Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net>
Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org>
Jilai Wang <quic_jilaiw@quicinc.com> <jilaiw@codeaurora.org>
+Jiri Kosina <jikos@kernel.org> <jikos@jikos.cz>
+Jiri Kosina <jikos@kernel.org> <jkosina@suse.cz>
+Jiri Kosina <jikos@kernel.org> <jkosina@suse.com>
Jiri Pirko <jiri@resnulli.us> <jiri@nvidia.com>
Jiri Pirko <jiri@resnulli.us> <jiri@mellanox.com>
Jiri Pirko <jiri@resnulli.us> <jpirko@redhat.com>
- lg,acx467akm-7
# LG Corporation 7" WXGA TFT LCD panel
- lg,ld070wx3-sl01
+ # LG Corporation 5" HD TFT LCD panel
+ - lg,lh500wx1-sd03
# One Stop Displays OSD101T2587-53TS 10.1" 1920x1200 panel
- osddisplays,osd101t2587-53ts
# Panasonic 10" WUXGA TFT LCD panel
- lemaker,bl035-rgb-002
# LG 7" (800x480 pixels) TFT LCD panel
- lg,lb070wv8
- # LG Corporation 5" HD TFT LCD panel
- - lg,lh500wx1-sd03
# LG LP079QX1-SP0V 7.9" (1536x2048 pixels) TFT LCD panel
- lg,lp079qx1-sp0v
# LG 9.7" (2048x1536 pixels) TFT LCD panel
FUSE_OPEN reply.
In direct-io mode the page cache is completely bypassed for reads and writes.
-No read-ahead takes place. Shared mmap is disabled.
+No read-ahead takes place. Shared mmap is disabled by default. To allow shared
+mmap, the FUSE_DIRECT_IO_ALLOW_MMAP flag may be enabled in the FUSE_INIT reply.
In cached mode reads may be satisfied from the page cache, and data may be
read-ahead by the kernel to fill the cache. The cache is always kept consistent
M: Michael Ellerman <mpe@ellerman.id.au>
R: Nicholas Piggin <npiggin@gmail.com>
R: Christophe Leroy <christophe.leroy@csgroup.eu>
+R: Aneesh Kumar K.V <aneesh.kumar@kernel.org>
+R: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
L: linuxppc-dev@lists.ozlabs.org
S: Supported
W: https://github.com/linuxppc/wiki/wiki
F: drivers/misc/sgi-xp/
SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
-M: Karsten Graul <kgraul@linux.ibm.com>
M: Wenjia Zhang <wenjia@linux.ibm.com>
M: Jan Karcher <jaka@linux.ibm.com>
R: D. Wythe <alibuda@linux.alibaba.com>
pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
+ /*
+ * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware
+ * dirtiness again.
+ */
+ if (pte_sw_dirty(pte))
+ pte = pte_mkdirty(pte);
return pte;
}
#define EFI_KIMG_PREFERRED_ADDRESS PHYSADDR(VMLINUX_LOAD_ADDRESS)
-unsigned long kernel_entry_address(void);
+unsigned long kernel_entry_address(unsigned long kernel_addr);
#endif /* _ASM_LOONGARCH_EFI_H */
obj-$(CONFIG_RELOCATABLE) += relocate.o
-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o
#ifndef _ASM_M68K_KEXEC_H
#define _ASM_M68K_KEXEC_H
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
/* Maximum physical address we can use pages from */
#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
#endif /* _ASM_M68K_KEXEC_H */
obj-$(CONFIG_M68K_NONCOHERENT_DMA) += dma.o
-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o
obj-$(CONFIG_BOOTINFO_PROC) += bootinfo_proc.o
obj-$(CONFIG_UBOOT) += uboot.o
compatible = "pci0014,7a03.0",
"pci0014,7a03",
"pciclass0c0320",
- "pciclass0c03",
- "loongson, pci-gmac";
+ "pciclass0c03";
reg = <0x1800 0x0 0x0 0x0 0x0>;
interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
compatible = "pci0014,7a03.0",
"pci0014,7a03",
"pciclass020000",
- "pciclass0200",
- "loongson, pci-gmac";
+ "pciclass0200";
reg = <0x1800 0x0 0x0 0x0 0x0>;
interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
.cpu_disable = octeon_cpu_disable,
.cpu_die = octeon_cpu_die,
#endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
#endif
};
.cpu_disable = octeon_cpu_disable,
.cpu_die = octeon_cpu_die,
#endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
#endif
};
prepare_frametrace(newregs);
}
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
struct kimage;
extern unsigned long kexec_args[4];
extern int (*_machine_kexec_prepare)(struct kimage *);
void (*cpu_die)(unsigned int cpu);
void (*cleanup_dead_cpu)(unsigned cpu);
#endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
void (*kexec_nonboot_cpu)(void);
#endif
};
extern void __noreturn play_dead(void);
#endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
static inline void kexec_nonboot_cpu(void)
{
extern const struct plat_smp_ops *mp_ops; /* private */
obj-$(CONFIG_RELOCATABLE) += relocate.o
-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o
+obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_EARLY_PRINTK_8250) += early_printk_8250.o
.cpu_disable = bmips_cpu_disable,
.cpu_die = bmips_cpu_die,
#endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
#endif
};
.cpu_disable = bmips_cpu_disable,
.cpu_die = bmips_cpu_die,
#endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
#endif
};
local_irq_enable();
}
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC)
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC_CORE)
enum cpu_death {
CPU_DEATH_HALT,
}
}
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
static void cps_kexec_nonboot_cpu(void)
{
cps_shutdown_this_cpu(CPU_DEATH_POWER);
}
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
-#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC */
+#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC_CORE */
#ifdef CONFIG_HOTPLUG_CPU
.cpu_die = cps_cpu_die,
.cleanup_dead_cpu = cps_cleanup_dead_cpu,
#endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
.kexec_nonboot_cpu = cps_kexec_nonboot_cpu,
#endif
};
}
}
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
/* 0X80000000~0X80200000 is safe */
#define MAX_ARGS 64
_machine_halt = loongson_halt;
pm_power_off = loongson_poweroff;
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL);
if (WARN_ON(!kexec_argv))
return -ENOMEM;
.cpu_disable = loongson3_cpu_disable,
.cpu_die = loongson3_cpu_die,
#endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
#endif
};
CONFIG_DEBUG_SG=y
CONFIG_DEBUG_NOTIFIERS=y
CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_DEBUG_CREDENTIALS=y
# CONFIG_FTRACE is not set
CONFIG_XMON=y
# CONFIG_RUNTIME_TESTING_MENU is not set
* same fault IRQ is not freed by the OS before.
*/
mutex_lock(&vas_pseries_mutex);
- if (migration_in_progress)
+ if (migration_in_progress) {
rc = -EBUSY;
- else
+ } else {
rc = allocate_setup_window(txwin, (u64 *)&domain[0],
cop_feat_caps->win_type);
+ if (!rc)
+ caps->nr_open_wins_progress++;
+ }
+
mutex_unlock(&vas_pseries_mutex);
if (rc)
goto out;
goto out_free;
txwin->win_type = cop_feat_caps->win_type;
- mutex_lock(&vas_pseries_mutex);
+
/*
+ * The migration SUSPEND thread sets migration_in_progress and
+ * closes all open windows from the list. But the window is
+ * added to the list after open and modify HCALLs. So possible
+ * that migration_in_progress is set before modify HCALL which
+ * may cause some windows are still open when the hypervisor
+ * initiates the migration.
+ * So checks the migration_in_progress flag again and close all
+ * open windows.
+ *
* Possible to lose the acquired credit with DLPAR core
* removal after the window is opened. So if there are any
* closed windows (means with lost credits), do not give new
* after the existing windows are reopened when credits are
* available.
*/
- if (!caps->nr_close_wins) {
+ mutex_lock(&vas_pseries_mutex);
+ if (!caps->nr_close_wins && !migration_in_progress) {
list_add(&txwin->win_list, &caps->list);
caps->nr_open_windows++;
+ caps->nr_open_wins_progress--;
mutex_unlock(&vas_pseries_mutex);
vas_user_win_add_mm_context(&txwin->vas_win.task_ref);
return &txwin->vas_win;
*/
free_irq_setup(txwin);
h_deallocate_vas_window(txwin->vas_win.winid);
+ /*
+ * Hold mutex and reduce nr_open_wins_progress counter.
+ */
+ mutex_lock(&vas_pseries_mutex);
+ caps->nr_open_wins_progress--;
+ mutex_unlock(&vas_pseries_mutex);
out:
atomic_dec(&cop_feat_caps->nr_used_credits);
kfree(txwin);
struct vas_caps *vcaps;
int i, rc = 0;
+ pr_info("VAS migration event %d\n", action);
+
/*
* NX-GZIP is not enabled. Nothing to do for migration.
*/
if (!copypaste_feat)
return rc;
- mutex_lock(&vas_pseries_mutex);
-
if (action == VAS_SUSPEND)
migration_in_progress = true;
else
switch (action) {
case VAS_SUSPEND:
+ mutex_lock(&vas_pseries_mutex);
rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows,
true);
+ /*
+ * Windows are included in the list after successful
+ * open. So wait for closing these in-progress open
+ * windows in vas_allocate_window() which will be
+ * done if the migration_in_progress is set.
+ */
+ while (vcaps->nr_open_wins_progress) {
+ mutex_unlock(&vas_pseries_mutex);
+ msleep(10);
+ mutex_lock(&vas_pseries_mutex);
+ }
+ mutex_unlock(&vas_pseries_mutex);
break;
case VAS_RESUME:
+ mutex_lock(&vas_pseries_mutex);
atomic_set(&caps->nr_total_credits, new_nr_creds);
rc = reconfig_open_windows(vcaps, new_nr_creds, true);
+ mutex_unlock(&vas_pseries_mutex);
break;
default:
/* should not happen */
goto out;
}
+ pr_info("VAS migration event (%d) successful\n", action);
+
out:
- mutex_unlock(&vas_pseries_mutex);
return rc;
}
struct vas_caps {
struct vas_cop_feat_caps caps;
struct list_head list; /* List of open windows */
+ int nr_open_wins_progress; /* Number of open windows in */
+ /* progress. Used in migration */
int nr_close_wins; /* closed windows in the hypervisor for DLPAR */
int nr_open_windows; /* Number of successful open windows */
u8 feat; /* Feature type */
If unsure what to do here, say N.
config ARCH_SUPPORTS_KEXEC
- def_bool MMU
+ def_bool y
config ARCH_SELECTS_KEXEC
def_bool y
select HOTPLUG_CPU if SMP
config ARCH_SUPPORTS_KEXEC_FILE
- def_bool 64BIT && MMU
+ def_bool 64BIT
config ARCH_SELECTS_KEXEC_FILE
def_bool y
#define PAGE_KERNEL __pgprot(0)
#define swapper_pg_dir NULL
#define TASK_SIZE 0xffffffffUL
-#define VMALLOC_START 0
+#define VMALLOC_START _AC(0, UL)
#define VMALLOC_END TASK_SIZE
#endif /* !CONFIG_MMU */
void arch_crash_save_vmcoreinfo(void)
{
- VMCOREINFO_NUMBER(VA_BITS);
VMCOREINFO_NUMBER(phys_ram_base);
vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET);
vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START);
vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END);
+#ifdef CONFIG_MMU
+ VMCOREINFO_NUMBER(VA_BITS);
vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START);
vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END);
#ifdef CONFIG_64BIT
vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR);
vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END);
+#endif
#endif
vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR);
vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n",
CONFIG_DEBUG_LIST=y
CONFIG_DEBUG_SG=y
CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_DEBUG_CREDENTIALS=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_REF_SCALE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=300
/* The native architecture */
#define KEXEC_ARCH KEXEC_ARCH_SH
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
/* arch/sh/kernel/machine_kexec.c */
void reserve_crashkernel(void);
}
#else
static inline void reserve_crashkernel(void) { }
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
#endif /* __ASM_SH_KEXEC_H */
obj-$(CONFIG_SH_STANDARD_BIOS) += sh_bios.o
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_MODULES) += sh_ksyms_32.o module.o
-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-$(CONFIG_IO_TRAPPED) += io_trapped.o
.shutdown = native_machine_shutdown,
.restart = native_machine_restart,
.halt = native_machine_halt,
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
.crash_shutdown = native_machine_crash_shutdown,
#endif
};
machine_ops.halt();
}
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
void machine_crash_shutdown(struct pt_regs *regs)
{
machine_ops.crash_shutdown(regs);
request_resource(res, &code_resource);
request_resource(res, &data_resource);
request_resource(res, &bss_resource);
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
request_resource(res, &crashk_res);
#endif
{
unsigned long addr = 0;
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
char val[MAX_ADDR_LEN] = { };
int ret;
#define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK)
-#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \
- (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
+#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \
(REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR)))
+#define BUTTRESS_ALL_IRQ_MASK (BUTTRESS_IRQ_MASK | \
+ (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)))
+
#define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK)
#define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1)
vdev->wa.clear_runtime_mem = false;
vdev->wa.d3hot_after_power_off = true;
- if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4)
+ REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK);
+ if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) {
+ /* Writing 1s does not clear the interrupt status register */
vdev->wa.interrupt_clear_with_0 = true;
+ REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, 0x0);
+ }
IVPU_PRINT_WA(punit_disabled);
IVPU_PRINT_WA(clear_runtime_mem);
struct sk_buff *skb;
unsigned int len;
- spin_lock(&card->cli_queue_lock);
+ spin_lock_bh(&card->cli_queue_lock);
skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]);
- spin_unlock(&card->cli_queue_lock);
+ spin_unlock_bh(&card->cli_queue_lock);
if(skb == NULL)
return sprintf(buf, "No data.\n");
struct pkt_hdr *header;
/* Remove any yet-to-be-transmitted packets from the pending queue */
- spin_lock(&card->tx_queue_lock);
+ spin_lock_bh(&card->tx_queue_lock);
skb_queue_walk_safe(&card->tx_queue[port], skb, tmpskb) {
if (SKB_CB(skb)->vcc == vcc) {
skb_unlink(skb, &card->tx_queue[port]);
solos_pop(vcc, skb);
}
}
- spin_unlock(&card->tx_queue_lock);
+ spin_unlock_bh(&card->tx_queue_lock);
skb = alloc_skb(sizeof(*header), GFP_KERNEL);
if (!skb) {
config SM_CAMCC_8550
tristate "SM8550 Camera Clock Controller"
+ depends on ARM64 || COMPILE_TEST
select SM_GCC_8550
help
Support for the camera clock controller on SM8550 devices.
PNAME(mux_pll_src_4plls_p) = { "cpll", "gpll", "gpll_div2", "usb480m" };
PNAME(mux_pll_src_3plls_p) = { "cpll", "gpll", "gpll_div2" };
-PNAME(mux_aclk_peri_src_p) = { "gpll_peri", "cpll_peri", "gpll_div2_peri", "gpll_div3_peri" };
+PNAME(mux_clk_peri_src_p) = { "gpll", "cpll", "gpll_div2", "gpll_div3" };
PNAME(mux_mmc_src_p) = { "cpll", "gpll", "gpll_div2", "xin24m" };
PNAME(mux_clk_cif_out_src_p) = { "clk_cif_src", "xin24m" };
PNAME(mux_sclk_vop_src_p) = { "cpll", "gpll", "gpll_div2", "gpll_div3" };
RK2928_CLKGATE_CON(0), 11, GFLAGS),
/* PD_PERI */
- GATE(0, "gpll_peri", "gpll", CLK_IGNORE_UNUSED,
+ COMPOSITE(0, "clk_peri_src", mux_clk_peri_src_p, 0,
+ RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS,
RK2928_CLKGATE_CON(2), 0, GFLAGS),
- GATE(0, "cpll_peri", "cpll", CLK_IGNORE_UNUSED,
- RK2928_CLKGATE_CON(2), 0, GFLAGS),
- GATE(0, "gpll_div2_peri", "gpll_div2", CLK_IGNORE_UNUSED,
- RK2928_CLKGATE_CON(2), 0, GFLAGS),
- GATE(0, "gpll_div3_peri", "gpll_div3", CLK_IGNORE_UNUSED,
- RK2928_CLKGATE_CON(2), 0, GFLAGS),
- COMPOSITE_NOGATE(0, "aclk_peri_src", mux_aclk_peri_src_p, 0,
- RK2928_CLKSEL_CON(10), 14, 2, MFLAGS, 0, 5, DFLAGS),
- COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "aclk_peri_src", 0,
+
+ COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "clk_peri_src", 0,
RK2928_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
RK2928_CLKGATE_CON(2), 3, GFLAGS),
- COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "aclk_peri_src", 0,
+ COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "clk_peri_src", 0,
RK2928_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
RK2928_CLKGATE_CON(2), 2, GFLAGS),
- GATE(ACLK_PERI, "aclk_peri", "aclk_peri_src", 0,
+ GATE(ACLK_PERI, "aclk_peri", "clk_peri_src", 0,
RK2928_CLKGATE_CON(2), 1, GFLAGS),
GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0,
GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED,
RK2928_CLKGATE_CON(2), 15, GFLAGS),
- COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0,
+ COMPOSITE(SCLK_SDMMC, "sclk_sdmmc", mux_mmc_src_p, 0,
RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS,
RK2928_CLKGATE_CON(2), 11, GFLAGS),
GATE(HCLK_I2S_2CH, "hclk_i2s_2ch", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS),
GATE(0, "hclk_usb_peri", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 13, GFLAGS),
GATE(HCLK_HOST2, "hclk_host2", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS),
- GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(3), 13, GFLAGS),
+ GATE(HCLK_OTG, "hclk_otg", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 13, GFLAGS),
GATE(0, "hclk_peri_ahb", "hclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 14, GFLAGS),
GATE(HCLK_SPDIF, "hclk_spdif", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 9, GFLAGS),
GATE(HCLK_TSP, "hclk_tsp", "hclk_peri", 0, RK2928_CLKGATE_CON(10), 12, GFLAGS),
RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0),
RK3036_PLL_RATE(312000000, 1, 78, 6, 1, 1, 0),
RK3036_PLL_RATE(297000000, 2, 99, 4, 1, 1, 0),
+ RK3036_PLL_RATE(292500000, 1, 195, 4, 4, 1, 0),
RK3036_PLL_RATE(241500000, 2, 161, 4, 2, 1, 0),
RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0),
RK3036_PLL_RATE(200000000, 1, 100, 3, 4, 1, 0),
{
resource_size_t base = -1;
- down_read(&cxl_dpa_rwsem);
+ lockdep_assert_held(&cxl_dpa_rwsem);
if (cxled->dpa_res)
base = cxled->dpa_res->start;
- up_read(&cxl_dpa_rwsem);
return base;
}
cxld->target_type = CXL_DECODER_HOSTONLYMEM;
else
cxld->target_type = CXL_DECODER_DEVMEM;
+
+ guard(rwsem_write)(&cxl_region_rwsem);
if (cxld->id != cxl_num_decoders_committed(port)) {
dev_warn(&port->dev,
"decoder%d.%d: Committed out of order\n",
if (!port || !is_cxl_endpoint(port))
return -EINVAL;
- rc = down_read_interruptible(&cxl_dpa_rwsem);
+ rc = down_read_interruptible(&cxl_region_rwsem);
if (rc)
return rc;
+ rc = down_read_interruptible(&cxl_dpa_rwsem);
+ if (rc) {
+ up_read(&cxl_region_rwsem);
+ return rc;
+ }
+
if (cxl_num_decoders_committed(port) == 0) {
/* No regions mapped to this memdev */
rc = cxl_get_poison_by_memdev(cxlmd);
rc = cxl_get_poison_by_endpoint(port);
}
up_read(&cxl_dpa_rwsem);
+ up_read(&cxl_region_rwsem);
return rc;
}
if (!IS_ENABLED(CONFIG_DEBUG_FS))
return 0;
- rc = down_read_interruptible(&cxl_dpa_rwsem);
+ rc = down_read_interruptible(&cxl_region_rwsem);
if (rc)
return rc;
+ rc = down_read_interruptible(&cxl_dpa_rwsem);
+ if (rc) {
+ up_read(&cxl_region_rwsem);
+ return rc;
+ }
+
rc = cxl_validate_poison_dpa(cxlmd, dpa);
if (rc)
goto out;
trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT);
out:
up_read(&cxl_dpa_rwsem);
+ up_read(&cxl_region_rwsem);
return rc;
}
if (!IS_ENABLED(CONFIG_DEBUG_FS))
return 0;
- rc = down_read_interruptible(&cxl_dpa_rwsem);
+ rc = down_read_interruptible(&cxl_region_rwsem);
if (rc)
return rc;
+ rc = down_read_interruptible(&cxl_dpa_rwsem);
+ if (rc) {
+ up_read(&cxl_region_rwsem);
+ return rc;
+ }
+
rc = cxl_validate_poison_dpa(cxlmd, dpa);
if (rc)
goto out;
trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR);
out:
up_read(&cxl_dpa_rwsem);
+ up_read(&cxl_region_rwsem);
return rc;
}
struct pci_dev *pdev = NULL;
struct cxl_memdev *cxlmd;
size_t cdat_length;
- void *cdat_table;
+ void *cdat_table, *cdat_buf;
int rc;
if (is_cxl_memdev(uport)) {
return;
}
- cdat_table = devm_kzalloc(dev, cdat_length + sizeof(__le32),
- GFP_KERNEL);
- if (!cdat_table)
+ cdat_buf = devm_kzalloc(dev, cdat_length + sizeof(__le32), GFP_KERNEL);
+ if (!cdat_buf)
return;
- rc = cxl_cdat_read_table(dev, cdat_doe, cdat_table, &cdat_length);
+ rc = cxl_cdat_read_table(dev, cdat_doe, cdat_buf, &cdat_length);
if (rc)
goto err;
- cdat_table = cdat_table + sizeof(__le32);
+ cdat_table = cdat_buf + sizeof(__le32);
if (cdat_checksum(cdat_table, cdat_length))
goto err;
err:
/* Don't leave table data allocated on error */
- devm_kfree(dev, cdat_table);
+ devm_kfree(dev, cdat_buf);
dev_err(dev, "Failed to read/validate CDAT.\n");
}
EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
static void remove_dev(void *dev)
{
- device_del(dev);
+ device_unregister(dev);
}
int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs,
char *buf)
{
struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
- u64 base = cxl_dpa_resource_start(cxled);
- return sysfs_emit(buf, "%#llx\n", base);
+ guard(rwsem_read)(&cxl_dpa_rwsem);
+ return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled));
}
static DEVICE_ATTR_RO(dpa_resource);
struct cxl_poison_context ctx;
int rc = 0;
- rc = down_read_interruptible(&cxl_region_rwsem);
- if (rc)
- return rc;
-
ctx = (struct cxl_poison_context) {
.port = port
};
rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport_dev),
&ctx);
- up_read(&cxl_region_rwsem);
return rc;
}
dma_pool_destroy(fsl_chan->tcd_pool);
fsl_chan->tcd_pool = NULL;
fsl_chan->is_sw = false;
+ fsl_chan->srcid = 0;
}
void fsl_edma_cleanup_vchan(struct dma_device *dmadev)
link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS |
DL_FLAG_PM_RUNTIME |
DL_FLAG_RPM_ACTIVE);
- if (IS_ERR(link)) {
- dev_err(dev, "Failed to add device_link to %d: %ld\n", i,
- PTR_ERR(link));
+ if (!link) {
+ dev_err(dev, "Failed to add device_link to %d\n", i);
return -EINVAL;
}
for (i = 0; i < fsl_edma->n_chans; i++) {
fsl_chan = &fsl_edma->chans[i];
+ if (fsl_edma->chan_masked & BIT(i))
+ continue;
spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
/* Make sure chan is idle or will force disable. */
if (unlikely(!fsl_chan->idle)) {
for (i = 0; i < fsl_edma->n_chans; i++) {
fsl_chan = &fsl_edma->chans[i];
+ if (fsl_edma->chan_masked & BIT(i))
+ continue;
fsl_chan->pm_state = RUNNING;
edma_write_tcdreg(fsl_chan, 0, csr);
if (fsl_chan->slave_id != 0)
fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true);
}
- edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
+ if (!(fsl_edma->drvdata->flags & FSL_EDMA_DRV_SPLIT_REG))
+ edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr);
return 0;
}
/*
* This macro calculates the offset into the GRPCFG register
* idxd - struct idxd *
- * n - wq id
- * ofs - the index of the 32b dword for the config register
+ * n - group id
+ * ofs - the index of the 64b qword for the config register
*
- * The WQCFG register block is divided into groups per each wq. The n index
- * allows us to move to the register group that's for that particular wq.
- * Each register is 32bits. The ofs gives us the number of register to access.
+ * The GRPCFG register block is divided into three sub-registers, which
+ * are GRPWQCFG, GRPENGCFG and GRPFLGCFG. The n index allows us to move
+ * to the register block that contains the three sub-registers.
+ * Each register block is 64bits. And the ofs gives us the offset
+ * within the GRPWQCFG register to access.
*/
#define GRPWQCFG_OFFSET(idxd_dev, n, ofs) ((idxd_dev)->grpcfg_offset +\
(n) * GRPCFG_SIZE + sizeof(u64) * (ofs))
portal = idxd_wq_portal_addr(wq);
- /*
- * The wmb() flushes writes to coherent DMA data before
- * possibly triggering a DMA read. The wmb() is necessary
- * even on UP because the recipient is a device.
- */
- wmb();
-
/*
* Pending the descriptor to the lockless list for the irq_entry
* that we designated the descriptor to.
llist_add(&desc->llnode, &ie->pending_llist);
}
+ /*
+ * The wmb() flushes writes to coherent DMA data before
+ * possibly triggering a DMA read. The wmb() is necessary
+ * even on UP because the recipient is a device.
