dev_do_open(hdev); + hci_dev_put(hdev); }

void hci_uuids_clear(struct hci_dev *hdev) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 56ecc5f97b91..452d839c152f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5282,9 +5282,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev);

conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn || !hci_conn_ssp_enabled(conn)) + if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) goto unlock;

+ /* Assume remote supports SSP since it has triggered this event */ + set_bit(HCI_CONN_SSP_ENABLED, &conn->flags); + hci_conn_hold(conn);

if (!hci_dev_test_flag(hdev, HCI_MGMT)) @@ -6716,6 +6719,10 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data, return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_UNKNOWN_CONN_ID);

+ if (max > hcon->le_conn_max_interval) + return send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + if (hci_check_conn_params(min, max, latency, timeout)) return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_INVALID_LL_PARAMS); @@ -7245,10 +7252,10 @@ static void hci_store_wake_reason(struct hci_dev *hdev, u8 event, * keep track of the bdaddr of the connection event that woke us up. */ if (event == HCI_EV_CONN_REQUEST) { - bacpy(&hdev->wake_addr, &conn_complete->bdaddr); + bacpy(&hdev->wake_addr, &conn_request->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_CONN_COMPLETE) { - bacpy(&hdev->wake_addr, &conn_request->bdaddr); + bacpy(&hdev->wake_addr, &conn_complete->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_LE_META) { struct hci_ev_le_meta *le_ev = (void *)skb->data; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 45d19294aa77..a33734046456 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2251,8 +2251,11 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev,

/* During suspend, only wakeable devices can be in acceptlist */ if (hdev->suspended && - !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) + !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) { + hci_le_del_accept_list_sync(hdev, &params->addr, + params->addr_type); return 0; + }

/* Select filter policy to accept all advertising */ if (*num_entries >= hdev->le_accept_list_size) @@ -5482,7 +5485,7 @@ static int hci_inquiry_sync(struct hci_dev *hdev, u8 length)

bt_dev_dbg(hdev, "");

- if (hci_dev_test_flag(hdev, HCI_INQUIRY)) + if (test_bit(HCI_INQUIRY, &hdev->flags)) return 0;

hci_dev_lock(hdev); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 81f5974e5eb5..b4cba55be5ad 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -5614,7 +5614,13 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,

memset(&rsp, 0, sizeof(rsp));

- err = hci_check_conn_params(min, max, latency, to_multiplier); + if (max > hcon->le_conn_max_interval) { + BT_DBG("requested connection interval exceeds current bounds."); + err = -EINVAL; + } else { + err = hci_check_conn_params(min, max, latency, to_multiplier); + } + if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 202ad43e35d6..bff48d576363 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -43,6 +43,10 @@ #include <linux/sysctl.h> #endif

+#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack_core.h> +#endif + static unsigned int brnf_net_id __read_mostly;

struct brnf_net { @@ -553,6 +557,90 @@ static unsigned int br_nf_pre_routing(void *priv, return NF_STOLEN; }