+ */
+ wmb();
+
if (wq_dedicated(wq)) {
iosubmit_cmds512(portal, desc->hw, 1);
} else {
enum dma_slave_buswidth max_width;
struct stm32_dma_desc *desc;
size_t xfer_count, offset;
- u32 num_sgs, best_burst, dma_burst, threshold;
- int i;
+ u32 num_sgs, best_burst, threshold;
+ int dma_burst, i;
num_sgs = DIV_ROUND_UP(len, STM32_DMA_ALIGNED_MAX_DATA_ITEMS);
desc = kzalloc(struct_size(desc, sg_req, num_sgs), GFP_NOWAIT);
best_burst = stm32_dma_get_best_burst(len, STM32_DMA_MAX_BURST,
threshold, max_width);
dma_burst = stm32_dma_get_burst(chan, best_burst);
+ if (dma_burst < 0) {
+ kfree(desc);
+ return NULL;
+ }
stm32_dma_clear_reg(&desc->sg_req[i].chan_reg);
desc->sg_req[i].chan_reg.dma_scr =
PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
- /* PDMA_MAIN0 - SPI0-3 */
+ /* PDMA_MAIN0 - SPI0-2 */
+ PSIL_PDMA_XY_PKT(0x4300),
+ PSIL_PDMA_XY_PKT(0x4301),
PSIL_PDMA_XY_PKT(0x4302),
PSIL_PDMA_XY_PKT(0x4303),
PSIL_PDMA_XY_PKT(0x4304),
PSIL_PDMA_XY_PKT(0x4309),
PSIL_PDMA_XY_PKT(0x430a),
PSIL_PDMA_XY_PKT(0x430b),
- PSIL_PDMA_XY_PKT(0x430c),
- PSIL_PDMA_XY_PKT(0x430d),
/* PDMA_MAIN1 - UART0-6 */
PSIL_PDMA_XY_PKT(0x4400),
PSIL_PDMA_XY_PKT(0x4401),
/* SAUL */
PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
- /* PDMA_MAIN0 - SPI0-3 */
+ /* PDMA_MAIN0 - SPI0-2 */
+ PSIL_PDMA_XY_PKT(0xc300),
+ PSIL_PDMA_XY_PKT(0xc301),
PSIL_PDMA_XY_PKT(0xc302),
PSIL_PDMA_XY_PKT(0xc303),
PSIL_PDMA_XY_PKT(0xc304),
PSIL_PDMA_XY_PKT(0xc309),
PSIL_PDMA_XY_PKT(0xc30a),
PSIL_PDMA_XY_PKT(0xc30b),
- PSIL_PDMA_XY_PKT(0xc30c),
- PSIL_PDMA_XY_PKT(0xc30d),
/* PDMA_MAIN1 - UART0-6 */
PSIL_PDMA_XY_PKT(0xc400),
PSIL_PDMA_XY_PKT(0xc401),
PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
- /* PDMA_MAIN0 - SPI0-3 */
+ /* PDMA_MAIN0 - SPI0-2 */
+ PSIL_PDMA_XY_PKT(0x4300),
+ PSIL_PDMA_XY_PKT(0x4301),
PSIL_PDMA_XY_PKT(0x4302),
PSIL_PDMA_XY_PKT(0x4303),
PSIL_PDMA_XY_PKT(0x4304),
PSIL_PDMA_XY_PKT(0x4309),
PSIL_PDMA_XY_PKT(0x430a),
PSIL_PDMA_XY_PKT(0x430b),
- PSIL_PDMA_XY_PKT(0x430c),
- PSIL_PDMA_XY_PKT(0x430d),
/* PDMA_MAIN1 - UART0-6 */
PSIL_PDMA_XY_PKT(0x4400),
PSIL_PDMA_XY_PKT(0x4401),
/* SAUL */
PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
- /* PDMA_MAIN0 - SPI0-3 */
+ /* PDMA_MAIN0 - SPI0-2 */
+ PSIL_PDMA_XY_PKT(0xc300),
+ PSIL_PDMA_XY_PKT(0xc301),
PSIL_PDMA_XY_PKT(0xc302),
PSIL_PDMA_XY_PKT(0xc303),
PSIL_PDMA_XY_PKT(0xc304),
PSIL_PDMA_XY_PKT(0xc309),
PSIL_PDMA_XY_PKT(0xc30a),
PSIL_PDMA_XY_PKT(0xc30b),
- PSIL_PDMA_XY_PKT(0xc30c),
- PSIL_PDMA_XY_PKT(0xc30d),
/* PDMA_MAIN1 - UART0-6 */
PSIL_PDMA_XY_PKT(0xc400),
PSIL_PDMA_XY_PKT(0xc401),
struct netlink_ext_ack *extack)
{
struct nlattr *tb[DPLL_A_PIN_MAX + 1];
- enum dpll_pin_state state;
u32 ppin_idx;
int ret;
return -EINVAL;
}
ppin_idx = nla_get_u32(tb[DPLL_A_PIN_PARENT_ID]);
- state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
- ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack);
- if (ret)
- return ret;
+
+ if (tb[DPLL_A_PIN_STATE]) {
+ enum dpll_pin_state state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
+
+ ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack);
+ if (ret)
+ return ret;
+ }
return 0;
}
edac_mc_id = emif_get_id(pdev->dev.of_node);
regval = readl(ddrmc_baseaddr + XDDR_REG_CONFIG0_OFFSET);
- num_chans = FIELD_PREP(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval);
+ num_chans = FIELD_GET(XDDR_REG_CONFIG0_NUM_CHANS_MASK, regval);
num_chans++;
- num_csrows = FIELD_PREP(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval);
+ num_csrows = FIELD_GET(XDDR_REG_CONFIG0_NUM_RANKS_MASK, regval);
num_csrows *= 2;
if (!num_csrows)
num_csrows = 1;
return status;
}
-unsigned long kernel_entry_address(void)
+unsigned long kernel_entry_address(unsigned long kernel_addr)
{
unsigned long base = (unsigned long)&kernel_offset - kernel_offset;
- return (unsigned long)&kernel_entry - base + VMLINUX_LOAD_ADDRESS;
+ return (unsigned long)&kernel_entry - base + kernel_addr;
}
return EFI_SUCCESS;
}
-unsigned long __weak kernel_entry_address(void)
+unsigned long __weak kernel_entry_address(unsigned long kernel_addr)
{
- return *(unsigned long *)(PHYSADDR(VMLINUX_LOAD_ADDRESS) + 8);
+ return *(unsigned long *)(kernel_addr + 8) - VMLINUX_LOAD_ADDRESS + kernel_addr;
}
efi_status_t efi_boot_kernel(void *handle, efi_loaded_image_t *image,
csr_write64(CSR_DMW0_INIT, LOONGARCH_CSR_DMWIN0);
csr_write64(CSR_DMW1_INIT, LOONGARCH_CSR_DMWIN1);
- real_kernel_entry = (void *)kernel_entry_address();
+ real_kernel_entry = (void *)kernel_entry_address(kernel_addr);
real_kernel_entry(true, (unsigned long)cmdline_ptr,
(unsigned long)efi_system_table);
efi_err("Memory acceptance protocol failed\n");
}
+static efi_char16_t *efistub_fw_vendor(void)
+{
+ unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor);
+
+ return (efi_char16_t *)vendor;
+}
+
static const efi_char16_t apple[] = L"Apple";
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_APPLE_PROPERTIES) &&
+ !memcmp(efistub_fw_vendor(), apple, sizeof(apple)))
+ retrieve_apple_device_properties(boot_params);
}
/*
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;
+ }
}
status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
amdgpu_ras_suspend(adev);
- amdgpu_ttm_set_buffer_funcs_status(adev, false);
-
amdgpu_device_ip_suspend_phase1(adev);
if (!adev->in_s0ix)
abo = ttm_to_amdgpu_bo(bo);
+ WARN_ON(abo->vm_bo);
+
if (abo->kfd_bo)
amdgpu_amdkfd_release_notify(abo);
if (!entry->bo)
return;
+
+ entry->bo->vm_bo = NULL;
shadow = amdgpu_bo_shadowed(entry->bo);
if (shadow) {
ttm_bo_set_bulk_move(&shadow->tbo, NULL);
amdgpu_bo_unref(&shadow);
}
ttm_bo_set_bulk_move(&entry->bo->tbo, NULL);
- entry->bo->vm_bo = NULL;
spin_lock(&entry->vm->status_lock);
list_del(&entry->vm_status);
struct amdgpu_ring *ring = adev->jpeg.inst->ring_dec;
int r;
- adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
- (adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0);
-
- WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL,
- ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT |
- VCN_JPEG_DB_CTRL__EN_MASK);
-
r = amdgpu_ring_test_helper(ring);
if (r)
return r;
if (adev->pm.dpm_enabled)
amdgpu_dpm_enable_jpeg(adev, true);
+ /* doorbell programming is done for every playback */
+ adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+ (adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0);
+
+ WREG32_SOC15(VCN, 0, regVCN_JPEG_DB_CTRL,
+ ring->doorbell_index << VCN_JPEG_DB_CTRL__OFFSET__SHIFT |
+ VCN_JPEG_DB_CTRL__EN_MASK);
+
/* disable power gating */
r = jpeg_v4_0_5_disable_static_power_gating(adev);
if (r)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int r;
+ adev->sdma.num_instances = SDMA_MAX_INSTANCE;
+
r = sdma_v2_4_init_microcode(adev);
if (r)
return r;
- adev->sdma.num_instances = SDMA_MAX_INSTANCE;
-
sdma_v2_4_set_ring_funcs(adev);
sdma_v2_4_set_buffer_funcs(adev);
sdma_v2_4_set_vm_pte_funcs(adev);
*flags |= AMD_CG_SUPPORT_SDMA_LS;
}
+static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ /* SDMA 5.2.3 (RMB) FW doesn't seem to properly
+ * disallow GFXOFF in some cases leading to
+ * hangs in SDMA. Disallow GFXOFF while SDMA is active.
+ * We can probably just limit this to 5.2.3,
+ * but it shouldn't hurt for other parts since
+ * this GFXOFF will be disallowed anyway when SDMA is
+ * active, this just makes it explicit.
+ */
+ amdgpu_gfx_off_ctrl(adev, false);
+}
+
+static void sdma_v5_2_ring_end_use(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ /* SDMA 5.2.3 (RMB) FW doesn't seem to properly
+ * disallow GFXOFF in some cases leading to
+ * hangs in SDMA. Allow GFXOFF when SDMA is complete.
+ */
+ amdgpu_gfx_off_ctrl(adev, true);
+}
+
const struct amd_ip_funcs sdma_v5_2_ip_funcs = {
.name = "sdma_v5_2",
.early_init = sdma_v5_2_early_init,
.test_ib = sdma_v5_2_ring_test_ib,
.insert_nop = sdma_v5_2_ring_insert_nop,
.pad_ib = sdma_v5_2_ring_pad_ib,
+ .begin_use = sdma_v5_2_ring_begin_use,
+ .end_use = sdma_v5_2_ring_end_use,
.emit_wreg = sdma_v5_2_ring_emit_wreg,
.emit_reg_wait = sdma_v5_2_ring_emit_reg_wait,
.emit_reg_write_reg_wait = sdma_v5_2_ring_emit_reg_write_reg_wait,
if (plane->type == DRM_PLANE_TYPE_CURSOR)
return;
+ if (new_plane_state->rotation != DRM_MODE_ROTATE_0)
+ goto ffu;
+
num_clips = drm_plane_get_damage_clips_count(new_plane_state);
clips = drm_plane_get_damage_clips(new_plane_state);
struct fixed31_32 v_scale_ratio;
enum dc_rotation_angle rotation;
bool mirror;
+ struct dc_stream_state *stream;
};
/* IPP related types */
if (src_y_offset < 0)
src_y_offset = 0;
/* Save necessary cursor info x, y position. w, h is saved in attribute func. */
- hubp->cur_rect.x = src_x_offset + param->viewport.x;
- hubp->cur_rect.y = src_y_offset + param->viewport.y;
+ if (param->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
+ param->rotation != ROTATION_ANGLE_0) {
+ hubp->cur_rect.x = 0;
+ hubp->cur_rect.y = 0;
+ hubp->cur_rect.w = param->stream->timing.h_addressable;
+ hubp->cur_rect.h = param->stream->timing.v_addressable;
+ } else {
+ hubp->cur_rect.x = src_x_offset + param->viewport.x;
+ hubp->cur_rect.y = src_y_offset + param->viewport.y;
+ }
}
void hubp2_clk_cntl(struct hubp *hubp, bool enable)
.phyclk_mhz = 600.0,
.phyclk_d18_mhz = 667.0,
.dscclk_mhz = 186.0,
- .dtbclk_mhz = 625.0,
+ .dtbclk_mhz = 600.0,
},
{
.state = 1,
.phyclk_mhz = 810.0,
.phyclk_d18_mhz = 667.0,
.dscclk_mhz = 209.0,
- .dtbclk_mhz = 625.0,
+ .dtbclk_mhz = 600.0,
},
{
.state = 2,
.phyclk_mhz = 810.0,
.phyclk_d18_mhz = 667.0,
.dscclk_mhz = 209.0,
- .dtbclk_mhz = 625.0,
+ .dtbclk_mhz = 600.0,
},
{
.state = 3,
.phyclk_mhz = 810.0,
.phyclk_d18_mhz = 667.0,
.dscclk_mhz = 371.0,
- .dtbclk_mhz = 625.0,
+ .dtbclk_mhz = 600.0,
},
{
.state = 4,
.phyclk_mhz = 810.0,
.phyclk_d18_mhz = 667.0,
.dscclk_mhz = 417.0,
- .dtbclk_mhz = 625.0,
+ .dtbclk_mhz = 600.0,
},
},
.num_states = 5,
clock_limits[i].socclk_mhz;
dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+ dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz =
+ clock_limits[i].dtbclk_mhz;
dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
clk_table->num_entries;
dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels =
clk_table->num_entries;
dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels =
clk_table->num_entries;
+ dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels =
+ clk_table->num_entries;
}
}
mode_lib->ms.NoOfDPPThisState,
mode_lib->ms.dpte_group_bytes,
s->HostVMInefficiencyFactor,
- mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
+ mode_lib->ms.soc.hostvm_min_page_size_kbytes,
mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
s->NextMaxVStartup = s->MaxVStartupAllPlanes[j];
mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
- mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
+ mode_lib->ms.soc.hostvm_min_page_size_kbytes,
mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k],
mode_lib->ms.MetaRowBytes[j][k],
mode_lib->ms.DPTEBytesPerRow[j][k],
CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
- CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
+ CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = mode_lib->ms.PTEBufferSizeNotExceededPerState;
UseMinimumDCFCLK_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
UseMinimumDCFCLK_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
UseMinimumDCFCLK_params->NumberOfActiveSurfaces = mode_lib->ms.num_active_planes;
- UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
+ UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
UseMinimumDCFCLK_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
UseMinimumDCFCLK_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
UseMinimumDCFCLK_params->ImmediateFlipRequirement = s->ImmediateFlipRequiredFinal;
CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
- CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
+ CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = s->dummy_boolean_array[0];
mode_lib->ms.cache_display_cfg.hw.DPPPerSurface,
locals->dpte_group_bytes,
s->HostVMInefficiencyFactor,
- mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
+ mode_lib->ms.soc.hostvm_min_page_size_kbytes,
mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
locals->TCalc = 24.0 / locals->DCFCLKDeepSleep;
CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable;
CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
- CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
+ CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k];
CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k];
mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
- mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
+ mode_lib->ms.soc.hostvm_min_page_size_kbytes,
locals->PDEAndMetaPTEBytesFrame[k],
locals->MetaRowByte[k],
locals->PixelPTEBytesPerRow[k],
}
for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dtbclk_levels; i++) {
- p->in_states->state_array[i].dtbclk_mhz =
- dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz;
+ if (dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz > 0)
+ p->in_states->state_array[i].dtbclk_mhz =
+ dml2->config.bbox_overrides.clks_table.clk_entries[i].dtbclk_mhz;
}
for (i = 0; i < dml2->config.bbox_overrides.clks_table.num_entries_per_clk.num_dispclk_levels; i++) {
.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
.rotation = pipe_ctx->plane_state->rotation,
- .mirror = pipe_ctx->plane_state->horizontal_mirror
+ .mirror = pipe_ctx->plane_state->horizontal_mirror,
+ .stream = pipe_ctx->stream,
};
bool pipe_split_on = false;
bool odm_combine_on = (pipe_ctx->next_odm_pipe != NULL) ||
if (link && link->dpcd_sink_ext_caps.bits.oled == 1) {
if (!read_default_bl_aux(link, &default_backlight))
default_backlight = 150000;
- // if > 5000, it might be wrong readback
- if (default_backlight > 5000000)
+ // if < 1 nits or > 5000, it might be wrong readback
+ if (default_backlight < 1000 || default_backlight > 5000000)
default_backlight = 150000;
return edp_set_backlight_level_nits(link, true,
((dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x08) ||
(dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x07)))
isPSRSUSupported = false;
+ else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03)
+ isPSRSUSupported = false;
else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1)
isPSRSUSupported = true;
}
} else if (DEVICE_ATTR_IS(xgmi_plpd_policy)) {
if (amdgpu_dpm_get_xgmi_plpd_mode(adev, NULL) == XGMI_PLPD_NONE)
*states = ATTR_STATE_UNSUPPORTED;
- } else if (DEVICE_ATTR_IS(pp_dpm_mclk_od)) {
+ } else if (DEVICE_ATTR_IS(pp_mclk_od)) {
if (amdgpu_dpm_get_mclk_od(adev) == -EOPNOTSUPP)
*states = ATTR_STATE_UNSUPPORTED;
- } else if (DEVICE_ATTR_IS(pp_dpm_sclk_od)) {
+ } else if (DEVICE_ATTR_IS(pp_sclk_od)) {
if (amdgpu_dpm_get_sclk_od(adev) == -EOPNOTSUPP)
*states = ATTR_STATE_UNSUPPORTED;
} else if (DEVICE_ATTR_IS(apu_thermal_cap)) {
drm_master_check_perm(struct drm_device *dev, struct drm_file *file_priv)
{
if (file_priv->was_master &&
- rcu_access_pointer(file_priv->pid) == task_pid(current))
+ rcu_access_pointer(file_priv->pid) == task_tgid(current))
return 0;
if (!capable(CAP_SYS_ADMIN))
struct drm_mode_set set;
uint32_t __user *set_connectors_ptr;
struct drm_modeset_acquire_ctx ctx;
- int ret;
- int i;
+ int ret, i, num_connectors = 0;
if (!drm_core_check_feature(dev, DRIVER_MODESET))
return -EOPNOTSUPP;
connector->name);
connector_set[i] = connector;
+ num_connectors++;
}
}
set.y = crtc_req->y;
set.mode = mode;
set.connectors = connector_set;
- set.num_connectors = crtc_req->count_connectors;
+ set.num_connectors = num_connectors;
set.fb = fb;
if (drm_drv_uses_atomic_modeset(dev))
drm_framebuffer_put(fb);
if (connector_set) {
- for (i = 0; i < crtc_req->count_connectors; i++) {
+ for (i = 0; i < num_connectors; i++) {
if (connector_set[i])
drm_connector_put(connector_set[i]);
}
override = drm_edid_override_get(connector);
if (override) {
- num_modes = drm_edid_connector_update(connector, override);
+ if (drm_edid_connector_update(connector, override) == 0)
+ num_modes = drm_edid_connector_add_modes(connector);
drm_edid_free(override);
const struct intel_crtc_state *crtc_state,
u8 link_bw, u8 rate_select)
{
- u8 link_config[2];
+ u8 lane_count = crtc_state->lane_count;
- /* Write the link configuration data */
- link_config[0] = link_bw;
- link_config[1] = crtc_state->lane_count;
if (crtc_state->enhanced_framing)
- link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
- drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2);
+ lane_count |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
+
+ if (link_bw) {
+ /* DP and eDP v1.3 and earlier link bw set method. */
+ u8 link_config[] = { link_bw, lane_count };
- /* eDP 1.4 rate select method. */
- if (!link_bw)
- drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET,
- &rate_select, 1);
+ drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config,
+ ARRAY_SIZE(link_config));
+ } else {
+ /*
+ * eDP v1.4 and later link rate set method.
+ *
+ * eDP v1.4x sinks shall ignore DP_LINK_RATE_SET if
+ * DP_LINK_BW_SET is set. Avoid writing DP_LINK_BW_SET.
+ *
+ * eDP v1.5 sinks allow choosing either, and the last choice
+ * shall be active.
+ */
+ drm_dp_dpcd_writeb(&intel_dp->aux, DP_LANE_COUNT_SET, lane_count);
+ drm_dp_dpcd_writeb(&intel_dp->aux, DP_LINK_RATE_SET, rate_select);
+ }
}
/*
struct drm_i915_private *i915 = to_i915(fb->base.dev);
unsigned int stride_tiles;
- if (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14)
+ if ((IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) &&
+ src_stride_tiles < dst_stride_tiles)
stride_tiles = src_stride_tiles;
else
stride_tiles = dst_stride_tiles;
size += remap_info->size;
} else {
- unsigned int dst_stride = plane_view_dst_stride_tiles(fb, color_plane,
- remap_info->width);
+ unsigned int dst_stride;
+
+ /*
+ * The hardware automagically calculates the CCS AUX surface
+ * stride from the main surface stride so can't really remap a
+ * smaller subset (unless we'd remap in whole AUX page units).
+ */
+ if (intel_fb_needs_pot_stride_remap(fb) &&
+ intel_fb_is_ccs_modifier(fb->base.modifier))
+ dst_stride = remap_info->src_stride;
+ else
+ dst_stride = remap_info->width;
+
+ dst_stride = plane_view_dst_stride_tiles(fb, color_plane, dst_stride);
assign_chk_ovf(i915, remap_info->dst_stride, dst_stride);
color_plane_info->mapping_stride = dst_stride *
{
struct drm_plane *plane = NULL;
struct intel_plane *intel_plane;
- struct intel_plane_state *plane_state = NULL;
struct intel_crtc_scaler_state *scaler_state =
&crtc_state->scaler_state;
struct drm_atomic_state *drm_state = crtc_state->uapi.state;
/* walkthrough scaler_users bits and start assigning scalers */
for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) {
+ struct intel_plane_state *plane_state = NULL;
int *scaler_id;
const char *name;
int idx, ret;
if (msg)
drm_notice(&engine->i915->drm,
"Resetting %s for %s\n", engine->name, msg);
- atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
+ i915_increase_reset_engine_count(&engine->i915->gpu_error, engine);
ret = intel_gt_reset_engine(engine);
if (ret) {
if (match) {
intel_engine_set_hung_context(e, ce);
engine_mask |= e->mask;
- atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]);
+ i915_increase_reset_engine_count(&i915->gpu_error,
+ e);
}
}
} else {
intel_engine_set_hung_context(ce->engine, ce);
engine_mask = ce->engine->mask;
- atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]);
+ i915_increase_reset_engine_count(&i915->gpu_error, ce->engine);
}
with_intel_runtime_pm(&i915->runtime_pm, wakeref)
#include "display/intel_display_device.h"
#include "gt/intel_engine.h"
+#include "gt/intel_engine_types.h"
#include "gt/intel_gt_types.h"
#include "gt/uc/intel_uc_fw.h"
atomic_t reset_count;
/** Number of times an engine has been reset */
- atomic_t reset_engine_count[I915_NUM_ENGINES];
+ atomic_t reset_engine_count[MAX_ENGINE_CLASS];
};
struct drm_i915_error_state_buf {
static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
const struct intel_engine_cs *engine)
{
- return atomic_read(&error->reset_engine_count[engine->uabi_class]);
+ return atomic_read(&error->reset_engine_count[engine->class]);
+}
+
+static inline void
+i915_increase_reset_engine_count(struct i915_gpu_error *error,
+ const struct intel_engine_cs *engine)
+{
+ atomic_inc(&error->reset_engine_count[engine->class]);
}
#define CORE_DUMP_FLAG_NONE 0x0
}
for_each_engine(engine, gt, id)
- t->reset_engine[id] =
- i915_reset_engine_count(&i915->gpu_error, engine);
+ t->reset_engine[i][id] =
+ i915_reset_engine_count(&i915->gpu_error,
+ engine);
}
t->reset_global = i915_reset_count(&i915->gpu_error);
for_each_gt(gt, i915, i) {
for_each_engine(engine, gt, id) {
- if (t->reset_engine[id] ==
+ if (t->reset_engine[i][id] ==
i915_reset_engine_count(&i915->gpu_error, engine))
continue;
gt_err(gt, "%s(%s): engine '%s' was reset %d times!\n",
t->func, t->name, engine->name,
i915_reset_engine_count(&i915->gpu_error, engine) -
- t->reset_engine[id]);
+ t->reset_engine[i][id]);
return -EIO;
}
}
#ifndef IGT_LIVE_TEST_H
#define IGT_LIVE_TEST_H
+#include "gt/intel_gt_defines.h" /* for I915_MAX_GT */
#include "gt/intel_engine.h" /* for I915_NUM_ENGINES */
struct drm_i915_private;
const char *name;
unsigned int reset_global;
- unsigned int reset_engine[I915_NUM_ENGINES];
+ unsigned int reset_engine[I915_MAX_GT][I915_NUM_ENGINES];
};
/*
/* Disable RELAY mode to pass the processed image */
cfg_val &= ~GAMMA_RELAY_MODE;
- cfg_val = readl(gamma->regs + DISP_GAMMA_CFG);
+ writel(cfg_val, gamma->regs + DISP_GAMMA_CFG);
}
void mtk_gamma_config(struct device *dev, unsigned int w,
crtc);
struct mtk_crtc_state *mtk_crtc_state = to_mtk_crtc_state(crtc_state);
struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+ unsigned long flags;
if (mtk_crtc->event && mtk_crtc_state->base.event)
DRM_ERROR("new event while there is still a pending event\n");
if (mtk_crtc_state->base.event) {
mtk_crtc_state->base.event->pipe = drm_crtc_index(crtc);
WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
+ spin_lock_irqsave(&crtc->dev->event_lock, flags);
mtk_crtc->event = mtk_crtc_state->base.event;
+ spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
mtk_crtc_state->base.event = NULL;
}
}
struct device *mtk_drm_crtc_dma_dev_get(struct drm_crtc *crtc)
{
- struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+ struct mtk_drm_crtc *mtk_crtc = NULL;
+
+ if (!crtc)
+ return NULL;
+
+ mtk_crtc = to_mtk_crtc(crtc);
+ if (!mtk_crtc)
+ return NULL;
return mtk_crtc->dma_dev;
}
struct mtk_drm_private *private = drm->dev_private;
struct mtk_drm_private *priv_n;
struct device *dma_dev = NULL;
+ struct drm_crtc *crtc;
int ret, i, j;
if (drm_firmware_drivers_only())
}
/* Use OVL device for all DMA memory allocations */
- dma_dev = mtk_drm_crtc_dma_dev_get(drm_crtc_from_index(drm, 0));
+ crtc = drm_crtc_from_index(drm, 0);
+ if (crtc)
+ dma_dev = mtk_drm_crtc_dma_dev_get(crtc);
if (!dma_dev) {
ret = -ENODEV;
dev_err(drm->dev, "Need at least one OVL device\n");
/* Ensure an ior is hooked up to this outp already */
ior = outp->func->inherit(outp);
- if (!ior)
+ if (!ior || !ior->arm.head)
return -ENODEV;
/* With iors, there will be a separate output path for each type of connector - and all of
#include <subdev/mmu.h>
struct gk20a_instobj {
- struct nvkm_memory memory;
+ struct nvkm_instobj base;
struct nvkm_mm_node *mn;
struct gk20a_instmem *imem;
/* CPU mapping */
u32 *vaddr;
};
-#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, memory)
+#define gk20a_instobj(p) container_of((p), struct gk20a_instobj, base.memory)
/*
* Used for objects allocated using the DMA API
list_del(&obj->vaddr_node);
vunmap(obj->base.vaddr);
obj->base.vaddr = NULL;
- imem->vaddr_use -= nvkm_memory_size(&obj->base.memory);
+ imem->vaddr_use -= nvkm_memory_size(&obj->base.base.memory);
nvkm_debug(&imem->base.subdev, "vaddr used: %x/%x\n", imem->vaddr_use,
imem->vaddr_max);
}
{
struct gk20a_instobj *node = gk20a_instobj(memory);
struct nvkm_vmm_map map = {
- .memory = &node->memory,
+ .memory = &node->base.memory,
.offset = offset,
.mem = node->mn,
};
return -ENOMEM;
*_node = &node->base;
- nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.memory);
- node->base.memory.ptrs = &gk20a_instobj_ptrs;
+ nvkm_memory_ctor(&gk20a_instobj_func_dma, &node->base.base.memory);
+ node->base.base.memory.ptrs = &gk20a_instobj_ptrs;
node->base.vaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT,
&node->handle, GFP_KERNEL,
*_node = &node->base;
node->dma_addrs = (void *)(node->pages + npages);
- nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.memory);
- node->base.memory.ptrs = &gk20a_instobj_ptrs;
+ nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.base.memory);
+ node->base.base.memory.ptrs = &gk20a_instobj_ptrs;
/* Allocate backing memory */
for (i = 0; i < npages; i++) {
else
ret = gk20a_instobj_ctor_dma(imem, size >> PAGE_SHIFT,
align, &node);
- *pmemory = node ? &node->memory : NULL;
+ *pmemory = node ? &node->base.memory : NULL;
if (ret)
return ret;
static const struct ltk050h3146w_desc ltk050h3148w_data = {
.mode = <k050h3148w_mode,
.init = ltk050h3148w_init_sequence,
- .mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE,
+ .mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_VIDEO_BURST,
};
static int ltk050h3146w_init_sequence(struct ltk050h3146w *ctx)
{ "Hailuck" },
{ "Jamesdonkey" },
{ "A3R" },
+ { "hfd.cn" },
+ { "WKB603" },
};
static bool apple_is_non_apple_keyboard(struct hid_device *hdev)
#define USB_VENDOR_ID_LABTEC 0x1020
#define USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD 0x0006
+#define USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE 0x8888
#define USB_VENDOR_ID_LAVIEW 0x22D4
#define USB_DEVICE_ID_GLORIOUS_MODEL_I 0x1503
* so set middlebutton_state to 3
* to never apply workaround anymore
*/
- if (cptkbd_data->middlebutton_state == 1 &&
+ if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD &&
+ cptkbd_data->middlebutton_state == 1 &&
usage->type == EV_REL &&
(usage->code == REL_X || usage->code == REL_Y)) {
cptkbd_data->middlebutton_state = 3;
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_T609A), HID_QUIRK_MULTI_INPUT },
+ { HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL },
* ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible.
*/
{ "CHPN0001" },
+ /*
+ * The IDEA5002 ACPI device causes high interrupt usage and spurious
+ * wakeups from suspend.
+ */
+ { "IDEA5002" },
{ }
};
* compare it to the stored version, just create the meta
*/
if (io_sq->disable_meta_caching) {
- if (unlikely(!ena_tx_ctx->meta_valid))
- return -EINVAL;
-
*have_meta = true;
return ena_com_create_meta(io_sq, ena_meta);
}
struct ena_tx_buffer *tx_info);
static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter,
int first_index, int count);
+static void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter,
+ int first_index, int count);
/* Increase a stat by cnt while holding syncp seqlock on 32bit machines */
static void ena_increase_stat(u64 *statp, u64 cnt,
static int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter)
{
+ u32 xdp_first_ring = adapter->xdp_first_ring;
+ u32 xdp_num_queues = adapter->xdp_num_queues;
int rc = 0;
- rc = ena_setup_tx_resources_in_range(adapter, adapter->xdp_first_ring,
- adapter->xdp_num_queues);
+ rc = ena_setup_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues);
if (rc)
goto setup_err;
- rc = ena_create_io_tx_queues_in_range(adapter,
- adapter->xdp_first_ring,
- adapter->xdp_num_queues);
+ rc = ena_create_io_tx_queues_in_range(adapter, xdp_first_ring, xdp_num_queues);
if (rc)
goto create_err;
return 0;
create_err:
- ena_free_all_io_tx_resources(adapter);
+ ena_free_all_io_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues);
setup_err:
return rc;
}
if (unlikely(!skb))
return NULL;
- /* sync this buffer for CPU use */
- dma_sync_single_for_cpu(rx_ring->dev,
- dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
- len,
- DMA_FROM_DEVICE);
skb_copy_to_linear_data(skb, buf_addr + buf_offset, len);
dma_sync_single_for_device(rx_ring->dev,
dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
buf_len = SKB_DATA_ALIGN(len + buf_offset + tailroom);
- pre_reuse_paddr = dma_unmap_addr(&rx_info->ena_buf, paddr);
-
/* If XDP isn't loaded try to reuse part of the RX buffer */
reuse_rx_buf_page = !is_xdp_loaded &&
ena_try_rx_buf_page_reuse(rx_info, buf_len, len, pkt_offset);
- dma_sync_single_for_cpu(rx_ring->dev,
- pre_reuse_paddr + pkt_offset,
- len,
- DMA_FROM_DEVICE);
-
if (!reuse_rx_buf_page)
ena_unmap_rx_buff_attrs(rx_ring, rx_info, DMA_ATTR_SKIP_CPU_SYNC);
}
}
-static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp)
+static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp, u16 num_descs)
{
struct ena_rx_buffer *rx_info;
int ret;
+ /* XDP multi-buffer packets not supported */
+ if (unlikely(num_descs > 1)) {
+ netdev_err_once(rx_ring->adapter->netdev,
+ "xdp: dropped unsupported multi-buffer packets\n");
+ ena_increase_stat(&rx_ring->rx_stats.xdp_drop, 1, &rx_ring->syncp);
+ return ENA_XDP_DROP;
+ }
+
rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
xdp_prepare_buff(xdp, page_address(rx_info->page),
rx_info->buf_offset,
rx_ring->ena_bufs[0].len, false);
- /* If for some reason we received a bigger packet than
- * we expect, then we simply drop it
- */
- if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU))
- return ENA_XDP_DROP;
ret = ena_xdp_execute(rx_ring, xdp);
int xdp_flags = 0;
int total_len = 0;
int xdp_verdict;
+ u8 pkt_offset;
int rc = 0;
int i;
/* First descriptor might have an offset set by the device */
rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
- rx_info->buf_offset += ena_rx_ctx.pkt_offset;
+ pkt_offset = ena_rx_ctx.pkt_offset;
+ rx_info->buf_offset += pkt_offset;
netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
"rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n",
rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto,
ena_rx_ctx.l4_proto, ena_rx_ctx.hash);
+ dma_sync_single_for_cpu(rx_ring->dev,
+ dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
+ rx_ring->ena_bufs[0].len,
+ DMA_FROM_DEVICE);
+
if (ena_xdp_present_ring(rx_ring))
- xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp);
+ xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp, ena_rx_ctx.descs);
/* allocate skb and fill it */
if (xdp_verdict == ENA_XDP_PASS)
if (xdp_verdict & ENA_XDP_FORWARDED) {
ena_unmap_rx_buff_attrs(rx_ring,
&rx_ring->rx_buffer_info[req_id],
- 0);
+ DMA_ATTR_SKIP_CPU_SYNC);
rx_ring->rx_buffer_info[req_id].page = NULL;
}
}
return;
kfree(self->buff_ring);
+ self->buff_ring = NULL;
- if (self->dx_ring)
+ if (self->dx_ring) {
dma_free_coherent(aq_nic_get_dev(self->aq_nic),
self->size * self->dx_size, self->dx_ring,
self->dx_ring_pa);
+ self->dx_ring = NULL;
+ }
}
unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data)
static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
struct sk_buff *skb)
{
+ skb_mark_for_recycle(skb);
+
if (skb->dev != bp->dev) {
/* this packet belongs to a vf-rep */
bnxt_vf_rep_rx(bp, skb);
return;
}
skb_record_rx_queue(skb, bnapi->index);
- skb_mark_for_recycle(skb);
napi_gro_receive(&bnapi->napi, skb);
}
+static bool bnxt_rx_ts_valid(struct bnxt *bp, u32 flags,
+ struct rx_cmp_ext *rxcmp1, u32 *cmpl_ts)
+{
+ u32 ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
+
+ if (BNXT_PTP_RX_TS_VALID(flags))
+ goto ts_valid;
+ if (!bp->ptp_all_rx_tstamp || !ts || !BNXT_ALL_RX_TS_VALID(flags))
+ return false;
+
+ts_valid:
+ *cmpl_ts = ts;
+ return true;
+}
+
/* returns the following:
* 1 - 1 packet successfully received
* 0 - successful TPA_START, packet not completed yet
struct sk_buff *skb;
struct xdp_buff xdp;
u32 flags, misc;
+ u32 cmpl_ts;
void *data;
int rc = 0;
}
}
- if (unlikely((flags & RX_CMP_FLAGS_ITYPES_MASK) ==
- RX_CMP_FLAGS_ITYPE_PTP_W_TS) || bp->ptp_all_rx_tstamp) {
+ if (bnxt_rx_ts_valid(bp, flags, rxcmp1, &cmpl_ts)) {
if (bp->flags & BNXT_FLAG_CHIP_P5) {
- u32 cmpl_ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
u64 ns, ts;
if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) {
bnxt_free_mem(bp, irq_re_init);
}
-int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
+void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
{
- int rc = 0;
-
if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
/* If we get here, it means firmware reset is in progress
* while we are trying to close. We can safely proceed with
#ifdef CONFIG_BNXT_SRIOV
if (bp->sriov_cfg) {
+ int rc;
+
rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait,
!bp->sriov_cfg,
BNXT_SRIOV_CFG_WAIT_TMO);
- if (rc)
- netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n");
+ if (!rc)
+ netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete, proceeding to close!\n");
+ else if (rc < 0)
+ netdev_warn(bp->dev, "SRIOV config operation interrupted, proceeding to close!\n");
}
#endif
__bnxt_close_nic(bp, irq_re_init, link_re_init);
- return rc;
}
static int bnxt_close(struct net_device *dev)
if (rc)
goto resume_exit;
+ bnxt_clear_reservations(bp, true);
+
if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) {
rc = -ENODEV;
goto resume_exit;
#define RX_CMP_FLAGS_ERROR (1 << 6)
#define RX_CMP_FLAGS_PLACEMENT (7 << 7)
#define RX_CMP_FLAGS_RSS_VALID (1 << 10)
- #define RX_CMP_FLAGS_UNUSED (1 << 11)
+ #define RX_CMP_FLAGS_PKT_METADATA_PRESENT (1 << 11)
#define RX_CMP_FLAGS_ITYPES_SHIFT 12
#define RX_CMP_FLAGS_ITYPES_MASK 0xf000
#define RX_CMP_FLAGS_ITYPE_UNKNOWN (0 << 12)
__le32 rx_cmp_rss_hash;
};
+#define BNXT_PTP_RX_TS_VALID(flags) \
+ (((flags) & RX_CMP_FLAGS_ITYPES_MASK) == RX_CMP_FLAGS_ITYPE_PTP_W_TS)
+
+#define BNXT_ALL_RX_TS_VALID(flags) \
+ !((flags) & RX_CMP_FLAGS_PKT_METADATA_PRESENT)
+
#define RX_CMP_HASH_VALID(rxcmp) \
((rxcmp)->rx_cmp_len_flags_type & cpu_to_le32(RX_CMP_FLAGS_RSS_VALID))
int bnxt_half_open_nic(struct bnxt *bp);
void bnxt_half_close_nic(struct bnxt *bp);
void bnxt_reenable_sriov(struct bnxt *bp);
-int bnxt_close_nic(struct bnxt *, bool, bool);
+void bnxt_close_nic(struct bnxt *, bool, bool);
void bnxt_get_ring_err_stats(struct bnxt *bp,
struct bnxt_total_ring_err_stats *stats);
int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
return -ENODEV;
}
bnxt_ulp_stop(bp);
- if (netif_running(bp->dev)) {
- rc = bnxt_close_nic(bp, true, true);
- if (rc) {
- NL_SET_ERR_MSG_MOD(extack, "Failed to close");
- dev_close(bp->dev);
- rtnl_unlock();
- break;
- }
- }
+ if (netif_running(bp->dev))
+ bnxt_close_nic(bp, true, true);
bnxt_vf_reps_free(bp);
rc = bnxt_hwrm_func_drv_unrgtr(bp);
if (rc) {
reset_coalesce:
if (test_bit(BNXT_STATE_OPEN, &bp->state)) {
if (update_stats) {
- rc = bnxt_close_nic(bp, true, false);
- if (!rc)
- rc = bnxt_open_nic(bp, true, false);
+ bnxt_close_nic(bp, true, false);
+ rc = bnxt_open_nic(bp, true, false);
} else {
rc = bnxt_hwrm_set_coal(bp);
}
* before PF unload
*/
}
- rc = bnxt_close_nic(bp, true, false);
- if (rc) {
- netdev_err(bp->dev, "Set channel failure rc :%x\n",
- rc);
- return rc;
- }
+ bnxt_close_nic(bp, true, false);
}
if (sh) {
bnxt_run_fw_tests(bp, test_mask, &test_results);
} else {
bnxt_ulp_stop(bp);
- rc = bnxt_close_nic(bp, true, false);
- if (rc) {
- etest->flags |= ETH_TEST_FL_FAILED;
- bnxt_ulp_start(bp, rc);
- return;
- }
+ bnxt_close_nic(bp, true, false);
bnxt_run_fw_tests(bp, test_mask, &test_results);
buf[BNXT_MACLPBK_TEST_IDX] = 1;
if (netif_running(bp->dev)) {
if (ptp->rx_filter == HWTSTAMP_FILTER_ALL) {
- rc = bnxt_close_nic(bp, false, false);
- if (!rc)
- rc = bnxt_open_nic(bp, false, false);
+ bnxt_close_nic(bp, false, false);
+ rc = bnxt_open_nic(bp, false, false);
} else {
bnxt_ptp_cfg_tstamp_filters(bp);
}
err = dpsw_acl_add_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
filter_block->acl_id, acl_entry_cfg);
- dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
+ dma_unmap_single(dev, acl_entry_cfg->key_iova,
+ DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE,
DMA_TO_DEVICE);
if (err) {
dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err);
err = dpsw_acl_remove_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
block->acl_id, acl_entry_cfg);
- dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
- DMA_TO_DEVICE);
+ dma_unmap_single(dev, acl_entry_cfg->key_iova,
+ DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE);
if (err) {
dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err);
kfree(cmd_buff);
return notifier_from_errno(err);
}
-static struct notifier_block dpaa2_switch_port_switchdev_nb;
-static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb;
-
static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
struct net_device *upper_dev,
struct netlink_ext_ack *extack)
goto err_egress_flood;
err = switchdev_bridge_port_offload(netdev, netdev, NULL,
- &dpaa2_switch_port_switchdev_nb,
- &dpaa2_switch_port_switchdev_blocking_nb,
- false, extack);
+ NULL, NULL, false, extack);
if (err)
goto err_switchdev_offload;
static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev)
{
- switchdev_bridge_port_unoffload(netdev, NULL,
- &dpaa2_switch_port_switchdev_nb,
- &dpaa2_switch_port_switchdev_blocking_nb);
+ switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL);
}
static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
return 0;
}
-static u16 fec_enet_get_raw_vlan_tci(struct sk_buff *skb)
-{
- struct vlan_ethhdr *vhdr;
- unsigned short vlan_TCI = 0;
-
- if (skb->protocol == htons(ETH_P_ALL)) {
- vhdr = (struct vlan_ethhdr *)(skb->data);
- vlan_TCI = ntohs(vhdr->h_vlan_TCI);
- }
-
- return vlan_TCI;
-}
-
static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb,
struct net_device *sb_dev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
- u16 vlan_tag;
+ u16 vlan_tag = 0;
if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
return netdev_pick_tx(ndev, skb, NULL);
- vlan_tag = fec_enet_get_raw_vlan_tci(skb);
- if (!vlan_tag)
+ /* VLAN is present in the payload.*/
+ if (eth_type_vlan(skb->protocol)) {
+ struct vlan_ethhdr *vhdr = skb_vlan_eth_hdr(skb);
+
+ vlan_tag = ntohs(vhdr->h_vlan_TCI);
+ /* VLAN is present in the skb but not yet pushed in the payload.*/
+ } else if (skb_vlan_tag_present(skb)) {
+ vlan_tag = skb->vlan_tci;
+ } else {
return vlan_tag;
+ }
return fec_enet_vlan_pri_to_queue[vlan_tag >> 13];
}
#define IAVF_FLAG_QUEUES_DISABLED BIT(17)
#define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18)
#define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20)
+#define IAVF_FLAG_FDIR_ENABLED BIT(21)
/* duplicates for common code */
#define IAVF_FLAG_DCB_ENABLED 0
/* flags for admin queue service task */
struct iavf_fdir_fltr *rule = NULL;
int ret = 0;
- if (!FDIR_FLTR_SUPPORT(adapter))
+ if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
return -EOPNOTSUPP;
spin_lock_bh(&adapter->fdir_fltr_lock);
unsigned int cnt = 0;
int val = 0;
- if (!FDIR_FLTR_SUPPORT(adapter))
+ if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
return -EOPNOTSUPP;
cmd->data = IAVF_MAX_FDIR_FILTERS;
int count = 50;
int err;
- if (!FDIR_FLTR_SUPPORT(adapter))
+ if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
return -EOPNOTSUPP;
if (fsp->flow_type & FLOW_MAC_EXT)
spin_lock_bh(&adapter->fdir_fltr_lock);
iavf_fdir_list_add_fltr(adapter, fltr);
adapter->fdir_active_fltr++;
- fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
- adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+ if (adapter->link_up) {
+ fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+ } else {
+ fltr->state = IAVF_FDIR_FLTR_INACTIVE;
+ }
spin_unlock_bh(&adapter->fdir_fltr_lock);
- mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
-
+ if (adapter->link_up)
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
ret:
if (err && fltr)
kfree(fltr);
struct iavf_fdir_fltr *fltr = NULL;
int err = 0;
- if (!FDIR_FLTR_SUPPORT(adapter))
+ if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
return -EOPNOTSUPP;
spin_lock_bh(&adapter->fdir_fltr_lock);
if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) {
fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST;
adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER;
+ } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) {
+ list_del(&fltr->list);
+ kfree(fltr);
+ adapter->fdir_active_fltr--;
+ fltr = NULL;
} else {
err = -EBUSY;
}
ret = 0;
break;
case ETHTOOL_GRXCLSRLCNT:
- if (!FDIR_FLTR_SUPPORT(adapter))
+ if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
break;
spin_lock_bh(&adapter->fdir_fltr_lock);
cmd->rule_cnt = adapter->fdir_active_fltr;
struct iavf_adapter;
-/* State of Flow Director filter */
+/* State of Flow Director filter
+ *
+ * *_REQUEST states are used to mark filter to be sent to PF driver to perform
+ * an action (either add or delete filter). *_PENDING states are an indication
+ * that request was sent to PF and the driver is waiting for response.
+ *
+ * Both DELETE and DISABLE states are being used to delete a filter in PF.
+ * The difference is that after a successful response filter in DEL_PENDING
+ * state is being deleted from VF driver as well and filter in DIS_PENDING state
+ * is being changed to INACTIVE state.
+ */
enum iavf_fdir_fltr_state_t {
IAVF_FDIR_FLTR_ADD_REQUEST, /* User requests to add filter */
IAVF_FDIR_FLTR_ADD_PENDING, /* Filter pending add by the PF */
IAVF_FDIR_FLTR_DEL_REQUEST, /* User requests to delete filter */
IAVF_FDIR_FLTR_DEL_PENDING, /* Filter pending delete by the PF */
+ IAVF_FDIR_FLTR_DIS_REQUEST, /* Filter scheduled to be disabled */
+ IAVF_FDIR_FLTR_DIS_PENDING, /* Filter pending disable by the PF */
+ IAVF_FDIR_FLTR_INACTIVE, /* Filter inactive on link down */
IAVF_FDIR_FLTR_ACTIVE, /* Filter is active */
};
kfree(mem->va);
}
-/**
- * iavf_lock_timeout - try to lock mutex but give up after timeout
- * @lock: mutex that should be locked
- * @msecs: timeout in msecs
- *
- * Returns 0 on success, negative on failure
- **/
-static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs)
-{
- unsigned int wait, delay = 10;
-
- for (wait = 0; wait < msecs; wait += delay) {
- if (mutex_trylock(lock))
- return 0;
-
- msleep(delay);
- }
-
- return -1;
-}
-
/**
* iavf_schedule_reset - Set the flags and schedule a reset event
* @adapter: board private structure
**/
static void iavf_clear_fdir_filters(struct iavf_adapter *adapter)
{
- struct iavf_fdir_fltr *fdir, *fdirtmp;
+ struct iavf_fdir_fltr *fdir;
/* remove all Flow Director filters */
spin_lock_bh(&adapter->fdir_fltr_lock);
- list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head,
- list) {
+ list_for_each_entry(fdir, &adapter->fdir_list_head, list) {
if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) {
- list_del(&fdir->list);
- kfree(fdir);
- adapter->fdir_active_fltr--;
- } else {
- fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+ /* Cancel a request, keep filter as inactive */
+ fdir->state = IAVF_FDIR_FLTR_INACTIVE;
+ } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+ fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
+ /* Disable filters which are active or have a pending
+ * request to PF to be added
+ */
+ fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST;
}
}
spin_unlock_bh(&adapter->fdir_fltr_lock);
}
}
+/**
+ * iavf_restore_fdir_filters
+ * @adapter: board private structure
+ *
+ * Restore existing FDIR filters when VF netdev comes back up.
+ **/
+static void iavf_restore_fdir_filters(struct iavf_adapter *adapter)
+{
+ struct iavf_fdir_fltr *f;
+
+ spin_lock_bh(&adapter->fdir_fltr_lock);
+ list_for_each_entry(f, &adapter->fdir_list_head, list) {
+ if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) {
+ /* Cancel a request, keep filter as active */
+ f->state = IAVF_FDIR_FLTR_ACTIVE;
+ } else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING ||
+ f->state == IAVF_FDIR_FLTR_INACTIVE) {
+ /* Add filters which are inactive or have a pending
+ * request to PF to be deleted
+ */
+ f->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+ }
+ }
+ spin_unlock_bh(&adapter->fdir_fltr_lock);
+}
+
/**
* iavf_open - Called when a network interface is made active
* @netdev: network interface device structure
spin_unlock_bh(&adapter->mac_vlan_list_lock);
- /* Restore VLAN filters that were removed with IFF_DOWN */
+ /* Restore filters that were removed with IFF_DOWN */
iavf_restore_filters(adapter);
+ iavf_restore_fdir_filters(adapter);
iavf_configure(adapter);
return ret;
}
+/**
+ * iavf_disable_fdir - disable Flow Director and clear existing filters
+ * @adapter: board private structure
+ **/
+static void iavf_disable_fdir(struct iavf_adapter *adapter)
+{
+ struct iavf_fdir_fltr *fdir, *fdirtmp;
+ bool del_filters = false;
+
+ adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED;
+
+ /* remove all Flow Director filters */
+ spin_lock_bh(&adapter->fdir_fltr_lock);
+ list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head,
+ list) {
+ if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST ||
+ fdir->state == IAVF_FDIR_FLTR_INACTIVE) {
+ /* Delete filters not registered in PF */
+ list_del(&fdir->list);
+ kfree(fdir);
+ adapter->fdir_active_fltr--;
+ } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+ fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
+ fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
+ /* Filters registered in PF, schedule their deletion */
+ fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+ del_filters = true;
+ } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+ /* Request to delete filter already sent to PF, change
+ * state to DEL_PENDING to delete filter after PF's
+ * response, not set as INACTIVE
+ */
+ fdir->state = IAVF_FDIR_FLTR_DEL_PENDING;
+ }
+ }
+ spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+ if (del_filters) {
+ adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER;
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+ }
+}
+
#define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \
NETIF_F_HW_VLAN_CTAG_TX | \
NETIF_F_HW_VLAN_STAG_RX | \
((netdev->features & NETIF_F_RXFCS) ^ (features & NETIF_F_RXFCS)))
iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
+ if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) {
+ if (features & NETIF_F_NTUPLE)
+ adapter->flags |= IAVF_FLAG_FDIR_ENABLED;
+ else
+ iavf_disable_fdir(adapter);
+ }
+
return 0;
}
features = iavf_fix_netdev_vlan_features(adapter, features);
+ if (!FDIR_FLTR_SUPPORT(adapter))
+ features &= ~NETIF_F_NTUPLE;
+
return iavf_fix_strip_features(adapter, features);
}
if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ if (FDIR_FLTR_SUPPORT(adapter)) {
+ netdev->hw_features |= NETIF_F_NTUPLE;
+ netdev->features |= NETIF_F_NTUPLE;
+ adapter->flags |= IAVF_FLAG_FDIR_ENABLED;
+ }
+
netdev->priv_flags |= IFF_UNICAST_FLT;
/* Do not turn on offloads when they are requested to be turned off.
return 0;
}
-/**
- * iavf_shutdown - Shutdown the device in preparation for a reboot
- * @pdev: pci device structure
- **/
-static void iavf_shutdown(struct pci_dev *pdev)
-{
- struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
- struct net_device *netdev = adapter->netdev;
-
- netif_device_detach(netdev);
-
- if (netif_running(netdev))
- iavf_close(netdev);
-
- if (iavf_lock_timeout(&adapter->crit_lock, 5000))
- dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__);
- /* Prevent the watchdog from running. */
- iavf_change_state(adapter, __IAVF_REMOVE);
- adapter->aq_required = 0;
- mutex_unlock(&adapter->crit_lock);
-
-#ifdef CONFIG_PM
- pci_save_state(pdev);
-
-#endif
- pci_disable_device(pdev);
-}
-
/**
* iavf_probe - Device Initialization Routine
* @pdev: PCI device information struct
**/
static void iavf_remove(struct pci_dev *pdev)
{
- struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
struct iavf_fdir_fltr *fdir, *fdirtmp;
struct iavf_vlan_filter *vlf, *vlftmp;
struct iavf_cloud_filter *cf, *cftmp;
struct iavf_adv_rss *rss, *rsstmp;
struct iavf_mac_filter *f, *ftmp;
+ struct iavf_adapter *adapter;
struct net_device *netdev;
struct iavf_hw *hw;
- netdev = adapter->netdev;
+ /* Don't proceed with remove if netdev is already freed */
+ netdev = pci_get_drvdata(pdev);
+ if (!netdev)
+ return;
+
+ adapter = iavf_pdev_to_adapter(pdev);
hw = &adapter->hw;
if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
destroy_workqueue(adapter->wq);
+ pci_set_drvdata(pdev, NULL);
+
free_netdev(netdev);
pci_disable_device(pdev);
}
+/**
+ * iavf_shutdown - Shutdown the device in preparation for a reboot
+ * @pdev: pci device structure
+ **/
+static void iavf_shutdown(struct pci_dev *pdev)
+{
+ iavf_remove(pdev);
+
+ if (system_state == SYSTEM_POWER_OFF)
+ pci_set_power_state(pdev, PCI_D3hot);
+}
+
static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume);
static struct pci_driver iavf_driver = {
**/
void iavf_del_fdir_filter(struct iavf_adapter *adapter)
{
+ struct virtchnl_fdir_del f = {};
struct iavf_fdir_fltr *fdir;
- struct virtchnl_fdir_del f;
bool process_fltr = false;
int len;
list_for_each_entry(fdir, &adapter->fdir_list_head, list) {
if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) {
process_fltr = true;
- memset(&f, 0, len);
f.vsi_id = fdir->vc_add_msg.vsi_id;
f.flow_id = fdir->flow_id;
fdir->state = IAVF_FDIR_FLTR_DEL_PENDING;
break;
+ } else if (fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST) {
+ process_fltr = true;
+ f.vsi_id = fdir->vc_add_msg.vsi_id;
+ f.flow_id = fdir->flow_id;
+ fdir->state = IAVF_FDIR_FLTR_DIS_PENDING;
+ break;
}
}
spin_unlock_bh(&adapter->fdir_fltr_lock);
netdev->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
}
+/**
+ * iavf_activate_fdir_filters - Reactivate all FDIR filters after a reset
+ * @adapter: private adapter structure
+ *
+ * Called after a reset to re-add all FDIR filters and delete some of them
+ * if they were pending to be deleted.
+ */
+static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
+{
+ struct iavf_fdir_fltr *f, *ftmp;
+ bool add_filters = false;
+
+ spin_lock_bh(&adapter->fdir_fltr_lock);
+ list_for_each_entry_safe(f, ftmp, &adapter->fdir_list_head, list) {
+ if (f->state == IAVF_FDIR_FLTR_ADD_REQUEST ||
+ f->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+ f->state == IAVF_FDIR_FLTR_ACTIVE) {
+ /* All filters and requests have been removed in PF,
+ * restore them
+ */
+ f->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+ add_filters = true;
+ } else if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
+ f->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+ /* Link down state, leave filters as inactive */
+ f->state = IAVF_FDIR_FLTR_INACTIVE;
+ } else if (f->state == IAVF_FDIR_FLTR_DEL_REQUEST ||
+ f->state == IAVF_FDIR_FLTR_DEL_PENDING) {
+ /* Delete filters that were pending to be deleted, the
+ * list on PF is already cleared after a reset
+ */
+ list_del(&f->list);
+ kfree(f);
+ adapter->fdir_active_fltr--;
+ }
+ }
+ spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+ if (add_filters)
+ adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+}
+
/**
* iavf_virtchnl_completion
* @adapter: adapter structure
spin_lock_bh(&adapter->fdir_fltr_lock);
list_for_each_entry(fdir, &adapter->fdir_list_head,
list) {
- if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) {
+ if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING ||
+ fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
fdir->state = IAVF_FDIR_FLTR_ACTIVE;
dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n",
iavf_stat_str(&adapter->hw,
spin_unlock_bh(&adapter->mac_vlan_list_lock);
+ iavf_activate_fdir_filters(adapter);
+
iavf_parse_vf_resource_msg(adapter);
/* negotiated VIRTCHNL_VF_OFFLOAD_VLAN_V2, so wait for the
list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head,
list) {
if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) {
- if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) {
+ if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
+ del_fltr->status ==
+ VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n",
fdir->loc);
list_del(&fdir->list);
del_fltr->status);
iavf_print_fdir_fltr(adapter, fdir);
}
+ } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+ if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
+ del_fltr->status ==
+ VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
+ fdir->state = IAVF_FDIR_FLTR_INACTIVE;
+ } else {
+ fdir->state = IAVF_FDIR_FLTR_ACTIVE;
+ dev_info(&adapter->pdev->dev, "Failed to disable Flow Director filter with status: %d\n",
+ del_fltr->status);
+ iavf_print_fdir_fltr(adapter, fdir);
+ }
}
}
spin_unlock_bh(&adapter->fdir_fltr_lock);
if (ret)
return ret;
+ INIT_WORK(&oct->tx_timeout_task, octep_tx_timeout_task);
+ INIT_WORK(&oct->ctrl_mbox_task, octep_ctrl_mbox_task);
+ INIT_DELAYED_WORK(&oct->intr_poll_task, octep_intr_poll_task);
+ oct->poll_non_ioq_intr = true;
+ queue_delayed_work(octep_wq, &oct->intr_poll_task,
+ msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
+
atomic_set(&oct->hb_miss_cnt, 0);
INIT_DELAYED_WORK(&oct->hb_task, octep_hb_timeout_task);
pci_read_config_byte(pdev, (pos + 8), &status);
dev_info(&pdev->dev, "Firmware ready status = %u\n", status);
- return status;
+#define FW_STATUS_READY 1ULL
+ return status == FW_STATUS_READY;
}
return false;
}
goto err_octep_config;
}
- octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
- &octep_dev->conf->fw_info);
+ err = octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
+ &octep_dev->conf->fw_info);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to get firmware info\n");
+ goto register_dev_err;
+ }
dev_info(&octep_dev->pdev->dev, "Heartbeat interval %u msecs Heartbeat miss count %u\n",
octep_dev->conf->fw_info.hb_interval,
octep_dev->conf->fw_info.hb_miss_count);
queue_delayed_work(octep_wq, &octep_dev->hb_task,
msecs_to_jiffies(octep_dev->conf->fw_info.hb_interval));
- INIT_WORK(&octep_dev->tx_timeout_task, octep_tx_timeout_task);
- INIT_WORK(&octep_dev->ctrl_mbox_task, octep_ctrl_mbox_task);
- INIT_DELAYED_WORK(&octep_dev->intr_poll_task, octep_intr_poll_task);
- octep_dev->poll_non_ioq_intr = true;
- queue_delayed_work(octep_wq, &octep_dev->intr_poll_task,
- msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
-
netdev->netdev_ops = &octep_netdev_ops;
octep_set_ethtool_ops(netdev);
netif_carrier_off(netdev);
cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE;
rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
+ /* Disable forward pause to driver */
+ cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
+ cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD;
+ rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
+
/* Enable channel mask for all LMACS */
if (is_dev_rpm2(rpm))
rpm_write(rpm, lmac_id, RPM2_CMR_CHAN_MSK_OR, 0xffff);
if (rx_pause) {
cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
- RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE |
- RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD);
+ RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE);
} else {
cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
- RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE |
- RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD);
+ RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE);
}
if (tx_pause) {
rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq");
if (!rvu_dl->devlink_wq)
- goto err;
+ return -ENOMEM;
INIT_WORK(&rvu_reporters->intr_work, rvu_nix_intr_work);
INIT_WORK(&rvu_reporters->gen_work, rvu_nix_gen_work);
INIT_WORK(&rvu_reporters->ras_work, rvu_nix_ras_work);
return 0;
-err:
- rvu_nix_health_reporters_destroy(rvu_dl);
- return -ENOMEM;
}
static int rvu_nix_health_reporters_create(struct rvu_devlink *rvu_dl)
int blkaddr, ucast_idx, index;
struct nix_rx_action action = { 0 };
u64 relaxed_mask;
+ u8 flow_key_alg;
if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc))
return;
action.op = NIX_RX_ACTIONOP_UCAST;
}
+ flow_key_alg = action.flow_key_alg;
+
/* RX_ACTION set to MCAST for CGX PF's */
if (hw->cap.nix_rx_multicast && pfvf->use_mce_list &&
is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
req.vf = pcifunc;
req.index = action.index;
req.match_id = action.match_id;
- req.flow_key_alg = action.flow_key_alg;
+ req.flow_key_alg = flow_key_alg;
rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
}
u8 mac_addr[ETH_ALEN] = { 0 };
struct nix_rx_action action = { 0 };
struct rvu_pfvf *pfvf;
+ u8 flow_key_alg;
u16 vf_func;
/* Only CGX PF/VF can add allmulticast entry */
*(u64 *)&action = npc_get_mcam_action(rvu, mcam,
blkaddr, ucast_idx);
+ flow_key_alg = action.flow_key_alg;
if (action.op != NIX_RX_ACTIONOP_RSS) {
*(u64 *)&action = 0;
action.op = NIX_RX_ACTIONOP_UCAST;
req.vf = pcifunc | vf_func;
req.index = action.index;
req.match_id = action.match_id;
- req.flow_key_alg = action.flow_key_alg;
+ req.flow_key_alg = flow_key_alg;
rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
}
mutex_unlock(&mcam->lock);
}
+static void npc_update_rx_action_with_alg_idx(struct rvu *rvu, struct nix_rx_action action,
+ struct rvu_pfvf *pfvf, int mcam_index, int blkaddr,
+ int alg_idx)
+
+{
+ struct npc_mcam *mcam = &rvu->hw->mcam;
+ struct rvu_hwinfo *hw = rvu->hw;
+ int bank, op_rss;
+
+ if (!is_mcam_entry_enabled(rvu, mcam, blkaddr, mcam_index))
+ return;
+
+ op_rss = (!hw->cap.nix_rx_multicast || !pfvf->use_mce_list);
+
+ bank = npc_get_bank(mcam, mcam_index);
+ mcam_index &= (mcam->banksize - 1);
+
+ /* If Rx action is MCAST update only RSS algorithm index */
+ if (!op_rss) {
+ *(u64 *)&action = rvu_read64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank));
+
+ action.flow_key_alg = alg_idx;
+ }
+ rvu_write64(rvu, blkaddr,
+ NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank), *(u64 *)&action);
+}
+
void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
int group, int alg_idx, int mcam_index)
{
struct npc_mcam *mcam = &rvu->hw->mcam;
- struct rvu_hwinfo *hw = rvu->hw;
struct nix_rx_action action;
int blkaddr, index, bank;
struct rvu_pfvf *pfvf;
/* If PF's promiscuous entry is enabled,
* Set RSS action for that entry as well
*/
- if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) &&
- is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) {
- bank = npc_get_bank(mcam, index);
- index &= (mcam->banksize - 1);
+ npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
+ alg_idx);
- rvu_write64(rvu, blkaddr,
- NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
- *(u64 *)&action);
- }
+ index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+ nixlf, NIXLF_ALLMULTI_ENTRY);
+ /* If PF's allmulti entry is enabled,
+ * Set RSS action for that entry as well
+ */
+ npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
+ alg_idx);
}
void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
mutex_unlock(&mbox->lock);
}
+static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf)
+{
+ int vf;
+
+ /* The AF driver will determine whether to allow the VF netdev or not */
+ if (is_otx2_vf(pfvf->pcifunc))
+ return true;
+
+ /* check if there are any trusted VFs associated with the PF netdev */
+ for (vf = 0; vf < pci_num_vf(pfvf->pdev); vf++)
+ if (pfvf->vf_configs[vf].trusted)
+ return true;
+ return false;
+}
+
static void otx2_do_set_rx_mode(struct otx2_nic *pf)
{
struct net_device *netdev = pf->netdev;
if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST))
req->mode |= NIX_RX_MODE_ALLMULTI;
- req->mode |= NIX_RX_MODE_USE_MCE;
+ if (otx2_promisc_use_mce_list(pf))
+ req->mode |= NIX_RX_MODE_USE_MCE;
otx2_sync_mbox_msg(&pf->mbox);
mutex_unlock(&pf->mbox.lock);
pf->vf_configs[vf].trusted = enable;
rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF);
- if (rc)
+ if (rc) {
pf->vf_configs[vf].trusted = !enable;
- else
+ } else {
netdev_info(pf->netdev, "VF %d is %strusted\n",
vf, enable ? "" : "not ");
+ otx2_set_rx_mode(netdev);
+ }
+
return rc;
}
MLX5E_STATE_DESTROYING,
MLX5E_STATE_XDP_TX_ENABLED,
MLX5E_STATE_XDP_ACTIVE,
+ MLX5E_STATE_CHANNELS_ACTIVE,
};
struct mlx5e_modify_sq_param {
struct mlx5_flow_spec *spec;
int err;
+ if (IS_ERR(post_act))
+ return PTR_ERR(post_act);
+
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
if (!spec)
return -ENOMEM;
struct mlx5e_post_act_handle *handle;
int err;
+ if (IS_ERR(post_act))
+ return ERR_CAST(post_act);
+
handle = kzalloc(sizeof(*handle), GFP_KERNEL);
if (!handle)
return ERR_PTR(-ENOMEM);
if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO)
esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom));
- sa_entry->esn_state.esn = esn;
+ if (sa_entry->esn_state.esn_msb)
+ sa_entry->esn_state.esn = esn;
+ else
+ /* According to RFC4303, section "3.3.3. Sequence Number Generation",
+ * the first packet sent using a given SA will contain a sequence
+ * number of 1.