+#if IS_ENABLED(CONFIG_NF_CONNTRACK) +/* conntracks' nf_confirm logic cannot handle cloned skbs referencing + * the same nf_conn entry, which will happen for multicast (broadcast) + * Frames on bridges. + * + * Example: + * macvlan0 + * br0 + * ethX ethY + * + * ethX (or Y) receives multicast or broadcast packet containing + * an IP packet, not yet in conntrack table. + * + * 1. skb passes through bridge and fake-ip (br_netfilter)Prerouting. + * -> skb->_nfct now references a unconfirmed entry + * 2. skb is broad/mcast packet. bridge now passes clones out on each bridge + * interface. + * 3. skb gets passed up the stack. + * 4. In macvlan case, macvlan driver retains clone(s) of the mcast skb + * and schedules a work queue to send them out on the lower devices. + * + * The clone skb->_nfct is not a copy, it is the same entry as the + * original skb. The macvlan rx handler then returns RX_HANDLER_PASS. + * 5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb. + * + * The Macvlan broadcast worker and normal confirm path will race. + * + * This race will not happen if step 2 already confirmed a clone. In that + * case later steps perform skb_clone() with skb->_nfct already confirmed (in + * hash table). This works fine. + * + * But such confirmation won't happen when eb/ip/nftables rules dropped the + * packets before they reached the nf_confirm step in postrouting. + * + * Work around this problem by explicit confirmation of the entry at + * LOCAL_IN time, before upper layer has a chance to clone the unconfirmed + * entry. + * + */ +static unsigned int br_nf_local_in(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conntrack *nfct = skb_nfct(skb); + const struct nf_ct_hook *ct_hook; + struct nf_conn *ct; + int ret; + + if (!nfct || skb->pkt_type == PACKET_HOST) + return NF_ACCEPT; + + ct = container_of(nfct, struct nf_conn, ct_general); + if (likely(nf_ct_is_confirmed(ct))) + return NF_ACCEPT; + + WARN_ON_ONCE(skb_shared(skb)); + WARN_ON_ONCE(refcount_read(&nfct->use) != 1); + + /* We can't call nf_confirm here, it would create a dependency + * on nf_conntrack module. + */ + ct_hook = rcu_dereference(nf_ct_hook); + if (!ct_hook) { + skb->_nfct = 0ul; + nf_conntrack_put(nfct); + return NF_ACCEPT; + } + + nf_bridge_pull_encap_header(skb); + ret = ct_hook->confirm(skb); + switch (ret & NF_VERDICT_MASK) { + case NF_STOLEN: + return NF_STOLEN; + default: + nf_bridge_push_encap_header(skb); + break; + } + + ct = container_of(nfct, struct nf_conn, ct_general); + WARN_ON_ONCE(!nf_ct_is_confirmed(ct)); + + return ret; +} +#endif

/* PF_BRIDGE/FORWARD *************************************************/ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -962,6 +1050,14 @@ static const struct nf_hook_ops br_nf_ops[] = { .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_BRNF, }, +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + { + .hook = br_nf_local_in, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_LOCAL_IN, + .priority = NF_BR_PRI_LAST, + }, +#endif { .hook = br_nf_forward_ip, .pf = NFPROTO_BRIDGE, diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 06d94b2c6b5d..c7c27ada6704 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -291,6 +291,30 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, return nf_conntrack_in(skb, &bridge_state); }

+static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + if (skb->pkt_type == PACKET_HOST) + return NF_ACCEPT; + + /* nf_conntrack_confirm() cannot handle concurrent clones, + * this happens for broad/multicast frames with e.g. macvlan on top + * of the bridge device. + */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) + return NF_ACCEPT; + + /* let inet prerouting call conntrack again */ + skb->_nfct = 0; + nf_ct_put(ct); + + return NF_ACCEPT; +} + static void nf_ct_bridge_frag_save(struct sk_buff *skb, struct nf_bridge_frag_data *data) { @@ -415,6 +439,12 @@ static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = { .hooknum = NF_BR_PRE_ROUTING, .priority = NF_IP_PRI_CONNTRACK, }, + { + .hook = nf_ct_bridge_in, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, { .hook = nf_ct_bridge_post, .pf = NFPROTO_BRIDGE, diff --git a/net/core/filter.c b/net/core/filter.c index 3a6110ea4009..cb7c4651eaec 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5752,6 +5752,12 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb;

+ if (flags & BPF_FIB_LOOKUP_TBID) { + tbid = params->tbid; + /* zero out for vlan output */ + params->tbid = 0; + } + tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; @@ -5803,6 +5809,9 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex;

+ if (flags & BPF_FIB_LOOKUP_SRC) + params->ipv4_src = fib_result_prefsrc(net, &res); + /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ @@ -5885,6 +5894,12 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb;

+ if (flags & BPF_FIB_LOOKUP_TBID) { + tbid = params->tbid; + /* zero out for vlan output */ + params->tbid = 0; + } + tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; @@ -5939,6 +5954,18 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex;

+ if (flags & BPF_FIB_LOOKUP_SRC) { + if (res.f6i->fib6_prefsrc.plen) { + *src = res.f6i->fib6_prefsrc.addr; + } else { + err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev, + &fl6.daddr, 0, + src); + if (err) + return BPF_FIB_LKUP_RET_NO_SRC_ADDR; + } + } + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params;

@@ -5957,7 +5984,8 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, #endif

#define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ - BPF_FIB_LOOKUP_SKIP_NEIGH) + BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ + BPF_FIB_LOOKUP_SRC)

BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7cf1e42d7f93..ac379e4590f8 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5026,10 +5026,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct net_device *dev; - struct nlattr *br_spec, *attr = NULL; + struct nlattr *br_spec, *attr, *br_flags_attr = NULL; int rem, err = -EOPNOTSUPP; u16 flags = 0; - bool have_flags = false;

if (nlmsg_len(nlh) < sizeof(*ifm)) return -EINVAL; @@ -5047,11 +5046,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) { if (nla_len(attr) < sizeof(flags)) return -EINVAL;

- have_flags = true; + br_flags_attr = attr; flags = nla_get_u16(attr); }

@@ -5095,8 +5094,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, } }

- if (have_flags) - memcpy(nla_data(attr), &flags, sizeof(flags)); + if (br_flags_attr) + memcpy(nla_data(br_flags_attr), &flags, sizeof(flags)); out: return err; } diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 80cdc6f6b34c..0323ab5023c6 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -83,7 +83,7 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb) return false;

/* Get next tlv */ - total_length += sizeof(struct hsr_sup_tlv) + hsr_sup_tag->tlv.HSR_TLV_length; + total_length += hsr_sup_tag->tlv.HSR_TLV_length; if (!pskb_may_pull(skb, total_length)) return false; skb_pull(skb, total_length); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 24961b304dad..328f9068c6a4 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -540,6 +540,20 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; }

+static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) +{ + /* we must cap headroom to some upperlimit, else pskb_expand_head + * will overflow header offsets in skb_headers_offset_update(). + */ + static const unsigned int max_allowed = 512; + + if (headroom > max_allowed) + headroom = max_allowed; + + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); +} + void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { @@ -614,13 +628,13 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, }

headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, headroom); - - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } + + ip_tunnel_adj_headroom(dev, headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; @@ -800,16 +814,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,

max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, max_headroom);

- if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return; }

+ ip_tunnel_adj_headroom(dev, max_headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 4073762996e2..fc761915c5f6 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -279,6 +279,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, goto free_nskb;

nf_ct_attach(nskb, oldskb); + nf_ct_set_closing(skb_nfct(oldskb));

#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip_local_out for bridged traffic, the MAC source on diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 46527b5cc8f0..1648373692a9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5473,9 +5473,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, }

addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) - return -EINVAL; - + if (!addr) { + err = -EINVAL; + goto errout; + } ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = dev_get_by_index(tgt_net, ifm->ifa_index); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0b42eb8c55aa..62247621cea5 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1077,6 +1077,7 @@ static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { .udp6_lib_lookup = __udp6_lib_lookup, .ipv6_setsockopt = do_ipv6_setsockopt, .ipv6_getsockopt = do_ipv6_getsockopt, + .ipv6_dev_get_saddr = ipv6_dev_get_saddr, };

static int __init inet6_init(void) diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 433d98bbe33f..71d692728230 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -344,6 +344,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen);

nf_ct_attach(nskb, oldskb); + nf_ct_set_closing(skb_nfct(oldskb));

#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip6_local_out for bridged traffic, the MAC source on diff --git a/net/mctp/route.c b/net/mctp/route.c index 256bf0b89e6c..0144d8ebdaef 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -888,7 +888,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex); if (!dev) { rcu_read_unlock(); - return rc; + goto out_free; } rt->dev = __mctp_dev_get(dev); rcu_read_unlock(); @@ -903,7 +903,8 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, rt->mtu = 0;

} else { - return -EINVAL; + rc = -EINVAL; + goto out_free; }

spin_lock_irqsave(&rt->dev->addrs_lock, flags); @@ -966,12 +967,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, rc = mctp_do_fragment_route(rt, skb, mtu, tag); }

+ /* route output functions consume the skb, even on error */ + skb = NULL; + out_release: if (!ext_rt) mctp_route_release(rt);

mctp_dev_put(tmp_rt.dev);

+out_free: + kfree_skb(skb); return rc; }

diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index e57c5f47f035..7017dd60659d 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -21,6 +21,9 @@ static int subflow_get_info(struct sock *sk, struct sk_buff *skb) bool slow; int err;