+ */
+ sa_entry->esn_state.esn = max_t(u32, esn, 1);
sa_entry->esn_state.esn_msb = esn_msb;
if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) {
attrs->replay_esn.esn = sa_entry->esn_state.esn;
attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb;
attrs->replay_esn.overlap = sa_entry->esn_state.overlap;
+ switch (x->replay_esn->replay_window) {
+ case 32:
+ attrs->replay_esn.replay_window =
+ MLX5_IPSEC_ASO_REPLAY_WIN_32BIT;
+ break;
+ case 64:
+ attrs->replay_esn.replay_window =
+ MLX5_IPSEC_ASO_REPLAY_WIN_64BIT;
+ break;
+ case 128:
+ attrs->replay_esn.replay_window =
+ MLX5_IPSEC_ASO_REPLAY_WIN_128BIT;
+ break;
+ case 256:
+ attrs->replay_esn.replay_window =
+ MLX5_IPSEC_ASO_REPLAY_WIN_256BIT;
+ break;
+ default:
+ WARN_ON(true);
+ return;
+ }
}
attrs->dir = x->xso.dir;
return;
mlx5e_accel_ipsec_fs_cleanup(ipsec);
- if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_TUNNEL)
+ if (ipsec->netevent_nb.notifier_call) {
unregister_netevent_notifier(&ipsec->netevent_nb);
- if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)
+ ipsec->netevent_nb.notifier_call = NULL;
+ }
+ if (ipsec->aso)
mlx5e_ipsec_aso_cleanup(ipsec);
destroy_workqueue(ipsec->wq);
kfree(ipsec);
}
}
+ if (x->xdo.type == XFRM_DEV_OFFLOAD_PACKET &&
+ !(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)) {
+ NL_SET_ERR_MSG_MOD(extack, "Packet offload is not supported");
+ return -EINVAL;
+ }
+
return 0;
}
.xdo_dev_state_free = mlx5e_xfrm_free_state,
.xdo_dev_offload_ok = mlx5e_ipsec_offload_ok,
.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
-};
-
-static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = {
- .xdo_dev_state_add = mlx5e_xfrm_add_state,
- .xdo_dev_state_delete = mlx5e_xfrm_del_state,
- .xdo_dev_state_free = mlx5e_xfrm_free_state,
- .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok,
- .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
.xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft,
.xdo_dev_policy_add = mlx5e_xfrm_add_policy,
mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n");
- if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)
- netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops;
- else
- netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops;
-
+ netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops;
netdev->features |= NETIF_F_HW_ESP;
netdev->hw_enc_features |= NETIF_F_HW_ESP;
u32 refcnt;
};
+struct mlx5e_ipsec_drop {
+ struct mlx5_flow_handle *rule;
+ struct mlx5_fc *fc;
+};
+
struct mlx5e_ipsec_rule {
struct mlx5_flow_handle *rule;
struct mlx5_modify_hdr *modify_hdr;
struct mlx5_pkt_reformat *pkt_reformat;
struct mlx5_fc *fc;
+ struct mlx5e_ipsec_drop replay;
+ struct mlx5e_ipsec_drop auth;
+ struct mlx5e_ipsec_drop trailer;
};
struct mlx5e_ipsec_miss {
struct mlx5_flow_handle *rule;
};
-struct mlx5e_ipsec_rx {
- struct mlx5e_ipsec_ft ft;
- struct mlx5e_ipsec_miss pol;
- struct mlx5e_ipsec_miss sa;
- struct mlx5e_ipsec_rule status;
- struct mlx5e_ipsec_miss status_drop;
- struct mlx5_fc *status_drop_cnt;
- struct mlx5e_ipsec_fc *fc;
- struct mlx5_fs_chains *chains;
- u8 allow_tunnel_mode : 1;
- struct xarray ipsec_obj_id_map;
-};
-
struct mlx5e_ipsec_tx_create_attr {
int prio;
int pol_level;
struct mlx5_ipsec_fs *roce;
u8 is_uplink_rep: 1;
struct mlx5e_ipsec_mpv_work mpv_work;
+ struct xarray ipsec_obj_id_map;
};
struct mlx5e_ipsec_esn_state {
u8 allow_tunnel_mode : 1;
};
+struct mlx5e_ipsec_status_checks {
+ struct mlx5_flow_group *drop_all_group;
+ struct mlx5e_ipsec_drop all;
+};
+
+struct mlx5e_ipsec_rx {
+ struct mlx5e_ipsec_ft ft;
+ struct mlx5e_ipsec_miss pol;
+ struct mlx5e_ipsec_miss sa;
+ struct mlx5e_ipsec_rule status;
+ struct mlx5e_ipsec_status_checks status_drops;
+ struct mlx5e_ipsec_fc *fc;
+ struct mlx5_fs_chains *chains;
+ u8 allow_tunnel_mode : 1;
+};
+
/* IPsec RX flow steering */
static enum mlx5_traffic_types family2tt(u32 family)
{
return mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
}
-static int ipsec_status_rule(struct mlx5_core_dev *mdev,
- struct mlx5e_ipsec_rx *rx,
- struct mlx5_flow_destination *dest)
+static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
+ struct mlx5e_ipsec_rx *rx)
+{
+ mlx5_del_flow_rules(rx->status_drops.all.rule);
+ mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc);
+ mlx5_destroy_flow_group(rx->status_drops.drop_all_group);
+}
+
+static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
+ struct mlx5e_ipsec_rx *rx)
{
- u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+ mlx5_del_flow_rules(rx->status.rule);
+
+ if (rx != ipsec->rx_esw)
+ return;
+
+#ifdef CONFIG_MLX5_ESWITCH
+ mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
+#endif
+}
+
+static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
+ struct mlx5e_ipsec_rx *rx)
+{
+ struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+ struct mlx5_flow_table *ft = rx->ft.status;
+ struct mlx5_core_dev *mdev = ipsec->mdev;
+ struct mlx5_flow_destination dest = {};
struct mlx5_flow_act flow_act = {};
- struct mlx5_modify_hdr *modify_hdr;
- struct mlx5_flow_handle *fte;
+ struct mlx5_flow_handle *rule;
+ struct mlx5_fc *flow_counter;
struct mlx5_flow_spec *spec;
int err;
if (!spec)
return -ENOMEM;
- /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */
- MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
- MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME);
- MLX5_SET(copy_action_in, action, src_offset, 0);
- MLX5_SET(copy_action_in, action, length, 7);
- MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
- MLX5_SET(copy_action_in, action, dst_offset, 24);
+ flow_counter = mlx5_fc_create(mdev, true);
+ if (IS_ERR(flow_counter)) {
+ err = PTR_ERR(flow_counter);
+ mlx5_core_err(mdev,
+ "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+ goto err_cnt;
+ }
+ sa_entry->ipsec_rule.auth.fc = flow_counter;
- modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
- 1, action);
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ flow_act.flags = FLOW_ACT_NO_APPEND;
+ dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+ dest.counter_id = mlx5_fc_id(flow_counter);
+ if (rx == ipsec->rx_esw)
+ spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
- if (IS_ERR(modify_hdr)) {
- err = PTR_ERR(modify_hdr);
+ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome);
+ MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1);
+ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
+ MLX5_SET(fte_match_param, spec->match_value,
+ misc_parameters_2.metadata_reg_c_2,
+ sa_entry->ipsec_obj_id | BIT(31));
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+ rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+ if (IS_ERR(rule)) {
+ err = PTR_ERR(rule);
mlx5_core_err(mdev,
- "fail to alloc ipsec copy modify_header_id err=%d\n", err);
- goto out_spec;
+ "Failed to add ipsec rx status drop rule, err=%d\n", err);
+ goto err_rule;
}
+ sa_entry->ipsec_rule.auth.rule = rule;
- /* create fte */
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ flow_counter = mlx5_fc_create(mdev, true);
+ if (IS_ERR(flow_counter)) {
+ err = PTR_ERR(flow_counter);
+ mlx5_core_err(mdev,
+ "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+ goto err_cnt_2;
+ }
+ sa_entry->ipsec_rule.trailer.fc = flow_counter;
+
+ dest.counter_id = mlx5_fc_id(flow_counter);
+ MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2);
+ rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+ if (IS_ERR(rule)) {
+ err = PTR_ERR(rule);
+ mlx5_core_err(mdev,
+ "Failed to add ipsec rx status drop rule, err=%d\n", err);
+ goto err_rule_2;
+ }
+ sa_entry->ipsec_rule.trailer.rule = rule;
+
+ kvfree(spec);
+ return 0;
+
+err_rule_2:
+ mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.trailer.fc);
+err_cnt_2:
+ mlx5_del_flow_rules(sa_entry->ipsec_rule.auth.rule);
+err_rule:
+ mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.auth.fc);
+err_cnt:
+ kvfree(spec);
+ return err;
+}
+
+static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_ipsec_rx *rx)
+{
+ struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+ struct mlx5_flow_table *ft = rx->ft.status;
+ struct mlx5_core_dev *mdev = ipsec->mdev;
+ struct mlx5_flow_destination dest = {};
+ struct mlx5_flow_act flow_act = {};
+ struct mlx5_flow_handle *rule;
+ struct mlx5_fc *flow_counter;
+ struct mlx5_flow_spec *spec;
+ int err;
+
+ spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+ if (!spec)
+ return -ENOMEM;
+
+ flow_counter = mlx5_fc_create(mdev, true);
+ if (IS_ERR(flow_counter)) {
+ err = PTR_ERR(flow_counter);
+ mlx5_core_err(mdev,
+ "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+ goto err_cnt;
+ }
+
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ flow_act.flags = FLOW_ACT_NO_APPEND;
+ dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+ dest.counter_id = mlx5_fc_id(flow_counter);
+ if (rx == ipsec->rx_esw)
+ spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+
+ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4);
+ MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1);
+ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
+ MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_2,
+ sa_entry->ipsec_obj_id | BIT(31));
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+ rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+ if (IS_ERR(rule)) {
+ err = PTR_ERR(rule);
+ mlx5_core_err(mdev,
+ "Failed to add ipsec rx status drop rule, err=%d\n", err);
+ goto err_rule;
+ }
+
+ sa_entry->ipsec_rule.replay.rule = rule;
+ sa_entry->ipsec_rule.replay.fc = flow_counter;
+
+ kvfree(spec);
+ return 0;
+
+err_rule:
+ mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+ kvfree(spec);
+ return err;
+}
+
+static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
+ struct mlx5e_ipsec_rx *rx)
+{
+ int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+ struct mlx5_flow_table *ft = rx->ft.status;
+ struct mlx5_core_dev *mdev = ipsec->mdev;
+ struct mlx5_flow_destination dest = {};
+ struct mlx5_flow_act flow_act = {};
+ struct mlx5_flow_handle *rule;
+ struct mlx5_fc *flow_counter;
+ struct mlx5_flow_spec *spec;
+ struct mlx5_flow_group *g;
+ u32 *flow_group_in;
+ int err = 0;
+
+ flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+ spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+ if (!flow_group_in || !spec) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
+ MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
+ g = mlx5_create_flow_group(ft, flow_group_in);
+ if (IS_ERR(g)) {
+ err = PTR_ERR(g);
+ mlx5_core_err(mdev,
+ "Failed to add ipsec rx status drop flow group, err=%d\n", err);
+ goto err_out;
+ }
+
+ flow_counter = mlx5_fc_create(mdev, false);
+ if (IS_ERR(flow_counter)) {
+ err = PTR_ERR(flow_counter);
+ mlx5_core_err(mdev,
+ "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+ goto err_cnt;
+ }
+
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+ dest.counter_id = mlx5_fc_id(flow_counter);
+ if (rx == ipsec->rx_esw)
+ spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+ rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+ if (IS_ERR(rule)) {
+ err = PTR_ERR(rule);
+ mlx5_core_err(mdev,
+ "Failed to add ipsec rx status drop rule, err=%d\n", err);
+ goto err_rule;
+ }
+
+ rx->status_drops.drop_all_group = g;
+ rx->status_drops.all.rule = rule;
+ rx->status_drops.all.fc = flow_counter;
+
+ kvfree(flow_group_in);
+ kvfree(spec);
+ return 0;
+
+err_rule:
+ mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+ mlx5_destroy_flow_group(g);
+err_out:
+ kvfree(flow_group_in);
+ kvfree(spec);
+ return err;
+}
+
+static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
+ struct mlx5e_ipsec_rx *rx,
+ struct mlx5_flow_destination *dest)
+{
+ struct mlx5_flow_act flow_act = {};
+ struct mlx5_flow_handle *rule;
+ struct mlx5_flow_spec *spec;
+ int err;
+
+ spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+ if (!spec)
+ return -ENOMEM;
+
+ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+ misc_parameters_2.ipsec_syndrome);
+ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+ misc_parameters_2.metadata_reg_c_4);
+ MLX5_SET(fte_match_param, spec->match_value,
+ misc_parameters_2.ipsec_syndrome, 0);
+ MLX5_SET(fte_match_param, spec->match_value,
+ misc_parameters_2.metadata_reg_c_4, 0);
+ if (rx == ipsec->rx_esw)
+ spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+ flow_act.flags = FLOW_ACT_NO_APPEND;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
MLX5_FLOW_CONTEXT_ACTION_COUNT;
- flow_act.modify_hdr = modify_hdr;
- fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
- if (IS_ERR(fte)) {
- err = PTR_ERR(fte);
- mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err);
- goto out;
+ rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
+ if (IS_ERR(rule)) {
+ err = PTR_ERR(rule);
+ mlx5_core_warn(ipsec->mdev,
+ "Failed to add ipsec rx status pass rule, err=%d\n", err);
+ goto err_rule;
}
+ rx->status.rule = rule;
kvfree(spec);
- rx->status.rule = fte;
- rx->status.modify_hdr = modify_hdr;
return 0;
-out:
- mlx5_modify_header_dealloc(mdev, modify_hdr);
-out_spec:
+err_rule:
kvfree(spec);
return err;
}
+static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+ struct mlx5e_ipsec_rx *rx)
+{
+ ipsec_rx_status_pass_destroy(ipsec, rx);
+ ipsec_rx_status_drop_destroy(ipsec, rx);
+}
+
+static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+ struct mlx5e_ipsec_rx *rx,
+ struct mlx5_flow_destination *dest)
+{
+ int err;
+
+ err = ipsec_rx_status_drop_all_create(ipsec, rx);
+ if (err)
+ return err;
+
+ err = ipsec_rx_status_pass_create(ipsec, rx, dest);
+ if (err)
+ goto err_pass_create;
+
+ return 0;
+
+err_pass_create:
+ ipsec_rx_status_drop_destroy(ipsec, rx);
+ return err;
+}
+
static int ipsec_miss_create(struct mlx5_core_dev *mdev,
struct mlx5_flow_table *ft,
struct mlx5e_ipsec_miss *miss,
mlx5_destroy_flow_table(rx->ft.sa);
if (rx->allow_tunnel_mode)
mlx5_eswitch_unblock_encap(mdev);
- if (rx == ipsec->rx_esw) {
- mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
- } else {
- mlx5_del_flow_rules(rx->status.rule);
- mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
- }
+ mlx5_ipsec_rx_status_destroy(ipsec, rx);
mlx5_destroy_flow_table(rx->ft.status);
mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
if (err)
return err;
- ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 0);
+ ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0);
if (IS_ERR(ft)) {
err = PTR_ERR(ft);
goto err_fs_ft_status;
dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
- if (rx == ipsec->rx_esw)
- err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest);
- else
- err = ipsec_status_rule(mdev, rx, dest);
+ err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
if (err)
goto err_add;
MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP);
}
-static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi)
+static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap)
{
/* SPI number */
spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
- MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi);
- MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi);
+ if (encap) {
+ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+ misc_parameters.inner_esp_spi);
+ MLX5_SET(fte_match_param, spec->match_value,
+ misc_parameters.inner_esp_spi, spi);
+ } else {
+ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+ misc_parameters.outer_esp_spi);
+ MLX5_SET(fte_match_param, spec->match_value,
+ misc_parameters.outer_esp_spi, spi);
+ }
}
static void setup_fte_no_frags(struct mlx5_flow_spec *spec)
struct mlx5_flow_act *flow_act)
{
enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir);
- u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+ u8 action[3][MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
struct mlx5_core_dev *mdev = ipsec->mdev;
struct mlx5_modify_hdr *modify_hdr;
+ u8 num_of_actions = 1;
- MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+ MLX5_SET(set_action_in, action[0], action_type, MLX5_ACTION_TYPE_SET);
switch (dir) {
case XFRM_DEV_OFFLOAD_IN:
- MLX5_SET(set_action_in, action, field,
+ MLX5_SET(set_action_in, action[0], field,
MLX5_ACTION_IN_FIELD_METADATA_REG_B);
+
+ num_of_actions++;
+ MLX5_SET(set_action_in, action[1], action_type, MLX5_ACTION_TYPE_SET);
+ MLX5_SET(set_action_in, action[1], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_2);
+ MLX5_SET(set_action_in, action[1], data, val);
+ MLX5_SET(set_action_in, action[1], offset, 0);
+ MLX5_SET(set_action_in, action[1], length, 32);
+
+ if (type == XFRM_DEV_OFFLOAD_CRYPTO) {
+ num_of_actions++;
+ MLX5_SET(set_action_in, action[2], action_type,
+ MLX5_ACTION_TYPE_SET);
+ MLX5_SET(set_action_in, action[2], field,
+ MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
+ MLX5_SET(set_action_in, action[2], data, 0);
+ MLX5_SET(set_action_in, action[2], offset, 0);
+ MLX5_SET(set_action_in, action[2], length, 32);
+ }
break;
case XFRM_DEV_OFFLOAD_OUT:
- MLX5_SET(set_action_in, action, field,
+ MLX5_SET(set_action_in, action[0], field,
MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
break;
default:
return -EINVAL;
}
- MLX5_SET(set_action_in, action, data, val);
- MLX5_SET(set_action_in, action, offset, 0);
- MLX5_SET(set_action_in, action, length, 32);
+ MLX5_SET(set_action_in, action[0], data, val);
+ MLX5_SET(set_action_in, action[0], offset, 0);
+ MLX5_SET(set_action_in, action[0], length, 32);
- modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, 1, action);
+ modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, num_of_actions, action);
if (IS_ERR(modify_hdr)) {
mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n",
PTR_ERR(modify_hdr));
else
setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
- setup_fte_spi(spec, attrs->spi);
- setup_fte_esp(spec);
+ setup_fte_spi(spec, attrs->spi, attrs->encap);
+ if (!attrs->encap)
+ setup_fte_esp(spec);
setup_fte_no_frags(spec);
setup_fte_upper_proto_match(spec, &attrs->upspec);
mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err);
goto err_add_flow;
}
+ if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
+ err = rx_add_rule_drop_replay(sa_entry, rx);
+ if (err)
+ goto err_add_replay;
+
+ err = rx_add_rule_drop_auth_trailer(sa_entry, rx);
+ if (err)
+ goto err_drop_reason;
+
kvfree(spec);
sa_entry->ipsec_rule.rule = rule;
sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat;
return 0;
+err_drop_reason:
+ if (sa_entry->ipsec_rule.replay.rule) {
+ mlx5_del_flow_rules(sa_entry->ipsec_rule.replay.rule);
+ mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc);
+ }
+err_add_replay:
+ mlx5_del_flow_rules(rule);
err_add_flow:
mlx5_fc_destroy(mdev, counter);
err_add_cnt:
switch (attrs->type) {
case XFRM_DEV_OFFLOAD_CRYPTO:
- setup_fte_spi(spec, attrs->spi);
+ setup_fte_spi(spec, attrs->spi, false);
setup_fte_esp(spec);
setup_fte_reg_a(spec);
break;
struct mlx5_eswitch *esw = mdev->priv.eswitch;
int err = 0;
- if (esw)
- down_write(&esw->mode_lock);
+ if (esw) {
+ err = mlx5_esw_lock(esw);
+ if (err)
+ return err;
+ }
if (mdev->num_block_ipsec) {
err = -EBUSY;
unlock:
if (esw)
- up_write(&esw->mode_lock);
+ mlx5_esw_unlock(esw);
return err;
}
if (ipsec_rule->modify_hdr)
mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
+
+ mlx5_del_flow_rules(ipsec_rule->trailer.rule);
+ mlx5_fc_destroy(mdev, ipsec_rule->trailer.fc);
+
+ mlx5_del_flow_rules(ipsec_rule->auth.rule);
+ mlx5_fc_destroy(mdev, ipsec_rule->auth.fc);
+
+ if (ipsec_rule->replay.rule) {
+ mlx5_del_flow_rules(ipsec_rule->replay.rule);
+ mlx5_fc_destroy(mdev, ipsec_rule->replay.fc);
+ }
mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
}
kfree(ipsec->rx_ipv6);
if (ipsec->is_uplink_rep) {
- xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map);
+ xa_destroy(&ipsec->ipsec_obj_id_map);
mutex_destroy(&ipsec->tx_esw->ft.mutex);
WARN_ON(ipsec->tx_esw->ft.refcnt);
mutex_init(&ipsec->tx_esw->ft.mutex);
mutex_init(&ipsec->rx_esw->ft.mutex);
ipsec->tx_esw->ns = ns_esw;
- xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
+ xa_init_flags(&ipsec->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
} else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) {
ipsec->roce = mlx5_ipsec_fs_roce_init(mdev, devcom);
} else {
#include "ipsec.h"
#include "lib/crypto.h"
#include "lib/ipsec_fs_roce.h"
+#include "fs_core.h"
+#include "eswitch.h"
enum {
MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET,
MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp))
caps |= MLX5_IPSEC_CAP_CRYPTO;
- if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload)) {
+ if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) &&
+ (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS ||
+ (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS &&
+ is_mdev_legacy_mode(mdev)))) {
if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
reformat_add_esp_trasport) &&
MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
if (attrs->dir == XFRM_DEV_OFFLOAD_IN) {
MLX5_SET(ipsec_aso, aso_ctx, window_sz,
- attrs->replay_esn.replay_window / 64);
+ attrs->replay_esn.replay_window);
MLX5_SET(ipsec_aso, aso_ctx, mode,
MLX5_IPSEC_ASO_REPLAY_PROTECTION);
}
dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx),
DMA_BIDIRECTIONAL);
kfree(aso);
+ ipsec->aso = NULL;
}
static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl,
{
int i;
+ ASSERT_RTNL();
if (chs->ptp) {
mlx5e_ptp_close(chs->ptp);
chs->ptp = NULL;
if (mlx5e_is_vport_rep(priv))
mlx5e_rep_activate_channels(priv);
+ set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+
mlx5e_wait_channels_min_rx_wqes(&priv->channels);
if (priv->rx_res)
mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels);
}
+static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv)
+{
+ WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state));
+ if (current_work() != &priv->tx_timeout_work)
+ cancel_work_sync(&priv->tx_timeout_work);
+}
+
void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
{
if (priv->rx_res)
mlx5e_rx_res_channels_deactivate(priv->rx_res);
+ clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+ mlx5e_cancel_tx_timeout_work(priv);
+
if (mlx5e_is_vport_rep(priv))
mlx5e_rep_deactivate_channels(priv);
struct net_device *netdev = priv->netdev;
int i;
- rtnl_lock();
- mutex_lock(&priv->state_lock);
+ /* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues
+ * through this flow. However, channel closing flows have to wait for
+ * this work to finish while holding rtnl lock too. So either get the
+ * lock or find that channels are being closed for other reason and
+ * this work is not relevant anymore.
+ */
+ while (!rtnl_trylock()) {
+ if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
+ return;
+ msleep(20);
+ }
if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
goto unlock;
}
unlock:
- mutex_unlock(&priv->state_lock);
rtnl_unlock();
}
dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch,
rpriv->rep->vport);
- if (dl_port) {
+ if (!IS_ERR(dl_port)) {
SET_NETDEV_DEVLINK_PORT(netdev, dl_port);
mlx5e_rep_vnic_reporter_create(priv, dl_port);
}
struct mlx5e_flow_meter_handle *meter;
enum mlx5e_post_meter_type type;
+ if (IS_ERR(post_act))
+ return PTR_ERR(post_act);
+
meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params);
if (IS_ERR(meter)) {
mlx5_core_err(priv->mdev, "Failed to get flow meter\n");
return err;
}
+static int
+set_branch_dest_ft(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr)
+{
+ struct mlx5e_post_act *post_act = get_post_action(priv);
+
+ if (IS_ERR(post_act))
+ return PTR_ERR(post_act);
+
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act);
+
+ return 0;
+}
+
static int
alloc_branch_attr(struct mlx5e_tc_flow *flow,
struct mlx5e_tc_act_branch_ctrl *cond,
break;
case FLOW_ACTION_ACCEPT:
case FLOW_ACTION_PIPE:
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv));
+ if (set_branch_dest_ft(flow->priv, attr))
+ goto out_err;
break;
case FLOW_ACTION_JUMP:
if (*jump_count) {
goto out_err;
}
*jump_count = cond->extval;
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv));
+ if (set_branch_dest_ft(flow->priv, attr))
+ goto out_err;
break;
default:
err = -EOPNOTSUPP;
MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL,
};
-static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx)
-{
- mlx5_del_flow_rules(rx->status_drop.rule);
- mlx5_destroy_flow_group(rx->status_drop.group);
- mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt);
-}
-
-static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx)
-{
- mlx5_del_flow_rules(rx->status.rule);
- mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
-}
-
-static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx)
-{
- int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
- struct mlx5_flow_table *ft = rx->ft.status;
- struct mlx5_core_dev *mdev = ipsec->mdev;
- struct mlx5_flow_destination dest = {};
- struct mlx5_flow_act flow_act = {};
- struct mlx5_flow_handle *rule;
- struct mlx5_fc *flow_counter;
- struct mlx5_flow_spec *spec;
- struct mlx5_flow_group *g;
- u32 *flow_group_in;
- int err = 0;
-
- flow_group_in = kvzalloc(inlen, GFP_KERNEL);
- spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
- if (!flow_group_in || !spec) {
- err = -ENOMEM;
- goto err_out;
- }
-
- MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
- MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
- g = mlx5_create_flow_group(ft, flow_group_in);
- if (IS_ERR(g)) {
- err = PTR_ERR(g);
- mlx5_core_err(mdev,
- "Failed to add ipsec rx status drop flow group, err=%d\n", err);
- goto err_out;
- }
-
- flow_counter = mlx5_fc_create(mdev, false);
- if (IS_ERR(flow_counter)) {
- err = PTR_ERR(flow_counter);
- mlx5_core_err(mdev,
- "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
- goto err_cnt;
- }
-
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
- dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
- dest.counter_id = mlx5_fc_id(flow_counter);
- spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
- rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
- if (IS_ERR(rule)) {
- err = PTR_ERR(rule);
- mlx5_core_err(mdev,
- "Failed to add ipsec rx status drop rule, err=%d\n", err);
- goto err_rule;
- }
-
- rx->status_drop.group = g;
- rx->status_drop.rule = rule;
- rx->status_drop_cnt = flow_counter;
-
- kvfree(flow_group_in);
- kvfree(spec);
- return 0;
-
-err_rule:
- mlx5_fc_destroy(mdev, flow_counter);
-err_cnt:
- mlx5_destroy_flow_group(g);
-err_out:
- kvfree(flow_group_in);
- kvfree(spec);
- return err;
-}
-
-static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx,
- struct mlx5_flow_destination *dest)
-{
- struct mlx5_flow_act flow_act = {};
- struct mlx5_flow_handle *rule;
- struct mlx5_flow_spec *spec;
- int err;
-
- spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
- if (!spec)
- return -ENOMEM;
-
- MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
- misc_parameters_2.ipsec_syndrome);
- MLX5_SET(fte_match_param, spec->match_value,
- misc_parameters_2.ipsec_syndrome, 0);
- spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
- flow_act.flags = FLOW_ACT_NO_APPEND;
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
- MLX5_FLOW_CONTEXT_ACTION_COUNT;
- rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
- if (IS_ERR(rule)) {
- err = PTR_ERR(rule);
- mlx5_core_warn(ipsec->mdev,
- "Failed to add ipsec rx status pass rule, err=%d\n", err);
- goto err_rule;
- }
-
- rx->status.rule = rule;
- kvfree(spec);
- return 0;
-
-err_rule:
- kvfree(spec);
- return err;
-}
-
-void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx)
-{
- esw_ipsec_rx_status_pass_destroy(ipsec, rx);
- esw_ipsec_rx_status_drop_destroy(ipsec, rx);
-}
-
-int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx,
- struct mlx5_flow_destination *dest)
-{
- int err;
-
- err = esw_ipsec_rx_status_drop_create(ipsec, rx);
- if (err)
- return err;
-
- err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest);
- if (err)
- goto err_pass_create;
-
- return 0;
-
-err_pass_create:
- esw_ipsec_rx_status_drop_destroy(ipsec, rx);
- return err;
-}
-
void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
struct mlx5e_ipsec_rx_create_attr *attr)
{
u32 mapped_id;
int err;
- err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id,
+ err = xa_alloc_bh(&ipsec->ipsec_obj_id_map, &mapped_id,
xa_mk_value(sa_entry->ipsec_obj_id),
XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0);
if (err)
return 0;
err_header_alloc:
- xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id);
+ xa_erase_bh(&ipsec->ipsec_obj_id_map, mapped_id);
return err;
}
struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
if (sa_entry->rx_mapped_id)
- xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map,
+ xa_erase_bh(&ipsec->ipsec_obj_id_map,
sa_entry->rx_mapped_id);
}
struct mlx5e_ipsec *ipsec = priv->ipsec;
void *val;
- val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id);
+ val = xa_load(&ipsec->ipsec_obj_id_map, id);
if (!val)
return -ENOENT;
xa_for_each(&esw->offloads.vport_reps, i, rep) {
rpriv = rep->rep_data[REP_ETH].priv;
- if (!rpriv || !rpriv->netdev)
+ if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems))
continue;
rhashtable_walk_enter(&rpriv->tc_ht, &iter);
struct mlx5e_ipsec_sa_entry;
#ifdef CONFIG_MLX5_ESWITCH
-void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx);
-int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx,
- struct mlx5_flow_destination *dest);
void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
struct mlx5e_ipsec_rx_create_attr *attr);
int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
struct mlx5e_ipsec_tx_create_attr *attr);
void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
#else
-static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx) {}
-
-static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
- struct mlx5e_ipsec_rx *rx,
- struct mlx5_flow_destination *dest)
-{
- return -EINVAL;
-}
-
static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
struct mlx5e_ipsec_rx_create_attr *attr) {}
{
int err;
- lockdep_assert_held(&esw->mode_lock);
+ devl_assert_locked(priv_to_devlink(esw->dev));
if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
esw_warn(esw->dev, "FDB is not supported, aborting ...\n");
if (toggle_lag)
mlx5_lag_disable_change(esw->dev);
- down_write(&esw->mode_lock);
if (!mlx5_esw_is_fdb_created(esw)) {
ret = mlx5_eswitch_enable_locked(esw, num_vfs);
} else {
}
}
- up_write(&esw->mode_lock);
-
if (toggle_lag)
mlx5_lag_enable_change(esw->dev);
return;
devl_assert_locked(priv_to_devlink(esw->dev));
- down_write(&esw->mode_lock);
/* If driver is unloaded, this function is called twice by remove_one()
* and mlx5_unload(). Prevent the second call.
*/
if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf)
- goto unlock;
+ return;
esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n",
esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
esw->esw_funcs.num_vfs = 0;
else
esw->esw_funcs.num_ec_vfs = 0;
-
-unlock:
- up_write(&esw->mode_lock);
}
/* Free resources for corresponding eswitch mode. It is called by devlink
devl_assert_locked(priv_to_devlink(esw->dev));
mlx5_lag_disable_change(esw->dev);
- down_write(&esw->mode_lock);
mlx5_eswitch_disable_locked(esw);
esw->mode = MLX5_ESWITCH_LEGACY;
- up_write(&esw->mode_lock);
mlx5_lag_enable_change(esw->dev);
}
if (!mlx5_esw_allowed(esw))
return true;
- if (down_read_trylock(&esw->mode_lock) != 0)
+ if (down_read_trylock(&esw->mode_lock) != 0) {
+ if (esw->eswitch_operation_in_progress) {
+ up_read(&esw->mode_lock);
+ return false;
+ }
return true;
+ }
return false;
}
if (down_write_trylock(&esw->mode_lock) == 0)
return -EINVAL;
- if (atomic64_read(&esw->user_count) > 0) {
+ if (esw->eswitch_operation_in_progress ||
+ atomic64_read(&esw->user_count) > 0) {
up_write(&esw->mode_lock);
return -EBUSY;
}
return esw->mode;
}
+int mlx5_esw_lock(struct mlx5_eswitch *esw)
+{
+ down_write(&esw->mode_lock);
+
+ if (esw->eswitch_operation_in_progress) {
+ up_write(&esw->mode_lock);
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
/**
* mlx5_esw_unlock() - Release write lock on esw mode lock
* @esw: eswitch device.
struct xarray paired;
struct mlx5_devcom_comp_dev *devcom;
u16 enabled_ipsec_vf_count;
+ bool eswitch_operation_in_progress;
};
void esw_offloads_disable(struct mlx5_eswitch *esw);
void mlx5_esw_get(struct mlx5_core_dev *dev);
void mlx5_esw_put(struct mlx5_core_dev *dev);
int mlx5_esw_try_lock(struct mlx5_eswitch *esw);
+int mlx5_esw_lock(struct mlx5_eswitch *esw);
void mlx5_esw_unlock(struct mlx5_eswitch *esw);
void esw_vport_change_handle_locked(struct mlx5_vport *vport);
static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
struct net *devl_net, *netdev_net;
- struct mlx5_eswitch *esw;
-
- esw = mlx5_devlink_eswitch_nocheck_get(devlink);
- netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev);
- devl_net = devlink_net(devlink);
+ bool ret = false;
- return net_eq(devl_net, netdev_net);
+ mutex_lock(&dev->mlx5e_res.uplink_netdev_lock);
+ if (dev->mlx5e_res.uplink_netdev) {
+ netdev_net = dev_net(dev->mlx5e_res.uplink_netdev);
+ devl_net = devlink_net(devlink);
+ ret = net_eq(devl_net, netdev_net);
+ }
+ mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock);
+ return ret;
}
int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev)
goto unlock;
}
+ esw->eswitch_operation_in_progress = true;
+ up_write(&esw->mode_lock);
+
mlx5_eswitch_disable_locked(esw);
if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
if (mlx5_devlink_trap_get_num_active(esw->dev)) {
NL_SET_ERR_MSG_MOD(extack,
"Can't change mode while devlink traps are active");
err = -EOPNOTSUPP;
- goto unlock;
+ goto skip;
}
err = esw_offloads_start(esw, extack);
} else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) {
err = -EINVAL;
}
+skip:
+ down_write(&esw->mode_lock);
+ esw->eswitch_operation_in_progress = false;
unlock:
mlx5_esw_unlock(esw);
enable_lag:
int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
{
struct mlx5_eswitch *esw;
- int err;
esw = mlx5_devlink_eswitch_get(devlink);
if (IS_ERR(esw))
return PTR_ERR(esw);
- down_read(&esw->mode_lock);
- err = esw_mode_to_devlink(esw->mode, mode);
- up_read(&esw->mode_lock);
- return err;
+ return esw_mode_to_devlink(esw->mode, mode);
}
static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode,
if (err)
goto out;
+ esw->eswitch_operation_in_progress = true;
+ up_write(&esw->mode_lock);
+
err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack);
- if (err)
- goto out;
+ if (!err)
+ esw->offloads.inline_mode = mlx5_mode;
- esw->offloads.inline_mode = mlx5_mode;
+ down_write(&esw->mode_lock);
+ esw->eswitch_operation_in_progress = false;
up_write(&esw->mode_lock);
return 0;
int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
{
struct mlx5_eswitch *esw;
- int err;
esw = mlx5_devlink_eswitch_get(devlink);
if (IS_ERR(esw))
return PTR_ERR(esw);
- down_read(&esw->mode_lock);
- err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
- up_read(&esw->mode_lock);
- return err;
+ return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
}
bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
goto unlock;
}
+ esw->eswitch_operation_in_progress = true;
+ up_write(&esw->mode_lock);
+
esw_destroy_offloads_fdb_tables(esw);
esw->offloads.encap = encap;
(void)esw_create_offloads_fdb_tables(esw);
}
+ down_write(&esw->mode_lock);
+ esw->eswitch_operation_in_progress = false;
+
unlock:
up_write(&esw->mode_lock);
return err;
if (IS_ERR(esw))
return PTR_ERR(esw);
- down_read(&esw->mode_lock);
*encap = esw->offloads.encap;
- up_read(&esw->mode_lock);
return 0;
}
mlx5_core_err(dev, "Failed to reload FW tracer\n");
}
+#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
+static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev)
+{
+ struct pci_dev *bridge = dev->pdev->bus->self;
+ u16 reg16;
+ int err;
+
+ if (!bridge)
+ return -EOPNOTSUPP;
+
+ err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, ®16);
+ if (err)
+ return err;
+
+ if ((reg16 & PCI_EXP_SLTCTL_HPIE) && (reg16 & PCI_EXP_SLTCTL_DLLSCE)) {
+ mlx5_core_warn(dev, "FW reset is not supported as HotPlug is enabled\n");
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+#endif
+
static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
{
struct pci_bus *bridge_bus = dev->pdev->bus;
return false;
}
+#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
+ err = mlx5_check_hotplug_interrupt(dev);
+ if (err)
+ return false;
+#endif
+
err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id);
if (err)
return false;
p_dma->virt_addr = NULL;
}
kfree(p_mngr->ilt_shadow);
+ p_mngr->ilt_shadow = NULL;
}
static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn,
#define QCASPI_MAX_REGS 0x20
+#define QCASPI_RX_MAX_FRAMES 4
+
static const u16 qcaspi_spi_regs[] = {
SPI_REG_BFR_SIZE,
SPI_REG_WRBUF_SPC_AVA,
{
struct qcaspi *qca = netdev_priv(dev);
- ring->rx_max_pending = 4;
+ ring->rx_max_pending = QCASPI_RX_MAX_FRAMES;
ring->tx_max_pending = TX_RING_MAX_LEN;
- ring->rx_pending = 4;
+ ring->rx_pending = QCASPI_RX_MAX_FRAMES;
ring->tx_pending = qca->txr.count;
}
struct kernel_ethtool_ringparam *kernel_ring,
struct netlink_ext_ack *extack)
{
- const struct net_device_ops *ops = dev->netdev_ops;
struct qcaspi *qca = netdev_priv(dev);
- if ((ring->rx_pending) ||
+ if (ring->rx_pending != QCASPI_RX_MAX_FRAMES ||
(ring->rx_mini_pending) ||
(ring->rx_jumbo_pending))
return -EINVAL;
- if (netif_running(dev))
- ops->ndo_stop(dev);
+ if (qca->spi_thread)
+ kthread_park(qca->spi_thread);
qca->txr.count = max_t(u32, ring->tx_pending, TX_RING_MIN_LEN);
qca->txr.count = min_t(u16, qca->txr.count, TX_RING_MAX_LEN);
- if (netif_running(dev))
- ops->ndo_open(dev);
+ if (qca->spi_thread)
+ kthread_unpark(qca->spi_thread);
return 0;
}
netdev_info(qca->net_dev, "SPI thread created\n");
while (!kthread_should_stop()) {
set_current_state(TASK_INTERRUPTIBLE);
+ if (kthread_should_park()) {
+ netif_tx_disable(qca->net_dev);
+ netif_carrier_off(qca->net_dev);
+ qcaspi_flush_tx_ring(qca);
+ kthread_parkme();
+ if (qca->sync == QCASPI_SYNC_READY) {
+ netif_carrier_on(qca->net_dev);
+ netif_wake_queue(qca->net_dev);
+ }
+ continue;
+ }
+
if ((qca->intr_req == qca->intr_svc) &&
!qca->txr.skb[qca->txr.head])
schedule();
if (intr_cause & SPI_INT_CPU_ON) {
qcaspi_qca7k_sync(qca, QCASPI_EVENT_CPUON);
+ /* Frame decoding in progress */
+ if (qca->frm_handle.state != qca->frm_handle.init)
+ qca->net_dev->stats.rx_dropped++;
+
+ qcafrm_fsm_init_spi(&qca->frm_handle);
+ qca->stats.device_reset++;
+
/* not synced. */
if (qca->sync != QCASPI_SYNC_READY)
continue;
- qca->stats.device_reset++;
netif_wake_queue(qca->net_dev);
netif_carrier_on(qca->net_dev);
}
return -ENODEV;
}
- if (!of_device_is_compatible(np, "loongson, pci-gmac")) {
- pr_info("dwmac_loongson_pci: Incompatible OF node\n");
- return -ENODEV;
- }
-
plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
if (!plat)
return -ENOMEM;
+ plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
+ sizeof(*plat->mdio_bus_data),
+ GFP_KERNEL);
+ if (!plat->mdio_bus_data)
+ return -ENOMEM;
+
plat->mdio_node = of_get_child_by_name(np, "mdio");
if (plat->mdio_node) {
dev_info(&pdev->dev, "Found MDIO subnode\n");
-
- plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
- sizeof(*plat->mdio_bus_data),
- GFP_KERNEL);
- if (!plat->mdio_bus_data) {
- ret = -ENOMEM;
- goto err_put_node;
- }
plat->mdio_bus_data->needs_reset = true;
}
#define RGMII_CONFIG_LOOPBACK_EN BIT(2)
#define RGMII_CONFIG_PROG_SWAP BIT(1)
#define RGMII_CONFIG_DDR_MODE BIT(0)
+#define RGMII_CONFIG_SGMII_CLK_DVDR GENMASK(18, 10)
/* SDCC_HC_REG_DLL_CONFIG fields */
#define SDCC_DLL_CONFIG_DLL_RST BIT(30)
#define ETHQOS_MAC_CTRL_SPEED_MODE BIT(14)
#define ETHQOS_MAC_CTRL_PORT_SEL BIT(15)
+#define SGMII_10M_RX_CLK_DVDR 0x31
+
struct ethqos_emac_por {
unsigned int offset;
unsigned int value;
return 0;
}
+/* On interface toggle MAC registers gets reset.
+ * Configure MAC block for SGMII on ethernet phy link up
+ */
static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
{
int val;
case SPEED_10:
val |= ETHQOS_MAC_CTRL_PORT_SEL;
val &= ~ETHQOS_MAC_CTRL_SPEED_MODE;
+ rgmii_updatel(ethqos, RGMII_CONFIG_SGMII_CLK_DVDR,
+ FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR,
+ SGMII_10M_RX_CLK_DVDR),
+ RGMII_IO_MACRO_CONFIG);
break;
}
new_bus->parent = priv->device;
err = of_mdiobus_register(new_bus, mdio_node);
- if (err != 0) {
+ if (err == -ENODEV) {
+ err = 0;
+ dev_info(dev, "MDIO bus is disabled\n");
+ goto bus_register_fail;
+ } else if (err) {
dev_err_probe(dev, err, "Cannot register the MDIO bus\n");
goto bus_register_fail;
}
return 0;
inst_rollback:
- for (i--; i >= 0; i--)
+ for (i--; i >= 0; i--) {
__team_option_inst_del_option(team, dst_opts[i]);
+ list_del(&dst_opts[i]->list);
+ }
i = option_count;
alloc_rollback:
static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata)
{
- /* Downstream devices need to be in D0 state before enabling PCI PM substates */
+ /*
+ * Downstream devices need to be in D0 state before enabling PCI PM
+ * substates.
+ */
pci_set_power_state(pdev, PCI_D0);
- pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL);
+ pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
return 0;
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON,
DEV_LS7A_LPC, system_bus_quirk);
+/*
+ * Some Loongson PCIe ports have hardware limitations on their Maximum Read
+ * Request Size. They can't handle anything larger than this. Sane
+ * firmware will set proper MRRS at boot, so we only need no_inc_mrrs for
+ * bridges. However, some MIPS Loongson firmware doesn't set MRRS properly,
+ * so we have to enforce maximum safe MRRS, which is 256 bytes.
+ */
+#ifdef CONFIG_MIPS
+static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev)
+{
+ struct pci_bus *bus = pdev->bus;
+ struct pci_dev *bridge;
+ static const struct pci_device_id bridge_devids[] = {
+ { PCI_VDEVICE(LOONGSON, DEV_LS2K_PCIE_PORT0) },
+ { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT0) },
+ { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT1) },
+ { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT2) },
+ { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT3) },
+ { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT4) },
+ { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT5) },
+ { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT6) },
+ { 0, },
+ };
+
+ /* look for the matching bridge */
+ while (!pci_is_root_bus(bus)) {
+ bridge = bus->self;
+ bus = bus->parent;
+
+ if (pci_match_id(bridge_devids, bridge)) {
+ if (pcie_get_readrq(pdev) > 256) {
+ pci_info(pdev, "limiting MRRS to 256\n");
+ pcie_set_readrq(pdev, 256);
+ }
+ break;
+ }
+ }
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_set_min_mrrs_quirk);
+#endif
+
static void loongson_mrrs_quirk(struct pci_dev *pdev)
{
- /*
- * Some Loongson PCIe ports have h/w limitations of maximum read
- * request size. They can't handle anything larger than this. So
- * force this limit on any devices attached under these ports.
- */
struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus);
bridge->no_inc_mrrs = 1;
if (!(features & VMD_FEAT_BIOS_PM_QUIRK))
return 0;
- pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL);
+ pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL);
pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR);
if (!pos)
if (pass && dev->subordinate) {
check_hotplug_bridge(slot, dev);
pcibios_resource_survey_bus(dev->subordinate);
- if (pci_is_root_bus(bus))
- __pci_bus_size_bridges(dev->subordinate, &add_list);
+ __pci_bus_size_bridges(dev->subordinate,
+ &add_list);
}
}
}
- if (pci_is_root_bus(bus))
- __pci_bus_assign_resources(bus, &add_list, NULL);
- else
- pci_assign_unassigned_bridge_resources(bus->self);
+ __pci_bus_assign_resources(bus, &add_list, NULL);
}
acpiphp_sanitize_bus(bus);
return bridge->link_state;
}
-static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem)
+static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool locked)
{
struct pcie_link_state *link = pcie_aspm_get_link(pdev);
return -EPERM;
}
- if (sem)
+ if (!locked)
down_read(&pci_bus_sem);
mutex_lock(&aspm_lock);
if (state & PCIE_LINK_STATE_L0S)
link->clkpm_disable = 1;
pcie_set_clkpm(link, policy_to_clkpm_state(link));
mutex_unlock(&aspm_lock);
- if (sem)
+ if (!locked)
up_read(&pci_bus_sem);
return 0;
int pci_disable_link_state_locked(struct pci_dev *pdev, int state)
{
- return __pci_disable_link_state(pdev, state, false);
+ lockdep_assert_held_read(&pci_bus_sem);
+
+ return __pci_disable_link_state(pdev, state, true);
}
EXPORT_SYMBOL(pci_disable_link_state_locked);
*/
int pci_disable_link_state(struct pci_dev *pdev, int state)
{
- return __pci_disable_link_state(pdev, state, true);
+ return __pci_disable_link_state(pdev, state, false);
}
EXPORT_SYMBOL(pci_disable_link_state);
-/**
- * pci_enable_link_state - Clear and set the default device link state so that
- * the link may be allowed to enter the specified states. Note that if the
- * BIOS didn't grant ASPM control to the OS, this does nothing because we can't
- * touch the LNKCTL register. Also note that this does not enable states
- * disabled by pci_disable_link_state(). Return 0 or a negative errno.
- *
- * @pdev: PCI device
- * @state: Mask of ASPM link states to enable
- */
-int pci_enable_link_state(struct pci_dev *pdev, int state)
+static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked)
{
struct pcie_link_state *link = pcie_aspm_get_link(pdev);
return -EPERM;
}
- down_read(&pci_bus_sem);
+ if (!locked)
+ down_read(&pci_bus_sem);
mutex_lock(&aspm_lock);
link->aspm_default = 0;
if (state & PCIE_LINK_STATE_L0S)
link->clkpm_default = (state & PCIE_LINK_STATE_CLKPM) ? 1 : 0;
pcie_set_clkpm(link, policy_to_clkpm_state(link));
mutex_unlock(&aspm_lock);
- up_read(&pci_bus_sem);
+ if (!locked)
+ up_read(&pci_bus_sem);
return 0;
}
+
+/**
+ * pci_enable_link_state - Clear and set the default device link state so that
+ * the link may be allowed to enter the specified states. Note that if the
+ * BIOS didn't grant ASPM control to the OS, this does nothing because we can't
+ * touch the LNKCTL register. Also note that this does not enable states
+ * disabled by pci_disable_link_state(). Return 0 or a negative errno.
+ *
+ * @pdev: PCI device
+ * @state: Mask of ASPM link states to enable
+ */
+int pci_enable_link_state(struct pci_dev *pdev, int state)
+{
+ return __pci_enable_link_state(pdev, state, false);
+}
EXPORT_SYMBOL(pci_enable_link_state);
+/**
+ * pci_enable_link_state_locked - Clear and set the default device link state
+ * so that the link may be allowed to enter the specified states. Note that if
+ * the BIOS didn't grant ASPM control to the OS, this does nothing because we
+ * can't touch the LNKCTL register. Also note that this does not enable states
+ * disabled by pci_disable_link_state(). Return 0 or a negative errno.
+ *
+ * @pdev: PCI device
+ * @state: Mask of ASPM link states to enable
+ *
+ * Context: Caller holds pci_bus_sem read lock.
+ */
+int pci_enable_link_state_locked(struct pci_dev *pdev, int state)
+{
+ lockdep_assert_held_read(&pci_bus_sem);
+
+ return __pci_enable_link_state(pdev, state, true);
+}
+EXPORT_SYMBOL(pci_enable_link_state_locked);
+
static int pcie_aspm_set_policy(const char *val,
const struct kernel_param *kp)
{
idx = 0;
while (cmn->dtc[j].counters[idx])
if (++idx == CMN_DT_NUM_COUNTERS)
- goto free_dtms;
+ return -ENOSPC;
}
hw->dtc_idx[j] = idx;
}
static long mtk_mipi_tx_pll_round_rate(struct clk_hw *hw, unsigned long rate,
unsigned long *prate)
{
- return clamp_val(rate, 50000000, 1600000000);
+ return clamp_val(rate, 125000000, 1600000000);
}
static const struct clk_ops mtk_mipi_tx_pll_ops = {
phy = devm_phy_create(&pdev->dev, NULL, &sp_uphy_ops);
if (IS_ERR(phy)) {
- ret = -PTR_ERR(phy);
+ ret = PTR_ERR(phy);
return ret;
}
u32 num_ports;
u32 reg_offset;
u32 qsgmii_main_ports;
+ bool no_offset;
};
static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode)
priv->num_ports = size / sizeof(u32);
if (!priv->num_ports)
return -EINVAL;
- priv->reg_offset = __be32_to_cpu(*offset);
+ if (!priv->no_offset)
+ priv->reg_offset = __be32_to_cpu(*offset);
}
if_phys = devm_kcalloc(dev, priv->num_ports,
dev_err(dev, "Failed to get syscon %d\n", ret);
return ret;
}
+ priv->no_offset = true;
}
ret = phy_gmii_sel_init_ports(priv);
bool wakeup_mode;
};
-static void detect_tablet_mode(struct platform_device *device)
+static void detect_tablet_mode(struct device *dev)
{
- struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev);
- acpi_handle handle = ACPI_HANDLE(&device->dev);
+ struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
+ acpi_handle handle = ACPI_HANDLE(dev);
unsigned long long vgbs;
acpi_status status;
int m;
input_report_switch(priv->switches_dev, SW_TABLET_MODE, m);
m = (vgbs & VGBS_DOCK_MODE_FLAG) ? 1 : 0;
input_report_switch(priv->switches_dev, SW_DOCK, m);
+
+ input_sync(priv->switches_dev);
}
/*
priv->switches_dev->id.bustype = BUS_HOST;
if (priv->has_switches) {
- detect_tablet_mode(device);
+ detect_tablet_mode(&device->dev);
ret = input_register_device(priv->switches_dev);
if (ret)
autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE);
sparse_keymap_report_event(input_dev, event, val, autorelease);
+
+ /* Some devices need this to report further events */
+ acpi_evaluate_object(handle, "VBDL", NULL, NULL);
}
/*
static int intel_vbtn_pm_resume(struct device *dev)
{
+ struct intel_vbtn_priv *priv = dev_get_drvdata(dev);
+
intel_vbtn_pm_complete(dev);
+
+ if (priv->has_switches)
+ detect_tablet_mode(dev);
+
return 0;
}
* @ips: IPS driver struct
*
* Check whether the MCP is over its thermal or power budget.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
*/
static bool mcp_exceeded(struct ips_driver *ips)
{
* @cpu: CPU number to check
*
* Check a given CPU's average temp or power is over its limit.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
*/
static bool cpu_exceeded(struct ips_driver *ips, int cpu)
{
* @ips: IPS driver struct
*
* Check the MCH temp & power against their maximums.
+ *
+ * Returns: %true if the temp or power has exceeded its maximum, else %false
*/
static bool mch_exceeded(struct ips_driver *ips)
{
* - down (at TDP limit)
* - adjust both CPU and GPU down if possible
*
- cpu+ gpu+ cpu+gpu- cpu-gpu+ cpu-gpu-
-cpu < gpu < cpu+gpu+ cpu+ gpu+ nothing
-cpu < gpu >= cpu+gpu-(mcp<) cpu+gpu-(mcp<) gpu- gpu-
-cpu >= gpu < cpu-gpu+(mcp<) cpu- cpu-gpu+(mcp<) cpu-
-cpu >= gpu >= cpu-gpu- cpu-gpu- cpu-gpu- cpu-gpu-
+ * |cpu+ gpu+ cpu+gpu- cpu-gpu+ cpu-gpu-
+ * cpu < gpu < |cpu+gpu+ cpu+ gpu+ nothing
+ * cpu < gpu >= |cpu+gpu-(mcp<) cpu+gpu-(mcp<) gpu- gpu-
+ * cpu >= gpu < |cpu-gpu+(mcp<) cpu- cpu-gpu+(mcp<) cpu-
+ * cpu >= gpu >=|cpu-gpu- cpu-gpu- cpu-gpu- cpu-gpu-
*
+ * Returns: %0
*/
static int ips_adjust(void *data)
{
* @data: ips driver structure
*
* This is the main function for the IPS driver. It monitors power and
- * tempurature in the MCP and adjusts CPU and GPU power clams accordingly.
+ * temperature in the MCP and adjusts CPU and GPU power clamps accordingly.
*
- * We keep a 5s moving average of power consumption and tempurature. Using
+ * We keep a 5s moving average of power consumption and temperature. Using
* that data, along with CPU vs GPU preference, we adjust the power clamps
* up or down.
+ *
+ * Returns: %0 on success or -errno on error
*/
static int ips_monitor(void *data)
{
* Handle temperature limit trigger events, generally by lowering the clamps.
* If we're at a critical limit, we clamp back to the lowest possible value
* to prevent emergency shutdown.