+ if (inet_sk_state_load(sk) == TCP_LISTEN) + return 0; + start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; @@ -65,7 +68,7 @@ static int subflow_get_info(struct sock *sk, struct sk_buff *skb) sf->map_data_len) || nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) || nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) || - nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) { + nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) { err = -EMSGSIZE; goto nla_failure; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 70a1025f093c..3328870b0c1f 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -407,23 +407,12 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } }

-static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr, - const struct mptcp_addr_info *addr) -{ - int i; - - for (i = 0; i < nr; i++) { - if (addrs[i].id == addr->id) - return true; - } - - return false; -} - /* Fill all the remote addresses into the array addrs[], * and return the array size. */ -static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh, +static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, + struct mptcp_addr_info *local, + bool fullmesh, struct mptcp_addr_info *addrs) { bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0); @@ -446,15 +435,28 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullm msk->pm.subflows++; addrs[i++] = remote; } else { + DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + + /* Forbid creation of new subflows matching existing + * ones, possibly already created by incoming ADD_ADDR + */ + bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + mptcp_for_each_subflow(msk, subflow) + if (READ_ONCE(subflow->local_id) == local->id) + __set_bit(subflow->remote_id, unavail_id); + mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); remote_address((struct sock_common *)ssk, &addrs[i]); - addrs[i].id = subflow->remote_id; + addrs[i].id = READ_ONCE(subflow->remote_id); if (deny_id0 && !addrs[i].id) continue;

- if (!lookup_address_in_vec(addrs, i, &addrs[i]) && - msk->pm.subflows < subflows_max) { + if (msk->pm.subflows < subflows_max) { + /* forbid creating multiple address towards + * this id + */ + __set_bit(addrs[i].id, unavail_id); msk->pm.subflows++; i++; } @@ -603,7 +605,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);

msk->pm.local_addr_used++; - nr = fill_remote_addresses_vec(msk, fullmesh, addrs); + nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); if (nr) __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); spin_unlock_bh(&msk->pm.lock); @@ -798,18 +800,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,

mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + u8 remote_id = READ_ONCE(subflow->remote_id); int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - u8 id = subflow->local_id; + u8 id = subflow_get_local_id(subflow);

- if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id) + if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) continue;

pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", - i, rm_id, subflow->local_id, subflow->remote_id, - msk->mpc_endpoint_id); + i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how);

@@ -2028,7 +2030,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) if (WARN_ON_ONCE(!sf)) return -EINVAL;

- if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE;

if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 631fa104617c..414ed70e7ba2 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -233,7 +233,7 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk,

lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->local_id == 0) { + if (READ_ONCE(subflow->local_id) == 0) { has_id_0 = true; break; } @@ -489,6 +489,16 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) goto destroy_err; }

+#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) { + ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6); + addr_l.family = AF_INET6; + } + if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) { + ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6); + addr_r.family = AF_INET6; + } +#endif if (addr_l.family != addr_r.family) { GENL_SET_ERR_MSG(info, "address families do not match"); err = -EINVAL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 859b18cb8e4f..3bc21581486a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -119,7 +119,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) subflow->request_mptcp = 1;

/* This is the first subflow, always with id 0 */ - subflow->local_id_valid = 1; + WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket);

return 0; @@ -1319,6 +1319,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, mpext = skb_ext_find(skb, SKB_EXT_MPTCP); if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) { TCP_SKB_CB(skb)->eor = 1; + tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; }

@@ -2440,6 +2441,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { __mptcp_subflow_disconnect(ssk, subflow, flags); + if (msk->subflow && ssk == msk->subflow->sk) + msk->subflow->state = SS_UNCONNECTED; release_sock(ssk);

goto out; @@ -3166,8 +3169,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)

return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } + +static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk) +{ + const struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; + struct ipv6_pinfo *newnp; + + newnp = inet6_sk(newsk); + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + if (!opt) + net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__); + } + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); +} #endif

+static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) +{ + struct ip_options_rcu *inet_opt, *newopt = NULL; + const struct inet_sock *inet = inet_sk(sk); + struct inet_sock *newinet; + + newinet = inet_sk(newsk); + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + inet_opt->opt.optlen, GFP_ATOMIC); + if (newopt) + memcpy(newopt, inet_opt, sizeof(*inet_opt) + + inet_opt->opt.optlen); + else + net_warn_ratelimited("%s: Failed to copy ip options\n", __func__); + } + RCU_INIT_POINTER(newinet->inet_opt, newopt); + rcu_read_unlock(); +} + struct sock *mptcp_sk_clone_init(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct sock *ssk, @@ -3188,6 +3233,13 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,