+ *
+ * Returns: IRQ_NONE or IRQ_HANDLED
*/
static irqreturn_t ips_irq_handler(int irq, void *arg)
{
/**
* ips_detect_cpu - detect whether CPU supports IPS
+ * @ips: IPS driver struct
*
* Walk our list and see if we're on a supported CPU. If we find one,
* return the limits for it.
+ *
+ * Returns: the &ips_mcp_limits struct that matches the boot CPU or %NULL
*/
static struct ips_mcp_limits *ips_detect_cpu(struct ips_driver *ips)
{
* monitor and control graphics turbo mode. If we can find them, we can
* enable graphics turbo, otherwise we must disable it to avoid exceeding
* thermal and power limits in the MCP.
+ *
+ * Returns: %true if the required symbols are found, else %false
*/
static bool ips_get_i915_syms(struct ips_driver *ips)
{
* Iterates over a quirks list until one is found that matches the
* ThinkPad's vendor, BIOS and EC model.
*
- * Returns 0 if nothing matches, otherwise returns the quirks field of
+ * Returns: %0 if nothing matches, otherwise returns the quirks field of
* the matching &struct tpacpi_quirk entry.
*
- * The match criteria is: vendor, ec and bios much match.
+ * The match criteria is: vendor, ec and bios must match.
*/
static unsigned long __init tpacpi_check_quirks(
const struct tpacpi_quirk *qlist,
/* ACPI helpers/functions/probes */
-/**
+/*
* This evaluates a ACPI method call specific to the battery
* ACPI extension. The specifics are that an error is marked
* in the 32rd bit of the response, so we just check that here.
static void intel_shim_vs_init(struct sdw_intel *sdw)
{
void __iomem *shim_vs = sdw->link_res->shim_vs;
- u16 act = 0;
+ u16 act;
+ act = intel_readw(shim_vs, SDW_SHIM2_INTEL_VS_ACTMCTL);
u16p_replace_bits(&act, 0x1, SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS);
act |= SDW_SHIM2_INTEL_VS_ACTMCTL_DACTQE;
act |= SDW_SHIM2_INTEL_VS_ACTMCTL_DODS;
* sdw_ml_sync_bank_switch: Multilink register bank switch
*
* @bus: SDW bus instance
+ * @multi_link: whether this is a multi-link stream with hardware-based sync
*
* Caller function should free the buffers on error
*/
-static int sdw_ml_sync_bank_switch(struct sdw_bus *bus)
+static int sdw_ml_sync_bank_switch(struct sdw_bus *bus, bool multi_link)
{
unsigned long time_left;
- if (!bus->multi_link)
+ if (!multi_link)
return 0;
/* Wait for completion of transfer */
bus->bank_switch_timeout = DEFAULT_BANK_SWITCH_TIMEOUT;
/* Check if bank switch was successful */
- ret = sdw_ml_sync_bank_switch(bus);
+ ret = sdw_ml_sync_bank_switch(bus, multi_link);
if (ret < 0) {
dev_err(bus->dev,
"multi link bank switch failed: %d\n", ret);
if (call->async) {
if (cancel_work_sync(&call->async_work))
afs_put_call(call);
- afs_put_call(call);
+ afs_set_call_complete(call, ret, 0);
}
ac->error = ret;
#include "debug.h"
#include "errcode.h"
#include "error.h"
+#include "journal.h"
#include "trace.h"
#include <linux/prefetch.h>
BUG_ON(btree_node_read_in_flight(b) ||
btree_node_write_in_flight(b));
- if (btree_node_dirty(b))
- bch2_btree_complete_write(c, b, btree_current_write(b));
- clear_btree_node_dirty_acct(c, b);
-
btree_node_data_free(c, b);
}
- BUG_ON(atomic_read(&c->btree_cache.dirty));
+ BUG_ON(!bch2_journal_error(&c->journal) &&
+ atomic_read(&c->btree_cache.dirty));
list_splice(&bc->freed_pcpu, &bc->freed_nonpcpu);
return bch2_trans_run(c, __bch2_btree_root_read(trans, id, k, level));
}
-void bch2_btree_complete_write(struct bch_fs *c, struct btree *b,
- struct btree_write *w)
+static void bch2_btree_complete_write(struct bch_fs *c, struct btree *b,
+ struct btree_write *w)
{
unsigned long old, new, v = READ_ONCE(b->will_make_reachable);
int bch2_btree_root_read(struct bch_fs *, enum btree_id,
const struct bkey_i *, unsigned);
-void bch2_btree_complete_write(struct bch_fs *, struct btree *,
- struct btree_write *);
-
bool bch2_btree_post_write_cleanup(struct bch_fs *, struct btree *);
enum btree_write_flags {
list_for_each_entry_safe(ck, n, &items, list) {
cond_resched();
- bch2_journal_pin_drop(&c->journal, &ck->journal);
-
list_del(&ck->list);
kfree(ck->k);
six_lock_exit(&ck->c.lock);
BTREE_UPDATE_PREJOURNAL);
}
+static noinline int bch2_btree_insert_clone_trans(struct btree_trans *trans,
+ enum btree_id btree,
+ struct bkey_i *k)
+{
+ struct bkey_i *n = bch2_trans_kmalloc(trans, bkey_bytes(&k->k));
+ int ret = PTR_ERR_OR_ZERO(n);
+ if (ret)
+ return ret;
+
+ bkey_copy(n, k);
+ return bch2_btree_insert_trans(trans, btree, n, 0);
+}
+
int __must_check bch2_trans_update_buffered(struct btree_trans *trans,
enum btree_id btree,
struct bkey_i *k)
EBUG_ON(trans->nr_wb_updates > trans->wb_updates_size);
EBUG_ON(k->k.u64s > BTREE_WRITE_BUFERED_U64s_MAX);
+ if (unlikely(trans->journal_replay_not_finished))
+ return bch2_btree_insert_clone_trans(trans, btree, k);
+
trans_for_each_wb_update(trans, i) {
if (i->btree == btree && bpos_eq(i->k.k.p, k->k.p)) {
bkey_copy(&i->k, k);
flags &= ~BCH_WATERMARK_MASK;
flags |= watermark;
+ if (!(flags & BTREE_INSERT_JOURNAL_RECLAIM) &&
+ watermark < c->journal.watermark) {
+ struct journal_res res = { 0 };
+
+ ret = drop_locks_do(trans,
+ bch2_journal_res_get(&c->journal, &res, 1,
+ watermark|JOURNAL_RES_GET_CHECK));
+ if (ret)
+ return ERR_PTR(ret);
+ }
+
while (1) {
nr_nodes[!!update_level] += 1 + split;
update_level++;
* we aren't using the extent overwrite path to delete, we're
* just using the normal key deletion path:
*/
- if (bkey_deleted(&n->k))
+ if (bkey_deleted(&n->k) && !(iter->flags & BTREE_ITER_IS_EXTENTS))
n->k.size = 0;
return bch2_trans_relock(trans) ?:
m->data_opts.rewrite_ptrs = 0;
/* if iter == NULL, it's just a promote */
if (iter)
- ret = bch2_extent_drop_ptrs(trans, iter, k, data_opts);
+ ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts);
goto done;
}
return ret;
}
-int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir)
+int bch2_empty_dir_snapshot(struct btree_trans *trans, u64 dir, u32 snapshot)
{
struct btree_iter iter;
struct bkey_s_c k;
- u32 snapshot;
int ret;
- ret = bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot);
- if (ret)
- return ret;
-
for_each_btree_key_upto_norestart(trans, iter, BTREE_ID_dirents,
- SPOS(dir.inum, 0, snapshot),
- POS(dir.inum, U64_MAX), 0, k, ret)
+ SPOS(dir, 0, snapshot),
+ POS(dir, U64_MAX), 0, k, ret)
if (k.k->type == KEY_TYPE_dirent) {
ret = -ENOTEMPTY;
break;
return ret;
}
+int bch2_empty_dir_trans(struct btree_trans *trans, subvol_inum dir)
+{
+ u32 snapshot;
+
+ return bch2_subvolume_get_snapshot(trans, dir.subvol, &snapshot) ?:
+ bch2_empty_dir_snapshot(trans, dir.inum, snapshot);
+}
+
int bch2_readdir(struct bch_fs *c, subvol_inum inum, struct dir_context *ctx)
{
struct btree_trans *trans = bch2_trans_get(c);
const struct bch_hash_info *,
const struct qstr *, subvol_inum *);
+int bch2_empty_dir_snapshot(struct btree_trans *, u64, u32);
int bch2_empty_dir_trans(struct btree_trans *, subvol_inum);
int bch2_readdir(struct bch_fs *, subvol_inum, struct dir_context *);
unsigned i = 0;
bkey_for_each_ptr_decode(k.k, ptrs, p, entry) {
- if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible) {
+ if (p.crc.compression_type == BCH_COMPRESSION_TYPE_incompressible ||
+ p.ptr.unwritten) {
rewrite_ptrs = 0;
goto incompressible;
}
if ((arg.flags & BCH_SUBVOL_SNAPSHOT_CREATE) &&
!arg.src_ptr)
- snapshot_src.subvol = to_bch_ei(dir)->ei_inode.bi_subvol;
+ snapshot_src.subvol = inode_inum(to_bch_ei(dir)).subvol;
inode = __bch2_create(file_mnt_idmap(filp), to_bch_ei(dir),
dst_dentry, arg.mode|S_IFDIR,
struct bch_fs *c = sb->s_fs_info;
int ret;
+ if (test_bit(BCH_FS_EMERGENCY_RO, &c->flags))
+ return 0;
+
down_write(&c->state_lock);
ret = bch2_fs_read_write(c);
up_write(&c->state_lock);
#include "btree_update.h"
#include "buckets.h"
#include "compress.h"
+#include "dirent.h"
#include "error.h"
#include "extents.h"
#include "extent_update.h"
if (ret)
goto out;
- if (fsck_err_on(S_ISDIR(inode.bi_mode), c,
- deleted_inode_is_dir,
- "directory %llu:%u in deleted_inodes btree",
- pos.offset, pos.snapshot))
- goto delete;
+ if (S_ISDIR(inode.bi_mode)) {
+ ret = bch2_empty_dir_snapshot(trans, pos.offset, pos.snapshot);
+ if (fsck_err_on(ret == -ENOTEMPTY, c, deleted_inode_is_dir,
+ "non empty directory %llu:%u in deleted_inodes btree",
+ pos.offset, pos.snapshot))
+ goto delete;
+ if (ret)
+ goto out;
+ }
if (fsck_err_on(!(inode.bi_flags & BCH_INODE_unlinked), c,
deleted_inode_not_unlinked,
return ret;
}
-static bool journal_entry_close(struct journal *j)
+bool bch2_journal_entry_close(struct journal *j)
{
bool ret;
bool ret = atomic64_read(&j->seq) == j->seq_ondisk;
if (!ret)
- journal_entry_close(j);
+ bch2_journal_entry_close(j);
return ret;
}
/*
* Recheck after taking the lock, so we don't race with another thread
- * that just did journal_entry_open() and call journal_entry_close()
+ * that just did journal_entry_open() and call bch2_journal_entry_close()
* unnecessarily
*/
if (journal_res_get_fast(j, res, flags)) {
bch2_journal_reclaim_stop(j);
bch2_journal_flush_all_pins(j);
- wait_event(j->wait, journal_entry_close(j));
+ wait_event(j->wait, bch2_journal_entry_close(j));
/*
* Always write a new journal entry, to make sure the clock hands are up
return s;
}
+bool bch2_journal_entry_close(struct journal *);
void bch2_journal_buf_put_final(struct journal *, u64, bool);
static inline void __bch2_journal_buf_put(struct journal *j, unsigned idx, u64 seq)
} while ((v = atomic64_cmpxchg(&j->reservations.counter,
old.v, new.v)) != old.v);
+ bch2_journal_reclaim_fast(j);
bch2_journal_space_available(j);
closure_wake_up(&w->wait);
(1U << JOURNAL_PIN_btree), 0, 0, 0))
*did_work = true;
+ if (seq_to_flush > journal_cur_seq(j))
+ bch2_journal_entry_close(j);
+
spin_lock(&j->lock);
/*
* If journal replay hasn't completed, the unreplayed journal entries
u64 start_seq = c->journal_replay_seq_start;
u64 end_seq = c->journal_replay_seq_start;
size_t i;
- int ret;
+ int ret = 0;
move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr);
keys->gap = keys->nr;
{
check_indirect_extent_deleting(new, &flags);
+ if (old.k->type == KEY_TYPE_reflink_v &&
+ new->k.type == KEY_TYPE_reflink_v &&
+ old.k->u64s == new->k.u64s &&
+ !memcmp(bkey_s_c_to_reflink_v(old).v->start,
+ bkey_i_to_reflink_v(new)->v.start,
+ bkey_val_bytes(&new->k) - 8))
+ return 0;
+
return bch2_trans_mark_extent(trans, btree_id, level, old, new, flags);
}
if (!btree_type_has_ptrs(id))
continue;
- for_each_btree_key(trans, iter, id, POS_MIN,
- BTREE_ITER_ALL_SNAPSHOTS, k, ret) {
+ ret = for_each_btree_key2(trans, iter, id, POS_MIN,
+ BTREE_ITER_ALL_SNAPSHOTS, k, ({
struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
const union bch_extent_entry *entry;
struct extent_ptr_decoded p;
nr_uncompressed_extents++;
else if (compressed)
nr_compressed_extents++;
- }
- bch2_trans_iter_exit(trans, &iter);
+ 0;
+ }));
}
bch2_trans_put(trans);
start = round_down(start, fs_info->sectorsize);
btrfs_free_reserved_data_space_noquota(fs_info, len);
- btrfs_qgroup_free_data(inode, reserved, start, len);
+ btrfs_qgroup_free_data(inode, reserved, start, len, NULL);
}
/*
}
}
+static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_root *gang[8];
+ int i;
+ int ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ while (1) {
+ ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
+ (void **)gang, 0,
+ ARRAY_SIZE(gang),
+ BTRFS_ROOT_TRANS_TAG);
+ if (ret == 0)
+ break;
+ for (i = 0; i < ret; i++) {
+ struct btrfs_root *root = gang[i];
+
+ btrfs_qgroup_free_meta_all_pertrans(root);
+ radix_tree_tag_clear(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ }
+ }
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+}
+
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_fs_info *fs_info)
{
EXTENT_DIRTY);
btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);
+ btrfs_free_all_qgroup_pertrans(fs_info);
+
cur_trans->state =TRANS_STATE_COMPLETED;
wake_up(&cur_trans->commit_wait);
}
return ret;
}
+static void free_head_ref_squota_rsv(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_head *href)
+{
+ u64 root = href->owning_root;
+
+ /*
+ * Don't check must_insert_reserved, as this is called from contexts
+ * where it has already been unset.
+ */
+ if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE ||
+ !href->is_data || !is_fstree(root))
+ return;
+
+ btrfs_qgroup_free_refroot(fs_info, root, href->reserved_bytes,
+ BTRFS_QGROUP_RSV_DATA);
+}
+
static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_head *href,
struct btrfs_delayed_ref_node *node,
struct btrfs_squota_delta delta = {
.root = href->owning_root,
.num_bytes = node->num_bytes,
- .rsv_bytes = href->reserved_bytes,
.is_data = true,
.is_inc = true,
.generation = trans->transid,
flags, ref->objectid,
ref->offset, &key,
node->ref_mod, href->owning_root);
+ free_head_ref_squota_rsv(trans->fs_info, href);
if (!ret)
ret = btrfs_record_squota_delta(trans->fs_info, &delta);
- else
- btrfs_qgroup_free_refroot(trans->fs_info, delta.root,
- delta.rsv_bytes, BTRFS_QGROUP_RSV_DATA);
} else if (node->action == BTRFS_ADD_DELAYED_REF) {
ret = __btrfs_inc_extent_ref(trans, node, parent, ref->root,
ref->objectid, ref->offset,
struct btrfs_squota_delta delta = {
.root = href->owning_root,
.num_bytes = fs_info->nodesize,
- .rsv_bytes = 0,
.is_data = false,
.is_inc = true,
.generation = trans->transid,
int ret = 0;
if (TRANS_ABORTED(trans)) {
- if (insert_reserved)
+ if (insert_reserved) {
btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+ free_head_ref_squota_rsv(trans->fs_info, href);
+ }
return 0;
}
struct btrfs_delayed_ref_root *delayed_refs,
struct btrfs_delayed_ref_head *head)
{
+ u64 ret = 0;
+
/*
* We had csum deletions accounted for in our delayed refs rsv, we need
* to drop the csum leaves for this update from our delayed_refs_rsv.
btrfs_delayed_refs_rsv_release(fs_info, 0, nr_csums);
- return btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
+ ret = btrfs_calc_delayed_ref_csum_bytes(fs_info, nr_csums);
}
- if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE &&
- head->must_insert_reserved && head->is_data)
- btrfs_qgroup_free_refroot(fs_info, head->owning_root,
- head->reserved_bytes, BTRFS_QGROUP_RSV_DATA);
+ /* must_insert_reserved can be set only if we didn't run the head ref. */
+ if (head->must_insert_reserved)
+ free_head_ref_squota_rsv(fs_info, head);
- return 0;
+ return ret;
}
static int cleanup_ref_head(struct btrfs_trans_handle *trans,
* spin lock.
*/
must_insert_reserved = locked_ref->must_insert_reserved;
+ /*
+ * Unsetting this on the head ref relinquishes ownership of
+ * the rsv_bytes, so it is critical that every possible code
+ * path from here forward frees all reserves including qgroup
+ * reserve.
+ */
locked_ref->must_insert_reserved = false;
extent_op = locked_ref->extent_op;
struct btrfs_squota_delta delta = {
.root = delayed_ref_root,
.num_bytes = num_bytes,
- .rsv_bytes = 0,
.is_data = is_data,
.is_inc = false,
.generation = btrfs_extent_generation(leaf, ei),
.root = root_objectid,
.num_bytes = ins->offset,
.generation = trans->transid,
- .rsv_bytes = 0,
.is_data = true,
.is_inc = true,
};
ret = 0;
} else {
u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM |
- EXTENT_DELALLOC_NEW | EXTENT_CTLBITS);
+ EXTENT_DELALLOC_NEW | EXTENT_CTLBITS |
+ EXTENT_QGROUP_RESERVED);
/*
* At this point we can safely clear everything except the
qgroup_reserved -= range->len;
} else if (qgroup_reserved > 0) {
btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved,
- range->start, range->len);
+ range->start, range->len, NULL);
qgroup_reserved -= range->len;
}
list_del(&range->list);
* And at reserve time, it's always aligned to page size, so
* just free one page here.
*/
- btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
+ btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL);
btrfs_free_path(path);
btrfs_end_transaction(trans);
return ret;
*/
if (state_flags & EXTENT_DELALLOC)
btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start,
- end - start + 1);
+ end - start + 1, NULL);
clear_extent_bit(io_tree, start, end,
EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING,
* reserved data space.
* Since the IO will never happen for this page.
*/
- btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur);
+ btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL);
if (!inode_evicting) {
clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED |
EXTENT_DELALLOC | EXTENT_UPTODATE |
struct btrfs_path *path;
u64 start = ins->objectid;
u64 len = ins->offset;
- int qgroup_released;
+ u64 qgroup_released = 0;
int ret;
memset(&stack_fi, 0, sizeof(stack_fi));
btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
/* Encryption and other encoding is reserved and all 0 */
- qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
- if (qgroup_released < 0)
- return ERR_PTR(qgroup_released);
+ ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released);
+ if (ret < 0)
+ return ERR_PTR(ret);
if (trans) {
ret = insert_reserved_file_extent(trans, inode,
btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0);
out_qgroup_free_data:
if (ret < 0)
- btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes);
+ btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL);
out_free_data_space:
/*
* If btrfs_reserve_extent() succeeded, then we already decremented
* are limited to own subvolumes only
*/
ret = -EPERM;
+ } else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) {
+ /*
+ * Snapshots must be made with the src_inode referring
+ * to the subvolume inode, otherwise the permission
+ * checking above is useless because we may have
+ * permission on a lower directory but not the subvol
+ * itself.
+ */
+ ret = -EINVAL;
} else {
ret = btrfs_mksnapshot(&file->f_path, idmap,
name, namelen,
{
struct btrfs_ordered_extent *entry;
int ret;
+ u64 qgroup_rsv = 0;
if (flags &
((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) {
/* For nocow write, we can release the qgroup rsv right now */
- ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes);
+ ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv);
if (ret < 0)
return ERR_PTR(ret);
} else {
* The ordered extent has reserved qgroup space, release now
* and pass the reserved number for qgroup_record to free.
*/
- ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes);
+ ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv);
if (ret < 0)
return ERR_PTR(ret);
}
entry->inode = igrab(&inode->vfs_inode);
entry->compress_type = compress_type;
entry->truncated_len = (u64)-1;
- entry->qgroup_rsv = ret;
+ entry->qgroup_rsv = qgroup_rsv;
entry->flags = flags;
refcount_set(&entry->refs, 1);
init_waitqueue_head(&entry->wait);
release = entry->disk_num_bytes;
else
release = entry->num_bytes;
- btrfs_delalloc_release_metadata(btrfs_inode, release, false);
+ btrfs_delalloc_release_metadata(btrfs_inode, release,
+ test_bit(BTRFS_ORDERED_IOERR,
+ &entry->flags));
}
percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,
/* Free ranges specified by @reserved, normally in error path */
static int qgroup_free_reserved_data(struct btrfs_inode *inode,
- struct extent_changeset *reserved, u64 start, u64 len)
+ struct extent_changeset *reserved,
+ u64 start, u64 len, u64 *freed_ret)
{
struct btrfs_root *root = inode->root;
struct ulist_node *unode;
struct ulist_iterator uiter;
struct extent_changeset changeset;
- int freed = 0;
+ u64 freed = 0;
int ret;
extent_changeset_init(&changeset);
}
btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed,
BTRFS_QGROUP_RSV_DATA);
- ret = freed;
+ if (freed_ret)
+ *freed_ret = freed;
+ ret = 0;
out:
extent_changeset_release(&changeset);
return ret;
static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
struct extent_changeset *reserved, u64 start, u64 len,
- int free)
+ u64 *released, int free)
{
struct extent_changeset changeset;
int trace_op = QGROUP_RELEASE;
/* In release case, we shouldn't have @reserved */
WARN_ON(!free && reserved);
if (free && reserved)
- return qgroup_free_reserved_data(inode, reserved, start, len);
+ return qgroup_free_reserved_data(inode, reserved, start, len, released);
extent_changeset_init(&changeset);
ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1,
EXTENT_QGROUP_RESERVED, &changeset);
btrfs_qgroup_free_refroot(inode->root->fs_info,
inode->root->root_key.objectid,
changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
- ret = changeset.bytes_changed;
+ if (released)
+ *released = changeset.bytes_changed;
out:
extent_changeset_release(&changeset);
return ret;
* NOTE: This function may sleep for memory allocation.
*/
int btrfs_qgroup_free_data(struct btrfs_inode *inode,
- struct extent_changeset *reserved, u64 start, u64 len)
+ struct extent_changeset *reserved,
+ u64 start, u64 len, u64 *freed)
{
- return __btrfs_qgroup_release_data(inode, reserved, start, len, 1);
+ return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1);
}
/*
*
* NOTE: This function may sleep for memory allocation.
*/
-int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len)
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released)
{
- return __btrfs_qgroup_release_data(inode, NULL, start, len, 0);
+ return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0);
}
static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes,
qgroup_rsv_release(fs_info, qgroup, num_bytes,
BTRFS_QGROUP_RSV_META_PREALLOC);
- qgroup_rsv_add(fs_info, qgroup, num_bytes,
- BTRFS_QGROUP_RSV_META_PERTRANS);
+ if (!sb_rdonly(fs_info->sb))
+ qgroup_rsv_add(fs_info, qgroup, num_bytes,
+ BTRFS_QGROUP_RSV_META_PERTRANS);
list_for_each_entry(glist, &qgroup->groups, next_group)
qgroup_iterator_add(&qgroup_list, glist->group);
*root = RB_ROOT;
}
+void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes)
+{
+ if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE)
+ return;
+
+ if (!is_fstree(root))
+ return;
+
+ btrfs_qgroup_free_refroot(fs_info, root, rsv_bytes, BTRFS_QGROUP_RSV_DATA);
+}
+
int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
struct btrfs_squota_delta *delta)
{
out:
spin_unlock(&fs_info->qgroup_lock);
- if (!ret && delta->rsv_bytes)
- btrfs_qgroup_free_refroot(fs_info, root, delta->rsv_bytes,
- BTRFS_QGROUP_RSV_DATA);
return ret;
}
u64 root;
/* The number of bytes in the extent being counted. */
u64 num_bytes;
- /* The number of bytes reserved for this extent. */
- u64 rsv_bytes;
/* The generation the extent was created in. */
u64 generation;
/* Whether we are using or freeing the extent. */
/* New io_tree based accurate qgroup reserve API */
int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
struct extent_changeset **reserved, u64 start, u64 len);
-int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len);
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released);
int btrfs_qgroup_free_data(struct btrfs_inode *inode,
struct extent_changeset *reserved, u64 start,
- u64 len);
+ u64 len, u64 *freed);
int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
enum btrfs_qgroup_rsv_type type, bool enforce);
int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
struct btrfs_root *root, struct extent_buffer *eb);
void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans);
bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info);
+void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes);
int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
struct btrfs_squota_delta *delta);
static struct kmem_cache *btrfs_trans_handle_cachep;
-#define BTRFS_ROOT_TRANS_TAG 0
-
/*
* Transaction states and transitions
*
#include "ctree.h"
#include "misc.h"
+/* Radix-tree tag for roots that are part of the trasaction. */
+#define BTRFS_ROOT_TRANS_TAG 0
+
enum btrfs_trans_state {
TRANS_STATE_RUNNING,
TRANS_STATE_COMMIT_PREP,
return;
}
/*
- * If i_disksize got extended due to writeback of delalloc blocks while
- * the DIO was running we could fail to cleanup the orphan list in
- * ext4_handle_inode_extension(). Do it now.
+ * If i_disksize got extended either due to writeback of delalloc
+ * blocks or extending truncate while the DIO was running we could fail
+ * to cleanup the orphan list in ext4_handle_inode_extension(). Do it
+ * now.
*/
if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
* blocks. But the code in ext4_iomap_alloc() is careful to use
* zeroed/unwritten extents if this is possible; thus we won't leave
* uninitialized blocks in a file even if we didn't succeed in writing
- * as much as we intended.
+ * as much as we intended. Also we can race with truncate or write
+ * expanding the file so we have to be a bit careful here.
*/
- WARN_ON_ONCE(i_size_read(inode) < READ_ONCE(EXT4_I(inode)->i_disksize));
- if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize))
+ if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) &&
+ pos + size <= i_size_read(inode))
return size;
return ext4_handle_inode_extension(inode, pos, size);
}
start = max(start, rounddown(ac->ac_o_ex.fe_logical,
(ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb)));
+ /* avoid unnecessary preallocation that may trigger assertions */
+ if (start + size > EXT_MAX_BLOCKS)
+ size = EXT_MAX_BLOCKS - start;
+
/* don't cover already allocated blocks in selected range */
if (ar->pleft && start <= ar->lleft) {
size -= ar->lleft + 1 - start;
if (fc->dax) {
fuse_free_dax_mem_ranges(&fc->dax->free_ranges);
kfree(fc->dax);
+ fc->dax = NULL;
}
}
if (!ia)
return -ENOMEM;
- if (fopen_direct_io && fc->direct_io_relax) {
+ if (fopen_direct_io && fc->direct_io_allow_mmap) {
res = filemap_write_and_wait_range(mapping, pos, pos + count - 1);
if (res) {
fuse_io_free(ia);
ssize_t res;
bool exclusive_lock =
!(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) ||
+ get_fuse_conn(inode)->direct_io_allow_mmap ||
iocb->ki_flags & IOCB_APPEND ||
fuse_direct_write_extending_i_size(iocb, from);
* Take exclusive lock if
* - Parallel direct writes are disabled - a user space decision
* - Parallel direct writes are enabled and i_size is being extended.
+ * - Shared mmap on direct_io file is supported (FUSE_DIRECT_IO_ALLOW_MMAP).
* This might not be needed at all, but needs further investigation.
*/
if (exclusive_lock)
if (ff->open_flags & FOPEN_DIRECT_IO) {
/* Can't provide the coherency needed for MAP_SHARED
- * if FUSE_DIRECT_IO_RELAX isn't set.
+ * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set.