__mptcp_init_sock(nsk);

+#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (nsk->sk_family == AF_INET6) + mptcp_copy_ip6_options(nsk, sk); + else +#endif + mptcp_copy_ip_options(nsk, sk); + msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; @@ -3200,7 +3252,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, msk->write_seq = subflow_req->idsn + 1; msk->snd_nxt = msk->write_seq; msk->snd_una = msk->write_seq; - msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd; + msk->wnd_end = msk->snd_nxt + tcp_sk(ssk)->snd_wnd; msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;

if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index b09220521323..2bc37773e780 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -475,7 +475,6 @@ struct mptcp_subflow_context { can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; u32 remote_nonce; @@ -483,7 +482,7 @@ struct mptcp_subflow_context { u32 local_nonce; u32 remote_token; u8 hmac[MPTCPOPT_HMAC_LEN]; - u8 local_id; + s16 local_id; /* if negative not initialized yet */ u8 remote_id; u8 reset_seen:1; u8 reset_transient:1; @@ -529,6 +528,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) { memset(&subflow->reset, 0, sizeof(subflow->reset)); subflow->request_mptcp = 1; + WRITE_ONCE(subflow->local_id, -1); }

static inline u64 @@ -909,6 +909,15 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);

+static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) +{ + int local_id = READ_ONCE(subflow->local_id); + + if (local_id < 0) + return 0; + return local_id; +} + void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 45d20e20cfc0..891c2f4fed08 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -446,7 +446,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->backup = mp_opt.backup; subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; - subflow->remote_id = mp_opt.join_id; + WRITE_ONCE(subflow->remote_id, mp_opt.join_id); pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -489,8 +489,8 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)

static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) { - subflow->local_id = local_id; - subflow->local_id_valid = 1; + WARN_ON_ONCE(local_id < 0 || local_id > 255); + WRITE_ONCE(subflow->local_id, local_id); }

static int subflow_chk_local_id(struct sock *sk) @@ -499,7 +499,7 @@ static int subflow_chk_local_id(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(subflow->conn); int err;

- if (likely(subflow->local_id_valid)) + if (likely(subflow->local_id >= 0)) return 0;

err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); @@ -1477,7 +1477,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; - subflow->remote_id = remote_id; + WRITE_ONCE(subflow->remote_id, remote_id); subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); mptcp_info2sockaddr(remote, &addr, ssk->sk_family); @@ -1630,6 +1630,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, pr_debug("subflow=%p", ctx);

ctx->tcp_sock = sk; + WRITE_ONCE(ctx->local_id, -1);

return ctx; } @@ -1867,13 +1868,13 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->idsn = subflow_req->idsn;

/* this is the first subflow, id is always 0 */ - new_ctx->local_id_valid = 1; + subflow_set_local_id(new_ctx, 0); } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->backup = subflow_req->backup; - new_ctx->remote_id = subflow_req->remote_id; + WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac;

diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 55a7f72d547c..edf92074221e 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -707,6 +707,22 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) } EXPORT_SYMBOL(nf_conntrack_destroy);

+void nf_ct_set_closing(struct nf_conntrack *nfct) +{ + const struct nf_ct_hook *ct_hook; + + if (!nfct) + return; + + rcu_read_lock(); + ct_hook = rcu_dereference(nf_ct_hook); + if (ct_hook) + ct_hook->set_closing(nfct); + + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(nf_ct_set_closing); + bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 796026296609..024f93fc8c0b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2772,11 +2772,24 @@ int nf_conntrack_init_start(void) return ret; }

+static void nf_conntrack_set_closing(struct nf_conntrack *nfct) +{ + struct nf_conn *ct = nf_ct_to_nf_conn(nfct); + + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + nf_conntrack_tcp_set_closing(ct); + break; + } +} + static const struct nf_ct_hook nf_conntrack_hook = { .update = nf_conntrack_update, .destroy = nf_ct_destroy, .get_tuple_skb = nf_conntrack_get_tuple_skb, .attach = nf_conntrack_attach, + .set_closing = nf_conntrack_set_closing, + .confirm = __nf_conntrack_confirm, };

void nf_conntrack_init_end(void) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index e0092bf273fd..9480e638e5d1 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -913,6 +913,41 @@ static bool tcp_can_early_drop(const struct nf_conn *ct) return false; }

+void nf_conntrack_tcp_set_closing(struct nf_conn *ct) +{ + enum tcp_conntrack old_state; + const unsigned int *timeouts; + u32 timeout; + + if (!nf_ct_is_confirmed(ct)) + return; + + spin_lock_bh(&ct->lock); + old_state = ct->proto.tcp.state; + ct->proto.tcp.state = TCP_CONNTRACK_CLOSE; + + if (old_state == TCP_CONNTRACK_CLOSE || + test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) { + spin_unlock_bh(&ct->lock); + return; + } + + timeouts = nf_ct_timeout_lookup(ct); + if (!timeouts) { + const struct nf_tcp_net *tn; + + tn = nf_tcp_pernet(nf_ct_net(ct)); + timeouts = tn->timeouts; + } + + timeout = timeouts[TCP_CONNTRACK_CLOSE]; + WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp); + + spin_unlock_bh(&ct->lock); + + nf_conntrack_event_cache(IPCT_PROTOINFO, ct); +} + static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state) { state->td_end = 0; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e21ec3ad8093..d3ba947f4376 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4752,6 +4752,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL;

+ if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout); if (err) return err; @@ -4760,6 +4763,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); }

diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index e1623fbf3654..e4b8c02c5e6a 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -358,10 +358,20 @@ static int nft_target_validate(const struct nft_ctx *ctx,

if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && ctx->family != NFPROTO_BRIDGE && ctx->family != NFPROTO_ARP) return -EOPNOTSUPP;

+ ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -607,10 +617,20 @@ static int nft_match_validate(const struct nft_ctx *ctx,

if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && ctx->family != NFPROTO_BRIDGE && ctx->family != NFPROTO_ARP) return -EOPNOTSUPP;

+ ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6857a4965fe8..e9b81cba1e2b 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -167,7 +167,7 @@ static inline u32 netlink_group_mask(u32 group) static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { - unsigned int len = skb_end_offset(skb); + unsigned int len = skb->len; struct sk_buff *new;

new = alloc_skb(len, gfp_mask); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 93e1bfa72d79..2bd27b77769c 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -273,6 +273,8 @@ static int tls_do_decryption(struct sock *sk, return 0;

ret = crypto_wait_req(ret, &ctx->async_wait); + } else if (darg->async) { + atomic_dec(&ctx->decrypt_pending); } darg->async = false;

@@ -2021,6 +2023,7 @@ int tls_sw_recvmsg(struct sock *sk, struct strp_msg *rxm; struct tls_msg *tlm; ssize_t copied = 0; + ssize_t peeked = 0; bool async = false; int target, err; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); @@ -2168,8 +2171,10 @@ int tls_sw_recvmsg(struct sock *sk, if (err < 0) goto put_on_rx_list_err;

- if (is_peek) + if (is_peek) { + peeked += chunk; goto put_on_rx_list; + }

if (partially_consumed) { rxm->offset += chunk; @@ -2208,8 +2213,8 @@ int tls_sw_recvmsg(struct sock *sk,

/* Drain records from the rx_list & copy if required */ if (is_peek || is_kvec) - err = process_rx_list(ctx, msg, &control, copied, - decrypted, is_peek, NULL); + err = process_rx_list(ctx, msg, &control, copied + peeked, + decrypted - peeked, is_peek, NULL); else err = process_rx_list(ctx, msg, &control, 0, async_copy_bytes, is_peek, NULL); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 767b338a7a2d..ab2c83d58b62 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -284,9 +284,17 @@ void unix_gc(void) * which are creating the cycle(s). */ skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) + list_for_each_entry(u, &gc_candidates, link) { scan_children(&u->sk, inc_inflight, &hitlist);

+#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif + } + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ @@ -314,17 +322,6 @@ void unix_gc(void) /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist);

-#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - list_for_each_entry_safe(u, next, &gc_candidates, link) { - struct sk_buff *skb = u->oob_skb; - - if (skb) { - u->oob_skb = NULL; - kfree_skb(skb); - } - } -#endif - spin_lock(&unix_gc_lock);