*/
- if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax)
+ if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap)
return -ENODEV;
invalidate_inode_pages2(file->f_mapping);
struct fuse_forget_link *next;
};
+/* Submount lookup tracking */
+struct fuse_submount_lookup {
+ /** Refcount */
+ refcount_t count;
+
+ /** Unique ID, which identifies the inode between userspace
+ * and kernel */
+ u64 nodeid;
+
+ /** The request used for sending the FORGET message */
+ struct fuse_forget_link *forget;
+};
+
/** FUSE inode */
struct fuse_inode {
/** Inode data */
*/
struct fuse_inode_dax *dax;
#endif
+ /** Submount specific lookup tracking */
+ struct fuse_submount_lookup *submount_lookup;
};
/** FUSE inode state bits */
/* Is tmpfile not implemented by fs? */
unsigned int no_tmpfile:1;
- /* relax restrictions in FOPEN_DIRECT_IO mode */
- unsigned int direct_io_relax:1;
+ /* Relax restrictions to allow shared mmap in FOPEN_DIRECT_IO mode */
+ unsigned int direct_io_allow_mmap:1;
/* Is statx not implemented by fs? */
unsigned int no_statx:1;
return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT);
}
+static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void)
+{
+ struct fuse_submount_lookup *sl;
+
+ sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT);
+ if (!sl)
+ return NULL;
+ sl->forget = fuse_alloc_forget();
+ if (!sl->forget)
+ goto out_free;
+
+ return sl;
+
+out_free:
+ kfree(sl);
+ return NULL;
+}
+
static struct inode *fuse_alloc_inode(struct super_block *sb)
{
struct fuse_inode *fi;
fi->attr_version = 0;
fi->orig_ino = 0;
fi->state = 0;
+ fi->submount_lookup = NULL;
mutex_init(&fi->mutex);
spin_lock_init(&fi->lock);
fi->forget = fuse_alloc_forget();
kmem_cache_free(fuse_inode_cachep, fi);
}
+static void fuse_cleanup_submount_lookup(struct fuse_conn *fc,
+ struct fuse_submount_lookup *sl)
+{
+ if (!refcount_dec_and_test(&sl->count))
+ return;
+
+ fuse_queue_forget(fc, sl->forget, sl->nodeid, 1);
+ sl->forget = NULL;
+ kfree(sl);
+}
+
static void fuse_evict_inode(struct inode *inode)
{
struct fuse_inode *fi = get_fuse_inode(inode);
fi->nlookup);
fi->forget = NULL;
}
+
+ if (fi->submount_lookup) {
+ fuse_cleanup_submount_lookup(fc, fi->submount_lookup);
+ fi->submount_lookup = NULL;
+ }
}
if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) {
WARN_ON(!list_empty(&fi->write_files));
fuse_dax_dontcache(inode, attr->flags);
}
+static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl,
+ u64 nodeid)
+{
+ sl->nodeid = nodeid;
+ refcount_set(&sl->count, 1);
+}
+
static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr,
struct fuse_conn *fc)
{
*/
if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) &&
S_ISDIR(attr->mode)) {
+ struct fuse_inode *fi;
+
inode = new_inode(sb);
if (!inode)
return NULL;
fuse_init_inode(inode, attr, fc);
- get_fuse_inode(inode)->nodeid = nodeid;
+ fi = get_fuse_inode(inode);
+ fi->nodeid = nodeid;
+ fi->submount_lookup = fuse_alloc_submount_lookup();
+ if (!fi->submount_lookup) {
+ iput(inode);
+ return NULL;
+ }
+ /* Sets nlookup = 1 on fi->submount_lookup->nlookup */
+ fuse_init_submount_lookup(fi->submount_lookup, nodeid);
inode->i_flags |= S_AUTOMOUNT;
goto done;
}
iput(inode);
goto retry;
}
-done:
fi = get_fuse_inode(inode);
spin_lock(&fi->lock);
fi->nlookup++;
spin_unlock(&fi->lock);
+done:
fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version);
return inode;
fc->init_security = 1;
if (flags & FUSE_CREATE_SUPP_GROUP)
fc->create_supp_group = 1;
- if (flags & FUSE_DIRECT_IO_RELAX)
- fc->direct_io_relax = 1;
+ if (flags & FUSE_DIRECT_IO_ALLOW_MMAP)
+ fc->direct_io_allow_mmap = 1;
} else {
ra_pages = fc->max_read / PAGE_SIZE;
fc->no_lock = 1;
FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
- FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX;
+ FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP;
#ifdef CONFIG_FUSE_DAX
if (fm->fc->dax)
flags |= FUSE_MAP_ALIGNMENT;
struct super_block *parent_sb = parent_fi->inode.i_sb;
struct fuse_attr root_attr;
struct inode *root;
+ struct fuse_submount_lookup *sl;
+ struct fuse_inode *fi;
fuse_sb_defaults(sb);
fm->sb = sb;
* its nlookup should not be incremented. fuse_iget() does
* that, though, so undo it here.
*/
- get_fuse_inode(root)->nlookup--;
+ fi = get_fuse_inode(root);
+ fi->nlookup--;
+
sb->s_d_op = &fuse_dentry_operations;
sb->s_root = d_make_root(root);
if (!sb->s_root)
return -ENOMEM;
+ /*
+ * Grab the parent's submount_lookup pointer and take a
+ * reference on the shared nlookup from the parent. This is to
+ * prevent the last forget for this nodeid from getting
+ * triggered until all users have finished with it.
+ */
+ sl = parent_fi->submount_lookup;
+ WARN_ON(!sl);
+ if (sl) {
+ refcount_inc(&sl->count);
+ fi->submount_lookup = sl;
+ }
+
return 0;
}
struct commit_header *tmp;
struct buffer_head *bh;
struct timespec64 now;
- blk_opf_t write_flags = REQ_OP_WRITE | REQ_SYNC;
+ blk_opf_t write_flags = REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS;
*cbh = NULL;
if (!ret)
ret = err;
}
+ cond_resched();
spin_lock(&journal->j_list_lock);
jinode->i_flags &= ~JI_COMMIT_RUNNING;
smp_mb();
*/
jbd2_journal_update_sb_log_tail(journal,
journal->j_tail_sequence,
- journal->j_tail,
- REQ_SYNC);
+ journal->j_tail, 0);
mutex_unlock(&journal->j_checkpoint_mutex);
} else {
jbd2_debug(3, "superblock not updated\n");
for (i = 0; i < bufs; i++) {
struct buffer_head *bh = wbuf[i];
+
/*
* Compute checksum.
*/
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
- submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
+ submit_bh(REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS,
+ bh);
}
cond_resched();
* space and if we lose sb update during power failure we'd replay
* old transaction with possibly newly overwritten data.
*/
- ret = jbd2_journal_update_sb_log_tail(journal, tid, block,
- REQ_SYNC | REQ_FUA);
+ ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA);
if (ret)
goto out;
*/
jbd2_journal_update_sb_log_tail(journal,
journal->j_tail_sequence,
- journal->j_tail,
- REQ_SYNC | REQ_FUA);
+ journal->j_tail, REQ_FUA);
mutex_unlock(&journal->j_checkpoint_mutex);
}
return jbd2_journal_start_thread(journal);
return -EIO;
}
- trace_jbd2_write_superblock(journal, write_flags);
+ /*
+ * Always set high priority flags to exempt from block layer's
+ * QOS policies, e.g. writeback throttle.
+ */
+ write_flags |= JBD2_JOURNAL_REQ_FLAGS;
if (!(journal->j_flags & JBD2_BARRIER))
write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
+
+ trace_jbd2_write_superblock(journal, write_flags);
+
if (buffer_write_io_error(bh)) {
/*
* Oh, dear. A previous attempt to write the journal
jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode);
sb->s_errno = cpu_to_be32(errcode);
- jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA);
+ jbd2_write_superblock(journal, REQ_FUA);
}
EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
++journal->j_transaction_sequence;
write_unlock(&journal->j_state_lock);
- jbd2_mark_journal_empty(journal,
- REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
+ jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA);
mutex_unlock(&journal->j_checkpoint_mutex);
} else
err = -EIO;
* the magic code for a fully-recovered superblock. Any future
* commits of data to the journal will restore the current
* s_start value. */
- jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+ jbd2_mark_journal_empty(journal, REQ_FUA);
if (flags)
err = __jbd2_journal_erase(journal, flags);
if (write) {
/* Lock to make assertions happy... */
mutex_lock_io(&journal->j_checkpoint_mutex);
- jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+ jbd2_mark_journal_empty(journal, REQ_FUA);
mutex_unlock(&journal->j_checkpoint_mutex);
}
int i;
int flags = nfsexp_flags(rqstp, exp);
- validate_process_creds();
-
/* discard any old override before preparing the new set */
revert_creds(get_cred(current_real_cred()));
new = prepare_creds();
else
new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
new->cap_permitted);
- validate_process_creds();
put_cred(override_creds(new));
put_cred(new);
- validate_process_creds();
return 0;
oom:
rqstp->rq_server->sv_maxconn = nn->max_connections;
svc_recv(rqstp);
- validate_process_creds();
}
atomic_dec(&nfsdstats.th_cnt);
int host_err;
bool retried = false;
- validate_process_creds();
/*
* If we get here, then the client has already done an "open",
* and (hopefully) checked permission - so allow OWNER_OVERRIDE
}
err = nfserrno(host_err);
}
- validate_process_creds();
return err;
}
nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags,
struct file **filp)
{
- int err;
-
- validate_process_creds();
- err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
- validate_process_creds();
- return err;
+ return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
}
/*
int error;
struct file *f;
- validate_creds(cred);
-
/* We must always pass in a valid mount pointer. */
BUG_ON(!path->mnt);
struct file *f;
int error;
- validate_creds(cred);
f = alloc_empty_file(flags, cred);
if (IS_ERR(f))
return f;
oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId);
#endif /* CIFS_DEBUG2 */
- rc = -EINVAL;
+
if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) {
+ spin_unlock(&cfids->cfid_list_lock);
+ rc = -EINVAL;
+ goto oshr_free;
+ }
+
+ rc = smb2_parse_contexts(server, rsp_iov,
+ &oparms.fid->epoch,
+ oparms.fid->lease_key,
+ &oplock, NULL, NULL);
+ if (rc) {
spin_unlock(&cfids->cfid_list_lock);
goto oshr_free;
}
- smb2_parse_contexts(server, o_rsp,
- &oparms.fid->epoch,
- oparms.fid->lease_key, &oplock,
- NULL, NULL);
+ rc = -EINVAL;
if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) {
spin_unlock(&cfids->cfid_list_lock);
goto oshr_free;
char *
smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr)
{
+ const int max_off = 4096;
+ const int max_len = 128 * 1024;
+
*off = 0;
*len = 0;
* Invalid length or offset probably means data area is invalid, but
* we have little choice but to ignore the data area in this case.
*/
- if (*off > 4096) {
- cifs_dbg(VFS, "offset %d too large, data area ignored\n", *off);
- *len = 0;
- *off = 0;
- } else if (*off < 0) {
- cifs_dbg(VFS, "negative offset %d to data invalid ignore data area\n",
- *off);
+ if (unlikely(*off < 0 || *off > max_off ||
+ *len < 0 || *len > max_len)) {
+ cifs_dbg(VFS, "%s: invalid data area (off=%d len=%d)\n",
+ __func__, *off, *len);
*off = 0;
*len = 0;
- } else if (*len < 0) {
- cifs_dbg(VFS, "negative data length %d invalid, data area ignored\n",
- *len);
- *len = 0;
- } else if (*len > 128 * 1024) {
- cifs_dbg(VFS, "data area larger than 128K: %d\n", *len);
+ } else if (*off == 0) {
*len = 0;
}
/* return pointer to beginning of data area, ie offset from SMB start */
- if ((*off != 0) && (*len != 0))
+ if (*off > 0 && *len > 0)
return (char *)shdr + *off;
- else
- return NULL;
+ return NULL;
}
/*
struct kvec *rsp_iov;
struct smb2_ioctl_rsp *ioctl_rsp;
struct reparse_data_buffer *reparse_buf;
- u32 plen;
+ u32 off, count, len;
cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
*/
if (rc == 0) {
/* See MS-FSCC 2.3.23 */
+ off = le32_to_cpu(ioctl_rsp->OutputOffset);
+ count = le32_to_cpu(ioctl_rsp->OutputCount);
+ if (check_add_overflow(off, count, &len) ||
+ len > rsp_iov[1].iov_len) {
+ cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n",
+ __func__, off, count);
+ rc = -EIO;
+ goto query_rp_exit;
+ }
- reparse_buf = (struct reparse_data_buffer *)
- ((char *)ioctl_rsp +
- le32_to_cpu(ioctl_rsp->OutputOffset));
- plen = le32_to_cpu(ioctl_rsp->OutputCount);
-
- if (plen + le32_to_cpu(ioctl_rsp->OutputOffset) >
- rsp_iov[1].iov_len) {
- cifs_tcon_dbg(FYI, "srv returned invalid ioctl len: %d\n",
- plen);
+ reparse_buf = (void *)((u8 *)ioctl_rsp + off);
+ len = sizeof(*reparse_buf);
+ if (count < len ||
+ count < le16_to_cpu(reparse_buf->ReparseDataLength) + len) {
+ cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n",
+ __func__, off, count);
rc = -EIO;
goto query_rp_exit;
}
struct smb2_hdr *shdr;
unsigned int pdu_length = server->pdu_size;
unsigned int buf_size;
+ unsigned int next_cmd;
struct mid_q_entry *mid_entry;
int next_is_large;
char *next_buffer = NULL;
next_is_large = server->large_buf;
one_more:
shdr = (struct smb2_hdr *)buf;
- if (shdr->NextCommand) {
+ next_cmd = le32_to_cpu(shdr->NextCommand);
+ if (next_cmd) {
+ if (WARN_ON_ONCE(next_cmd > pdu_length))
+ return -1;
if (next_is_large)
next_buffer = (char *)cifs_buf_get();
else
next_buffer = (char *)cifs_small_buf_get();
- memcpy(next_buffer,
- buf + le32_to_cpu(shdr->NextCommand),
- pdu_length - le32_to_cpu(shdr->NextCommand));
+ memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd);
}
mid_entry = smb2_find_mid(server, buf);
else
ret = cifs_handle_standard(server, mid_entry);
- if (ret == 0 && shdr->NextCommand) {
- pdu_length -= le32_to_cpu(shdr->NextCommand);
+ if (ret == 0 && next_cmd) {
+ pdu_length -= next_cmd;
server->large_buf = next_is_large;
if (next_is_large)
server->bigbuf = buf = next_buffer;
posix->nlink, posix->mode, posix->reparse_tag);
}
-void
-smb2_parse_contexts(struct TCP_Server_Info *server,
- struct smb2_create_rsp *rsp,
- unsigned int *epoch, char *lease_key, __u8 *oplock,
- struct smb2_file_all_info *buf,
- struct create_posix_rsp *posix)
+int smb2_parse_contexts(struct TCP_Server_Info *server,
+ struct kvec *rsp_iov,
+ unsigned int *epoch,
+ char *lease_key, __u8 *oplock,
+ struct smb2_file_all_info *buf,
+ struct create_posix_rsp *posix)
{
- char *data_offset;
+ struct smb2_create_rsp *rsp = rsp_iov->iov_base;
struct create_context *cc;
- unsigned int next;
- unsigned int remaining;
+ size_t rem, off, len;
+ size_t doff, dlen;
+ size_t noff, nlen;
char *name;
static const char smb3_create_tag_posix[] = {
0x93, 0xAD, 0x25, 0x50, 0x9C,
};
*oplock = 0;
- data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset);
- remaining = le32_to_cpu(rsp->CreateContextsLength);
- cc = (struct create_context *)data_offset;
+
+ off = le32_to_cpu(rsp->CreateContextsOffset);
+ rem = le32_to_cpu(rsp->CreateContextsLength);
+ if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len)
+ return -EINVAL;
+ cc = (struct create_context *)((u8 *)rsp + off);
/* Initialize inode number to 0 in case no valid data in qfid context */
if (buf)
buf->IndexNumber = 0;
- while (remaining >= sizeof(struct create_context)) {
- name = le16_to_cpu(cc->NameOffset) + (char *)cc;
- if (le16_to_cpu(cc->NameLength) == 4 &&
- strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0)
- *oplock = server->ops->parse_lease_buf(cc, epoch,
- lease_key);
- else if (buf && (le16_to_cpu(cc->NameLength) == 4) &&
- strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0)
- parse_query_id_ctxt(cc, buf);
- else if ((le16_to_cpu(cc->NameLength) == 16)) {
- if (posix &&
- memcmp(name, smb3_create_tag_posix, 16) == 0)
+ while (rem >= sizeof(*cc)) {
+ doff = le16_to_cpu(cc->DataOffset);
+ dlen = le32_to_cpu(cc->DataLength);
+ if (check_add_overflow(doff, dlen, &len) || len > rem)
+ return -EINVAL;
+
+ noff = le16_to_cpu(cc->NameOffset);
+ nlen = le16_to_cpu(cc->NameLength);
+ if (noff + nlen >= doff)
+ return -EINVAL;
+
+ name = (char *)cc + noff;
+ switch (nlen) {
+ case 4:
+ if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) {
+ *oplock = server->ops->parse_lease_buf(cc, epoch,
+ lease_key);
+ } else if (buf &&
+ !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) {
+ parse_query_id_ctxt(cc, buf);
+ }
+ break;
+ case 16:
+ if (posix && !memcmp(name, smb3_create_tag_posix, 16))
parse_posix_ctxt(cc, buf, posix);
+ break;
+ default:
+ cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n",
+ __func__, nlen, dlen);
+ if (IS_ENABLED(CONFIG_CIFS_DEBUG2))
+ cifs_dump_mem("context data: ", cc, dlen);
+ break;
}
- /* else {
- cifs_dbg(FYI, "Context not matched with len %d\n",
- le16_to_cpu(cc->NameLength));
- cifs_dump_mem("Cctxt name: ", name, 4);
- } */
-
- next = le32_to_cpu(cc->Next);
- if (!next)
+
+ off = le32_to_cpu(cc->Next);
+ if (!off)
break;
- remaining -= next;
- cc = (struct create_context *)((char *)cc + next);
+ if (check_sub_overflow(rem, off, &rem))
+ return -EINVAL;
+ cc = (struct create_context *)((u8 *)cc + off);
}
if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE)
*oplock = rsp->OplockLevel;
- return;
+ return 0;
}
static int
}
- smb2_parse_contexts(server, rsp, &oparms->fid->epoch,
- oparms->fid->lease_key, oplock, buf, posix);
+ rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch,
+ oparms->fid->lease_key, oplock, buf, posix);
creat_exit:
SMB2_open_free(&rqst);
free_rsp_buf(resp_buftype, rsp);
extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
enum securityEnum);
-extern void smb2_parse_contexts(struct TCP_Server_Info *server,
- struct smb2_create_rsp *rsp,
- unsigned int *epoch, char *lease_key,
- __u8 *oplock, struct smb2_file_all_info *buf,
- struct create_posix_rsp *posix);
+int smb2_parse_contexts(struct TCP_Server_Info *server,
+ struct kvec *rsp_iov,
+ unsigned int *epoch,
+ char *lease_key, __u8 *oplock,
+ struct smb2_file_all_info *buf,
+ struct create_posix_rsp *posix);
+
extern int smb3_encryption_required(const struct cifs_tcon *tcon);
extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
struct kvec *iov, unsigned int min_buf_size);
#define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */
#define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ"
#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC"
-#define SMB2_CREATE_ALLOCATION_SIZE "AISi"
+#define SMB2_CREATE_ALLOCATION_SIZE "AlSi"
#define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc"
#define SMB2_CREATE_TIMEWARP_REQUEST "TWrp"
#define SMB2_CREATE_QUERY_ON_DISK_ID "QFid"
#define SMB2_LEASE_WRITE_CACHING_LE cpu_to_le32(0x04)
#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02)
+#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE cpu_to_le32(0x04)
#define SMB2_LEASE_KEY_SIZE 16
lease->new_state = 0;
lease->flags = lctx->flags;
lease->duration = lctx->duration;
+ lease->is_dir = lctx->is_dir;
memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE);
lease->version = lctx->version;
- lease->epoch = 0;
+ lease->epoch = le16_to_cpu(lctx->epoch);
INIT_LIST_HEAD(&opinfo->lease_entry);
opinfo->o_lease = lease;
{
struct oplock_info *opinfo;
- if (S_ISDIR(file_inode(fp->filp)->i_mode))
- return;
+ if (fp->reserve_lease_break)
+ smb_lazy_parent_lease_break_close(fp);
opinfo = opinfo_get(fp);
if (!opinfo)
/* upgrading lease */
if ((atomic_read(&ci->op_count) +
atomic_read(&ci->sop_count)) == 1) {
- if (lease->state ==
- (lctx->req_state & lease->state)) {
+ if (lease->state != SMB2_LEASE_NONE_LE &&
+ lease->state == (lctx->req_state & lease->state)) {
lease->state |= lctx->req_state;
if (lctx->req_state &
SMB2_LEASE_WRITE_CACHING_LE)
lease_read_to_write(opinfo);
+
}
} else if ((atomic_read(&ci->op_count) +
atomic_read(&ci->sop_count)) > 1) {
lease->new_state =
SMB2_LEASE_READ_CACHING_LE;
} else {
- if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE)
+ if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE &&
+ !lease->is_dir)
lease->new_state =
SMB2_LEASE_READ_CACHING_LE;
else
SMB2_LEASE_KEY_SIZE);
lease2->duration = lease1->duration;
lease2->flags = lease1->flags;
+ lease2->epoch = lease1->epoch++;
}
static int add_lease_global_list(struct oplock_info *opinfo)
}
}
+void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
+ struct lease_ctx_info *lctx)
+{
+ struct oplock_info *opinfo;
+ struct ksmbd_inode *p_ci = NULL;
+
+ if (lctx->version != 2)
+ return;
+
+ p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent);
+ if (!p_ci)
+ return;
+
+ read_lock(&p_ci->m_lock);
+ list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) {
+ if (!opinfo->is_lease)
+ continue;
+
+ if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE &&
+ (!(lctx->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) ||
+ !compare_guid_key(opinfo, fp->conn->ClientGUID,
+ lctx->parent_lease_key))) {
+ if (!atomic_inc_not_zero(&opinfo->refcount))
+ continue;
+
+ atomic_inc(&opinfo->conn->r_count);
+ if (ksmbd_conn_releasing(opinfo->conn)) {
+ atomic_dec(&opinfo->conn->r_count);
+ continue;
+ }
+
+ read_unlock(&p_ci->m_lock);
+ oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE);
+ opinfo_conn_put(opinfo);
+ read_lock(&p_ci->m_lock);
+ }
+ }
+ read_unlock(&p_ci->m_lock);
+
+ ksmbd_inode_put(p_ci);
+}
+
+void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp)
+{
+ struct oplock_info *opinfo;
+ struct ksmbd_inode *p_ci = NULL;
+
+ rcu_read_lock();
+ opinfo = rcu_dereference(fp->f_opinfo);
+ rcu_read_unlock();
+
+ if (!opinfo->is_lease || opinfo->o_lease->version != 2)
+ return;
+
+ p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent);
+ if (!p_ci)
+ return;
+
+ read_lock(&p_ci->m_lock);
+ list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) {
+ if (!opinfo->is_lease)
+ continue;
+
+ if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE) {
+ if (!atomic_inc_not_zero(&opinfo->refcount))
+ continue;
+
+ atomic_inc(&opinfo->conn->r_count);
+ if (ksmbd_conn_releasing(opinfo->conn)) {
+ atomic_dec(&opinfo->conn->r_count);
+ continue;
+ }
+ read_unlock(&p_ci->m_lock);
+ oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE);
+ opinfo_conn_put(opinfo);
+ read_lock(&p_ci->m_lock);
+ }
+ }
+ read_unlock(&p_ci->m_lock);
+
+ ksmbd_inode_put(p_ci);
+}
+
/**
* smb_grant_oplock() - handle oplock/lease request on file open
* @work: smb work
bool prev_op_has_lease;
__le32 prev_op_state = 0;
- /* not support directory lease */
- if (S_ISDIR(file_inode(fp->filp)->i_mode))
- return 0;
-
opinfo = alloc_opinfo(work, pid, tid);
if (!opinfo)
return -ENOMEM;
memcpy(buf->lcontext.LeaseKey, lease->lease_key,
SMB2_LEASE_KEY_SIZE);
buf->lcontext.LeaseFlags = lease->flags;
+ buf->lcontext.Epoch = cpu_to_le16(++lease->epoch);
buf->lcontext.LeaseState = lease->state;
memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key,
SMB2_LEASE_KEY_SIZE);
/**
* parse_lease_state() - parse lease context containted in file open request
* @open_req: buffer containing smb2 file open(create) request
+ * @is_dir: whether leasing file is directory
*
* Return: oplock state, -ENOENT if create lease context not found
*/
-struct lease_ctx_info *parse_lease_state(void *open_req)
+struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir)
{
struct create_context *cc;
struct smb2_create_req *req = (struct smb2_create_req *)open_req;
struct create_lease_v2 *lc = (struct create_lease_v2 *)cc;
memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
- lreq->req_state = lc->lcontext.LeaseState;
+ if (is_dir) {
+ lreq->req_state = lc->lcontext.LeaseState &
+ ~SMB2_LEASE_WRITE_CACHING_LE;
+ lreq->is_dir = true;
+ } else
+ lreq->req_state = lc->lcontext.LeaseState;
lreq->flags = lc->lcontext.LeaseFlags;
+ lreq->epoch = lc->lcontext.Epoch;
lreq->duration = lc->lcontext.LeaseDuration;
memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey,
SMB2_LEASE_KEY_SIZE);
__le32 flags;
__le64 duration;
__u8 parent_lease_key[SMB2_LEASE_KEY_SIZE];
+ __le16 epoch;
int version;
+ bool is_dir;
};
struct lease_table {
__u8 parent_lease_key[SMB2_LEASE_KEY_SIZE];
int version;
unsigned short epoch;
+ bool is_dir;
struct lease_table *l_lb;
};
/* Lease related functions */
void create_lease_buf(u8 *rbuf, struct lease *lease);
-struct lease_ctx_info *parse_lease_state(void *open_req);
+struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir);
__u8 smb2_map_lease_to_oplock(__le32 lease_state);
int lease_read_to_write(struct oplock_info *opinfo);
int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci,
struct lease_ctx_info *lctx);
void destroy_lease_table(struct ksmbd_conn *conn);
+void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
+ struct lease_ctx_info *lctx);
+void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp);
#endif /* __KSMBD_OPLOCK_H */
conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
- conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+ conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+ SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION &&
conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)
conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
- conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+ conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+ SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
(!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
- conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
+ conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
+ SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
(!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME |
XATTR_DOSINFO_ITIME;
- rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, false);
+ rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, true);
if (rc)
ksmbd_debug(SMB, "failed to store file attribute into xattr\n");
}
}
}
- req_op_level = req->RequestedOplockLevel;
- if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE)
- lc = parse_lease_state(req);
-
if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) {
pr_err("Invalid impersonationlevel : 0x%x\n",
le32_to_cpu(req->ImpersonationLevel));
goto err_out;
}
- rc = ksmbd_vfs_getattr(&path, &stat);
- if (rc)
- goto err_out;
-
- if (stat.result_mask & STATX_BTIME)
- fp->create_time = ksmbd_UnixTimeToNT(stat.btime);
- else
- fp->create_time = ksmbd_UnixTimeToNT(stat.ctime);
- if (req->FileAttributes || fp->f_ci->m_fattr == 0)
- fp->f_ci->m_fattr =
- cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes)));
-
- if (!created)
- smb2_update_xattrs(tcon, &path, fp);
- else
- smb2_new_xattrs(tcon, &path, fp);
-
if (file_present || created)
ksmbd_vfs_kern_path_unlock(&parent_path, &path);
need_truncate = 1;
}
+ req_op_level = req->RequestedOplockLevel;
+ if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE)
+ lc = parse_lease_state(req, S_ISDIR(file_inode(filp)->i_mode));
+
share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp);
if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) ||
(req_op_level == SMB2_OPLOCK_LEVEL_LEASE &&
}
} else {
if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) {
+ /*
+ * Compare parent lease using parent key. If there is no
+ * a lease that has same parent key, Send lease break
+ * notification.
+ */
+ smb_send_parent_lease_break_noti(fp, lc);
+
req_op_level = smb2_map_lease_to_oplock(lc->req_state);
ksmbd_debug(SMB,
"lease req for(%s) req oplock state 0x%x, lease state 0x%x\n",
}
}
+ rc = ksmbd_vfs_getattr(&path, &stat);
+ if (rc)
+ goto err_out1;
+
+ if (stat.result_mask & STATX_BTIME)
+ fp->create_time = ksmbd_UnixTimeToNT(stat.btime);
+ else
+ fp->create_time = ksmbd_UnixTimeToNT(stat.ctime);
+ if (req->FileAttributes || fp->f_ci->m_fattr == 0)
+ fp->f_ci->m_fattr =
+ cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes)));
+
+ if (!created)
+ smb2_update_xattrs(tcon, &path, fp);
+ else
+ smb2_new_xattrs(tcon, &path, fp);
+
memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE);
rsp->StructureSize = cpu_to_le16(89);
smb2_remove_blocked_lock,
argv);
if (rc) {
+ kfree(argv);
err = -ENOMEM;
goto out;
}
le32_to_cpu(req->LeaseState));
}
+ if (ret < 0) {
+ rsp->hdr.Status = err;
+ goto err_out;
+ }
+
lease_state = lease->state;
opinfo->op_state = OPLOCK_STATE_NONE;
wake_up_interruptible_all(&opinfo->oplock_q);
wake_up_interruptible_all(&opinfo->oplock_brk);
opinfo_put(opinfo);
- if (ret < 0) {
- rsp->hdr.Status = err;
- goto err_out;
- }
-
rsp->StructureSize = cpu_to_le16(36);
rsp->Reserved = 0;
rsp->Flags = 0;
}
}
+ /* Reserve lease break for parent dir at closing time */
+ fp->reserve_lease_break = true;
+
/* Do we need to break any of a levelII oplock? */
smb_break_all_levII_oplock(work, fp, 1);
return __ksmbd_inode_lookup(fp->filp->f_path.dentry);
}
+struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d)
+{
+ struct ksmbd_inode *ci;
+
+ read_lock(&inode_hash_lock);
+ ci = __ksmbd_inode_lookup(d);
+ read_unlock(&inode_hash_lock);
+
+ return ci;
+}
+
int ksmbd_query_inode_status(struct dentry *dentry)
{
struct ksmbd_inode *ci;
kfree(ci);
}
-static void ksmbd_inode_put(struct ksmbd_inode *ci)
+void ksmbd_inode_put(struct ksmbd_inode *ci)
{
if (atomic_dec_and_test(&ci->m_count))
ksmbd_inode_free(ci);
struct ksmbd_readdir_data readdir_data;
int dot_dotdot[2];
unsigned int f_state;
+ bool reserve_lease_break;
};
static inline void set_ctx_actor(struct dir_context *ctx,
struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id,
u64 pid);
void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp);
+struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d);
+void ksmbd_inode_put(struct ksmbd_inode *ci);
struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id);
struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid);
struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry);
if (strcmp(ei_child->name, name) != 0)
continue;
ret = simple_lookup(dir, dentry, flags);
+ if (IS_ERR(ret))
+ goto out;
create_dir_dentry(ei, ei_child, ei_dentry, true);
created = true;
break;
if (r <= 0)
continue;
ret = simple_lookup(dir, dentry, flags);
+ if (IS_ERR(ret))
+ goto out;
create_file_dentry(ei, i, ei_dentry, name, mode, cdata,
fops, true);
break;
{
struct inode *inode = mapping->host;
struct folio *folio = filemap_lock_folio(mapping, index);
- if (!folio) {
+ if (IS_ERR(folio)) {
folio = read_mapping_folio(mapping, index, NULL);
if (IS_ERR(folio)) {
* same context as task->real_cred.