/* There could be io_uring registered files, just push them back to diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c259d3227a9e..1a3bd554e258 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4137,6 +4137,8 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info)

if (ntype != NL80211_IFTYPE_MESH_POINT) return -EINVAL; + if (otype != NL80211_IFTYPE_MESH_POINT) + return -EINVAL; if (netif_running(dev)) return -EBUSY;

diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 64ed7665455f..d328965f32f7 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -824,8 +824,8 @@ static int current_check_refer_path(struct dentry *const old_dentry, bool allow_parent1, allow_parent2; access_mask_t access_request_parent1, access_request_parent2; struct path mnt_dir; - layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS], - layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS]; + layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {}, + layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {};

if (!dom) return 0; diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index f4cd9b58b205..a7af085550b2 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -2648,13 +2648,14 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, { int error = buffer_len; size_t avail_len = buffer_len; - char *cp0 = head->write_buf; + char *cp0; int idx;

if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; + cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ diff --git a/sound/core/Makefile b/sound/core/Makefile index 2762f03d9b7b..a7a1590b2952 100644 --- a/sound/core/Makefile +++ b/sound/core/Makefile @@ -30,7 +30,6 @@ snd-ctl-led-objs := control_led.o snd-rawmidi-objs := rawmidi.o snd-timer-objs := timer.o snd-hrtimer-objs := hrtimer.o -snd-rtctimer-objs := rtctimer.o snd-hwdep-objs := hwdep.o snd-seq-device-objs := seq_device.o

diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index 9be2260e4ca2..f8b644cb9157 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -934,7 +934,7 @@ static int generate_device_pkt_descs(struct amdtp_stream *s, // to the reason. unsigned int safe_cycle = increment_ohci_cycle_count(next_cycle, IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES); - lost = (compare_ohci_cycle_count(safe_cycle, cycle) > 0); + lost = (compare_ohci_cycle_count(safe_cycle, cycle) < 0); } if (lost) { dev_err(&s->unit->device, "Detect discontinuity of cycle: %d %d\n", diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 92a656fb5321..75bd7b2fa4ee 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9662,6 +9662,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), @@ -9687,11 +9688,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ab9, "HP EliteBook 840 G8 (MB 8AB8)", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), + SND_PCI_QUIRK(0x103c, 0x8b3f, "HP mt440 Mobile Thin Client U91", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 201dc77ebbd7..d5d2183730b9 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3109,6 +3109,10 @@ union bpf_attr { * **BPF_FIB_LOOKUP_DIRECT** * Do a direct table lookup vs full lookup using FIB * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. * **BPF_FIB_LOOKUP_OUTPUT** * Perform lookup from an egress perspective (default is * ingress). @@ -3117,6 +3121,11 @@ union bpf_attr { * and *params*->smac will not be set as output. A common * use case is to call **bpf_redirect_neigh**\ () after * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -6687,6 +6696,8 @@ enum { BPF_FIB_LOOKUP_DIRECT = (1U << 0), BPF_FIB_LOOKUP_OUTPUT = (1U << 1), BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), + BPF_FIB_LOOKUP_SRC = (1U << 4), };

enum { @@ -6699,6 +6710,7 @@ enum { BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ };

struct bpf_fib_lookup { @@ -6733,6 +6745,9 @@ struct bpf_fib_lookup { __u32 rt_metric; };

+ /* input: source address to consider for lookup + * output: source address result from lookup + */ union { __be32 ipv4_src; __u32 ipv6_src[4]; /* in6_addr; network order */ @@ -6747,9 +6762,19 @@ struct bpf_fib_lookup { __u32 ipv6_dst[4]; /* in6_addr; network order */ };

- /* output */ - __be16 h_vlan_proto; - __be16 h_vlan_TCI; + union { + struct { + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + __u8 smac[6]; /* ETH_ALEN */ __u8 dmac[6]; /* ETH_ALEN */ }; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 2107579e2939..a20dca9d26d6 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -144,6 +144,11 @@ check_tools() exit $ksft_skip fi

+ if ! ss -h | grep -q MPTCP; then + echo "SKIP: ss tool does not support MPTCP" + exit $ksft_skip + fi + # Use the legacy version if available to support old kernel versions if iptables-legacy -V &> /dev/null; then iptables="iptables-legacy"