*/
struct cred {
- atomic_t usage;
-#ifdef CONFIG_DEBUG_CREDENTIALS
- atomic_t subscribers; /* number of processes subscribed */
- void *put_addr;
- unsigned magic;
-#define CRED_MAGIC 0x43736564
-#define CRED_MAGIC_DEAD 0x44656144
-#endif
+ atomic_long_t usage;
kuid_t uid; /* real UID of the task */
kgid_t gid; /* real GID of the task */
kuid_t suid; /* saved UID of the task */
extern void __init cred_init(void);
extern int set_cred_ucounts(struct cred *);
-/*
- * check for validity of credentials
- */
-#ifdef CONFIG_DEBUG_CREDENTIALS
-extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned);
-extern void __validate_process_creds(struct task_struct *,
- const char *, unsigned);
-
-extern bool creds_are_invalid(const struct cred *cred);
-
-static inline void __validate_creds(const struct cred *cred,
- const char *file, unsigned line)
-{
- if (unlikely(creds_are_invalid(cred)))
- __invalid_creds(cred, file, line);
-}
-
-#define validate_creds(cred) \
-do { \
- __validate_creds((cred), __FILE__, __LINE__); \
-} while(0)
-
-#define validate_process_creds() \
-do { \
- __validate_process_creds(current, __FILE__, __LINE__); \
-} while(0)
-
-extern void validate_creds_for_do_exit(struct task_struct *);
-#else
-static inline void validate_creds(const struct cred *cred)
-{
-}
-static inline void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-}
-static inline void validate_process_creds(void)
-{
-}
-#endif
-
static inline bool cap_ambient_invariant_ok(const struct cred *cred)
{
return cap_issubset(cred->cap_ambient,
*/
static inline struct cred *get_new_cred_many(struct cred *cred, int nr)
{
- atomic_add(nr, &cred->usage);
+ atomic_long_add(nr, &cred->usage);
return cred;
}
struct cred *nonconst_cred = (struct cred *) cred;
if (!cred)
return cred;
- validate_creds(cred);
nonconst_cred->non_rcu = 0;
return get_new_cred_many(nonconst_cred, nr);
}
struct cred *nonconst_cred = (struct cred *) cred;
if (!cred)
return NULL;
- if (!atomic_inc_not_zero(&nonconst_cred->usage))
+ if (!atomic_long_inc_not_zero(&nonconst_cred->usage))
return NULL;
- validate_creds(cred);
nonconst_cred->non_rcu = 0;
return cred;
}
struct cred *cred = (struct cred *) _cred;
if (cred) {
- validate_creds(cred);
- if (atomic_sub_and_test(nr, &cred->usage))
+ if (atomic_long_sub_and_test(nr, &cred->usage))
__put_cred(cred);
}
}
* update
*/
unsigned long next_ops_update_sis;
+ /* for waiting until the execution of the kdamond_fn is started */
+ struct completion kdamond_started;
/* public: */
struct task_struct *kdamond;
/* keep async read/write and isreg together and in order */
REQ_F_SUPPORT_NOWAIT_BIT,
REQ_F_ISREG_BIT,
+ REQ_F_POLL_NO_LAZY_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT),
/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT),
+ /* don't use lazy poll wake for this request */
+ REQ_F_POLL_NO_LAZY = BIT(REQ_F_POLL_NO_LAZY_BIT),
};
typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3)
JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT)
+/* Journal high priority write IO operation flags */
+#define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE)
+
/*
* Journal flag definitions
*/
u8 reserved_at_140[0x8];
u8 bth_dst_qp[0x18];
- u8 reserved_at_160[0x20];
+ u8 inner_esp_spi[0x20];
u8 outer_esp_spi[0x20];
u8 reserved_at_1a0[0x60];
};
MLX5_IPSEC_ASO_INC_SN = 0x2,
};
+enum {
+ MLX5_IPSEC_ASO_REPLAY_WIN_32BIT = 0x0,
+ MLX5_IPSEC_ASO_REPLAY_WIN_64BIT = 0x1,
+ MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2,
+ MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3,
+};
+
struct mlx5_ifc_ipsec_aso_bits {
u8 valid[0x1];
u8 reserved_at_201[0x1];
*/
static inline bool vma_is_initial_heap(const struct vm_area_struct *vma)
{
- return vma->vm_start <= vma->vm_mm->brk &&
- vma->vm_end >= vma->vm_mm->start_brk;
+ return vma->vm_start < vma->vm_mm->brk &&
+ vma->vm_end > vma->vm_mm->start_brk;
}
/*
* its "stack". It's not even well-defined for programs written
* languages like Go.
*/
- return vma->vm_start <= vma->vm_mm->start_stack &&
- vma->vm_end >= vma->vm_mm->start_stack;
+ return vma->vm_start <= vma->vm_mm->start_stack &&
+ vma->vm_end >= vma->vm_mm->start_stack;
}
static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
if (folio_test_unevictable(folio) || !lrugen->enabled)
return false;
/*
- * There are three common cases for this page:
- * 1. If it's hot, e.g., freshly faulted in or previously hot and
- * migrated, add it to the youngest generation.
- * 2. If it's cold but can't be evicted immediately, i.e., an anon page
- * not in swapcache or a dirty page pending writeback, add it to the
- * second oldest generation.
- * 3. Everything else (clean, cold) is added to the oldest generation.
+ * There are four common cases for this page:
+ * 1. If it's hot, i.e., freshly faulted in, add it to the youngest
+ * generation, and it's protected over the rest below.
+ * 2. If it can't be evicted immediately, i.e., a dirty page pending
+ * writeback, add it to the second youngest generation.
+ * 3. If it should be evicted first, e.g., cold and clean from
+ * folio_rotate_reclaimable(), add it to the oldest generation.
+ * 4. Everything else falls between 2 & 3 above and is added to the
+ * second oldest generation if it's considered inactive, or the
+ * oldest generation otherwise. See lru_gen_is_active().
*/
if (folio_test_active(folio))
seq = lrugen->max_seq;
else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) ||
(folio_test_reclaim(folio) &&
(folio_test_dirty(folio) || folio_test_writeback(folio))))
- seq = lrugen->min_seq[type] + 1;
- else
+ seq = lrugen->max_seq - 1;
+ else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq)
seq = lrugen->min_seq[type];
+ else
+ seq = lrugen->min_seq[type] + 1;
gen = lru_gen_from_seq(seq);
flags = (gen + 1UL) << LRU_GEN_PGOFF;
* the old generation, is incremented when all its bins become empty.
*
* There are four operations:
- * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its
+ * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its
* current generation (old or young) and updates its "seg" to "head";
- * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its
+ * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its
* current generation (old or young) and updates its "seg" to "tail";
- * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old
+ * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old
* generation, updates its "gen" to "old" and resets its "seg" to "default";
- * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the
+ * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the
* young generation, updates its "gen" to "young" and resets its "seg" to
* "default".
*
* The events that trigger the above operations are:
* 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
- * 2. The first attempt to reclaim an memcg below low, which triggers
+ * 2. The first attempt to reclaim a memcg below low, which triggers
* MEMCG_LRU_TAIL;
- * 3. The first attempt to reclaim an memcg below reclaimable size threshold,
- * which triggers MEMCG_LRU_TAIL;
- * 4. The second attempt to reclaim an memcg below reclaimable size threshold,
- * which triggers MEMCG_LRU_YOUNG;
- * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG;
+ * 3. The first attempt to reclaim a memcg offlined or below reclaimable size
+ * threshold, which triggers MEMCG_LRU_TAIL;
+ * 4. The second attempt to reclaim a memcg offlined or below reclaimable size
+ * threshold, which triggers MEMCG_LRU_YOUNG;
+ * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG;
* 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
- * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
+ * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD.
*
- * Note that memcg LRU only applies to global reclaim, and the round-robin
- * incrementing of their max_seq counters ensures the eventual fairness to all
- * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * Notes:
+ * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing
+ * of their max_seq counters ensures the eventual fairness to all eligible
+ * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * 2. There are only two valid generations: old (seq) and young (seq+1).
+ * MEMCG_NR_GENS is set to three so that when reading the generation counter
+ * locklessly, a stale value (seq-1) does not wraparound to young.
*/
-#define MEMCG_NR_GENS 2
+#define MEMCG_NR_GENS 3
#define MEMCG_NR_BINS 8
struct lru_gen_memcg {
int pci_disable_link_state(struct pci_dev *pdev, int state);
int pci_disable_link_state_locked(struct pci_dev *pdev, int state);
int pci_enable_link_state(struct pci_dev *pdev, int state);
+int pci_enable_link_state_locked(struct pci_dev *pdev, int state);
void pcie_no_aspm(void);
bool pcie_aspm_support_enabled(void);
bool pcie_aspm_enabled(struct pci_dev *pdev);
{ return 0; }
static inline int pci_enable_link_state(struct pci_dev *pdev, int state)
{ return 0; }
+static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state)
+{ return 0; }
static inline void pcie_no_aspm(void) { }
static inline bool pcie_aspm_support_enabled(void) { return false; }
static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; }
__u8 length;
__u8 prefix_len;
+ union __packed {
+ __u8 flags;
+ struct __packed {
#if defined(__BIG_ENDIAN_BITFIELD)
- __u8 onlink : 1,
+ __u8 onlink : 1,
autoconf : 1,
reserved : 6;
#elif defined(__LITTLE_ENDIAN_BITFIELD)
- __u8 reserved : 6,
+ __u8 reserved : 6,
autoconf : 1,
onlink : 1;
#else
#error "Please fix <asm/byteorder.h>"
#endif
+ };
+ };
__be32 valid;
__be32 prefered;
__be32 reserved2;
struct in6_addr prefix;
};
+/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */
+static_assert(sizeof(struct prefix_info) == 32);
+
#include <linux/ipv6.h>
#include <linux/netdevice.h>
#include <net/if_inet6.h>
#define IF_RS_SENT 0x10
#define IF_READY 0x80000000
-/* prefix flags */
-#define IF_PREFIX_ONLINK 0x01
-#define IF_PREFIX_AUTOCONF 0x02
-
enum {
INET6_IFADDR_STATE_PREDAD,
INET6_IFADDR_STATE_DAD,
enum flow_offload_tuple_dir dir,
struct nf_flow_rule *flow_rule);
void (*free)(struct nf_flowtable *ft);
+ void (*get)(struct nf_flowtable *ft);
+ void (*put)(struct nf_flowtable *ft);
nf_hookfn *hook;
struct module *owner;
};
}
list_add_tail(&block_cb->list, &block->cb_list);
+ up_write(&flow_table->flow_block_lock);
+
+ if (flow_table->type->get)
+ flow_table->type->get(flow_table);
+ return 0;
unlock:
up_write(&flow_table->flow_block_lock);
WARN_ON(true);
}
up_write(&flow_table->flow_block_lock);
+
+ if (flow_table->type->put)
+ flow_table->type->put(flow_table);
}
void flow_offload_route_init(struct flow_offload *flow,
* - add FUSE_HAS_EXPIRE_ONLY
*
* 7.39
- * - add FUSE_DIRECT_IO_RELAX
+ * - add FUSE_DIRECT_IO_ALLOW_MMAP
* - add FUSE_STATX and related structures
*/
* FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir,
* symlink and mknod (single group that matches parent)
* FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation
- * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now
- * allow shared mmap
+ * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode.
*/
#define FUSE_ASYNC_READ (1 << 0)
#define FUSE_POSIX_LOCKS (1 << 1)
#define FUSE_HAS_INODE_DAX (1ULL << 33)
#define FUSE_CREATE_SUPP_GROUP (1ULL << 34)
#define FUSE_HAS_EXPIRE_ONLY (1ULL << 35)
-#define FUSE_DIRECT_IO_RELAX (1ULL << 36)
+#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36)
+
+/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
+#define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP
/**
* CUSE INIT request/reply flags
static void __io_poll_execute(struct io_kiocb *req, int mask)
{
+ unsigned flags = 0;
+
io_req_set_res(req, mask, 0);
req->io_task_work.func = io_poll_task_func;
trace_io_uring_task_add(req, mask);
- __io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE);
+
+ if (!(req->flags & REQ_F_POLL_NO_LAZY))
+ flags = IOU_F_TWQ_LAZY_WAKE;
+ __io_req_task_work_add(req, flags);
}
static inline void io_poll_execute(struct io_kiocb *req, int res)
poll->head = head;
poll->wait.private = (void *) wqe_private;
- if (poll->events & EPOLLEXCLUSIVE)
+ if (poll->events & EPOLLEXCLUSIVE) {
+ /*
+ * Exclusive waits may only wake a limited amount of entries
+ * rather than all of them, this may interfere with lazy
+ * wake if someone does wait(events > 1). Ensure we don't do
+ * lazy wake for those, as we need to process each one as they
+ * come in.
+ */
+ req->flags |= REQ_F_POLL_NO_LAZY;
add_wait_queue_exclusive(head, &poll->wait);
- else
+ } else {
add_wait_queue(head, &poll->wait);
+ }
}
static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
#include <linux/nospec.h>
#include <uapi/linux/io_uring.h>
-#include <uapi/asm-generic/ioctls.h>
+#include <asm/ioctls.h>
#include "io_uring.h"
#include "rsrc.h"
config CRASH_DUMP
bool "kernel crash dumps"
depends on ARCH_SUPPORTS_CRASH_DUMP
- depends on ARCH_SUPPORTS_KEXEC
select CRASH_CORE
select KEXEC_CORE
help
* It returns 0 on success and -EINVAL on failure.
*/
static int __init parse_crashkernel_suffix(char *cmdline,
- unsigned long long *crash_size,
+ unsigned long long *crash_size,
const char *suffix)
{
char *cur = cmdline;
unsigned long long *crash_base,
const char *suffix)
{
- char *first_colon, *first_space;
- char *ck_cmdline;
- char *name = "crashkernel=";
+ char *first_colon, *first_space;
+ char *ck_cmdline;
+ char *name = "crashkernel=";
BUG_ON(!crash_size || !crash_base);
*crash_size = 0;
return;
}
- if ((crash_base > CRASH_ADDR_LOW_MAX) &&
+ if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
crash_low_size && reserve_crashkernel_low(crash_low_size)) {
memblock_phys_free(crash_base, crash_size);
return;
*/
struct cred init_cred = {
.usage = ATOMIC_INIT(4),
-#ifdef CONFIG_DEBUG_CREDENTIALS
- .subscribers = ATOMIC_INIT(2),
- .magic = CRED_MAGIC,
-#endif
.uid = GLOBAL_ROOT_UID,
.gid = GLOBAL_ROOT_GID,
.suid = GLOBAL_ROOT_UID,
.ucounts = &init_ucounts,
};
-static inline void set_cred_subscribers(struct cred *cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- atomic_set(&cred->subscribers, n);
-#endif
-}
-
-static inline int read_cred_subscribers(const struct cred *cred)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- return atomic_read(&cred->subscribers);
-#else
- return 0;
-#endif
-}
-
-static inline void alter_cred_subscribers(const struct cred *_cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
- struct cred *cred = (struct cred *) _cred;
-
- atomic_add(n, &cred->subscribers);
-#endif
-}
-
/*
* The RCU callback to actually dispose of a set of credentials
*/
kdebug("put_cred_rcu(%p)", cred);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- if (cred->magic != CRED_MAGIC_DEAD ||
- atomic_read(&cred->usage) != 0 ||
- read_cred_subscribers(cred) != 0)
- panic("CRED: put_cred_rcu() sees %p with"
- " mag %x, put %p, usage %d, subscr %d\n",
- cred, cred->magic, cred->put_addr,
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
-#else
- if (atomic_read(&cred->usage) != 0)
- panic("CRED: put_cred_rcu() sees %p with usage %d\n",
- cred, atomic_read(&cred->usage));
-#endif
+ if (atomic_long_read(&cred->usage) != 0)
+ panic("CRED: put_cred_rcu() sees %p with usage %ld\n",
+ cred, atomic_long_read(&cred->usage));
security_cred_free(cred);
key_put(cred->session_keyring);
*/
void __put_cred(struct cred *cred)
{
- kdebug("__put_cred(%p{%d,%d})", cred,
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
-
- BUG_ON(atomic_read(&cred->usage) != 0);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(cred) != 0);
- cred->magic = CRED_MAGIC_DEAD;
- cred->put_addr = __builtin_return_address(0);
-#endif
+ kdebug("__put_cred(%p{%ld})", cred,
+ atomic_long_read(&cred->usage));
+
+ BUG_ON(atomic_long_read(&cred->usage) != 0);
BUG_ON(cred == current->cred);
BUG_ON(cred == current->real_cred);
{
struct cred *real_cred, *cred;
- kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred,
- atomic_read(&tsk->cred->usage),
- read_cred_subscribers(tsk->cred));
+ kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred,
+ atomic_long_read(&tsk->cred->usage));
real_cred = (struct cred *) tsk->real_cred;
tsk->real_cred = NULL;
cred = (struct cred *) tsk->cred;
tsk->cred = NULL;
- validate_creds(cred);
if (real_cred == cred) {
- alter_cred_subscribers(cred, -2);
put_cred_many(cred, 2);
} else {
- validate_creds(real_cred);
- alter_cred_subscribers(real_cred, -1);
put_cred(real_cred);
- alter_cred_subscribers(cred, -1);
put_cred(cred);
}
if (!new)
return NULL;
- atomic_set(&new->usage, 1);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- new->magic = CRED_MAGIC;
-#endif
+ atomic_long_set(&new->usage, 1);
if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
const struct cred *old;
struct cred *new;
- validate_process_creds();
-
new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
if (!new)
return NULL;
memcpy(new, old, sizeof(struct cred));
new->non_rcu = 0;
- atomic_set(&new->usage, 1);
- set_cred_subscribers(new, 0);
+ atomic_long_set(&new->usage, 1);
get_group_info(new->group_info);
get_uid(new->user);
get_user_ns(new->user_ns);
if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
- validate_creds(new);
return new;
error:
clone_flags & CLONE_THREAD
) {
p->real_cred = get_cred_many(p->cred, 2);
- alter_cred_subscribers(p->cred, 2);
- kdebug("share_creds(%p{%d,%d})",
- p->cred, atomic_read(&p->cred->usage),
- read_cred_subscribers(p->cred));
+ kdebug("share_creds(%p{%ld})",
+ p->cred, atomic_long_read(&p->cred->usage));
inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
return 0;
}
p->cred = p->real_cred = get_cred(new);
inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
- alter_cred_subscribers(new, 2);
- validate_creds(new);
return 0;
error_put:
struct task_struct *task = current;
const struct cred *old = task->real_cred;
- kdebug("commit_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
+ kdebug("commit_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
BUG_ON(task->cred != old);
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(old) < 2);
- validate_creds(old);
- validate_creds(new);
-#endif
- BUG_ON(atomic_read(&new->usage) < 1);
+ BUG_ON(atomic_long_read(&new->usage) < 1);
get_cred(new); /* we will require a ref for the subj creds too */
* RLIMIT_NPROC limits on user->processes have already been checked
* in set_user().
*/
- alter_cred_subscribers(new, 2);
if (new->user != old->user || new->user_ns != old->user_ns)
inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
rcu_assign_pointer(task->real_cred, new);
rcu_assign_pointer(task->cred, new);
if (new->user != old->user || new->user_ns != old->user_ns)
dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
- alter_cred_subscribers(old, -2);
/* send notifications */
if (!uid_eq(new->uid, old->uid) ||
*/
void abort_creds(struct cred *new)
{
- kdebug("abort_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
+ kdebug("abort_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
-#ifdef CONFIG_DEBUG_CREDENTIALS
- BUG_ON(read_cred_subscribers(new) != 0);
-#endif
- BUG_ON(atomic_read(&new->usage) < 1);
+ BUG_ON(atomic_long_read(&new->usage) < 1);
put_cred(new);
}
EXPORT_SYMBOL(abort_creds);
{
const struct cred *old = current->cred;
- kdebug("override_creds(%p{%d,%d})", new,
- atomic_read(&new->usage),
- read_cred_subscribers(new));
-
- validate_creds(old);
- validate_creds(new);
+ kdebug("override_creds(%p{%ld})", new,
+ atomic_long_read(&new->usage));
/*
* NOTE! This uses 'get_new_cred()' rather than 'get_cred()'.
* we are only installing the cred into the thread-synchronous
* '->cred' pointer, not the '->real_cred' pointer that is
* visible to other threads under RCU.
- *
- * Also note that we did validate_creds() manually, not depending
- * on the validation in 'get_cred()'.
*/
get_new_cred((struct cred *)new);
- alter_cred_subscribers(new, 1);
rcu_assign_pointer(current->cred, new);
- alter_cred_subscribers(old, -1);
- kdebug("override_creds() = %p{%d,%d}", old,
- atomic_read(&old->usage),
- read_cred_subscribers(old));
+ kdebug("override_creds() = %p{%ld}", old,
+ atomic_long_read(&old->usage));
return old;
}
EXPORT_SYMBOL(override_creds);
{
const struct cred *override = current->cred;
- kdebug("revert_creds(%p{%d,%d})", old,
- atomic_read(&old->usage),
- read_cred_subscribers(old));
+ kdebug("revert_creds(%p{%ld})", old,
+ atomic_long_read(&old->usage));
- validate_creds(old);
- validate_creds(override);
- alter_cred_subscribers(old, 1);
rcu_assign_pointer(current->cred, old);
- alter_cred_subscribers(override, -1);
put_cred(override);
}
EXPORT_SYMBOL(revert_creds);
kdebug("prepare_kernel_cred() alloc %p", new);
old = get_task_cred(daemon);
- validate_creds(old);
*new = *old;
new->non_rcu = 0;
- atomic_set(&new->usage, 1);
- set_cred_subscribers(new, 0);
+ atomic_long_set(&new->usage, 1);
get_uid(new->user);
get_user_ns(new->user_ns);
get_group_info(new->group_info);
goto error;
put_cred(old);
- validate_creds(new);
return new;
error:
return security_kernel_create_files_as(new, inode);
}
EXPORT_SYMBOL(set_create_files_as);
-
-#ifdef CONFIG_DEBUG_CREDENTIALS
-
-bool creds_are_invalid(const struct cred *cred)
-{
- if (cred->magic != CRED_MAGIC)
- return true;
- return false;
-}
-EXPORT_SYMBOL(creds_are_invalid);
-
-/*
- * dump invalid credentials
- */
-static void dump_invalid_creds(const struct cred *cred, const char *label,
- const struct task_struct *tsk)
-{
- pr_err("%s credentials: %p %s%s%s\n",
- label, cred,
- cred == &init_cred ? "[init]" : "",
- cred == tsk->real_cred ? "[real]" : "",
- cred == tsk->cred ? "[eff]" : "");
- pr_err("->magic=%x, put_addr=%p\n",
- cred->magic, cred->put_addr);
- pr_err("->usage=%d, subscr=%d\n",
- atomic_read(&cred->usage),
- read_cred_subscribers(cred));
- pr_err("->*uid = { %d,%d,%d,%d }\n",
- from_kuid_munged(&init_user_ns, cred->uid),
- from_kuid_munged(&init_user_ns, cred->euid),
- from_kuid_munged(&init_user_ns, cred->suid),
- from_kuid_munged(&init_user_ns, cred->fsuid));
- pr_err("->*gid = { %d,%d,%d,%d }\n",
- from_kgid_munged(&init_user_ns, cred->gid),
- from_kgid_munged(&init_user_ns, cred->egid),
- from_kgid_munged(&init_user_ns, cred->sgid),
- from_kgid_munged(&init_user_ns, cred->fsgid));
-#ifdef CONFIG_SECURITY
- pr_err("->security is %p\n", cred->security);
- if ((unsigned long) cred->security >= PAGE_SIZE &&
- (((unsigned long) cred->security & 0xffffff00) !=
- (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)))
- pr_err("->security {%x, %x}\n",
- ((u32*)cred->security)[0],
- ((u32*)cred->security)[1]);
-#endif
-}
-
-/*
- * report use of invalid credentials
- */
-void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line)
-{
- pr_err("Invalid credentials\n");
- pr_err("At %s:%u\n", file, line);
- dump_invalid_creds(cred, "Specified", current);
- BUG();
-}
-EXPORT_SYMBOL(__invalid_creds);
-
-/*
- * check the credentials on a process
- */
-void __validate_process_creds(struct task_struct *tsk,
- const char *file, unsigned line)
-{
- if (tsk->cred == tsk->real_cred) {
- if (unlikely(read_cred_subscribers(tsk->cred) < 2 ||
- creds_are_invalid(tsk->cred)))
- goto invalid_creds;
- } else {
- if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 ||
- read_cred_subscribers(tsk->cred) < 1 ||
- creds_are_invalid(tsk->real_cred) ||
- creds_are_invalid(tsk->cred)))
- goto invalid_creds;
- }
- return;
-
-invalid_creds:
- pr_err("Invalid process credentials\n");
- pr_err("At %s:%u\n", file, line);
-
- dump_invalid_creds(tsk->real_cred, "Real", tsk);
- if (tsk->cred != tsk->real_cred)
- dump_invalid_creds(tsk->cred, "Effective", tsk);
- else
- pr_err("Effective creds == Real creds\n");
- BUG();
-}
-EXPORT_SYMBOL(__validate_process_creds);
-
-/*
- * check creds for do_exit()
- */
-void validate_creds_for_do_exit(struct task_struct *tsk)
-{
- kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})",
- tsk->real_cred, tsk->cred,
- atomic_read(&tsk->cred->usage),
- read_cred_subscribers(tsk->cred));
-
- __validate_process_creds(tsk, __FILE__, __LINE__);
-}
-
-#endif /* CONFIG_DEBUG_CREDENTIALS */
ptrace_event(PTRACE_EVENT_EXIT, code);
user_events_exit(tsk);
- validate_creds_for_do_exit(tsk);
-
io_uring_files_cancel();
exit_signals(tsk); /* sets PF_EXITING */
if (tsk->task_frag.page)
put_page(tsk->task_frag.page);
- validate_creds_for_do_exit(tsk);
exit_task_stack_account(tsk);
check_stack_usage();
write_lock(&resource_lock);
for (addr = gfr_start(base, size, align, flags);
- gfr_continue(base, addr, size, flags);
- addr = gfr_next(addr, size, flags)) {
+ gfr_continue(base, addr, align, flags);
+ addr = gfr_next(addr, align, flags)) {
if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) !=
REGION_DISJOINT)
continue;
*cnt = rb_time_cnt(top);
- /* If top and msb counts don't match, this interrupted a write */
- if (*cnt != rb_time_cnt(msb))
+ /* If top, msb or bottom counts don't match, this interrupted a write */
+ if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
return false;
/* The shift to msb will lose its cnt bits */
unsigned long cnt2, top2, bottom2, msb2;
u64 val;
+ /* Any interruptions in this function should cause a failure */
+ cnt = local_read(&t->cnt);
+
/* The cmpxchg always fails if it interrupted an update */
if (!__rb_time_read(t, &val, &cnt2))
return false;
if (val != expect)
return false;
- cnt = local_read(&t->cnt);
if ((cnt & 3) != cnt2)
return false;
cnt2 = cnt + 1;
rb_time_split(val, &top, &bottom, &msb);
+ msb = rb_time_val_cnt(msb, cnt);
top = rb_time_val_cnt(top, cnt);
bottom = rb_time_val_cnt(bottom, cnt);
rb_time_split(set, &top2, &bottom2, &msb2);
+ msb2 = rb_time_val_cnt(msb2, cnt);
top2 = rb_time_val_cnt(top2, cnt2);
bottom2 = rb_time_val_cnt(bottom2, cnt2);
free_buffer_page(bpage);
}
+ free_page((unsigned long)cpu_buffer->free_page);
+
kfree(cpu_buffer);
}
*/
barrier();
- if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE)
+ if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
/* Writer corrupted the read? */
goto reset;
return length;
}
-static u64 rb_time_delta(struct ring_buffer_event *event)
-{
- switch (event->type_len) {
- case RINGBUF_TYPE_PADDING:
- return 0;
-
- case RINGBUF_TYPE_TIME_EXTEND:
- return rb_event_time_stamp(event);
-
- case RINGBUF_TYPE_TIME_STAMP:
- return 0;
-
- case RINGBUF_TYPE_DATA:
- return event->time_delta;
- default:
- return 0;
- }
-}
-
static inline bool
rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
unsigned long new_index, old_index;
struct buffer_page *bpage;
unsigned long addr;
- u64 write_stamp;
- u64 delta;
new_index = rb_event_index(event);
old_index = new_index + rb_event_ts_length(event);
bpage = READ_ONCE(cpu_buffer->tail_page);
- delta = rb_time_delta(event);
-
- if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp))
- return false;
-
- /* Make sure the write stamp is read before testing the location */
- barrier();
-
+ /*
+ * Make sure the tail_page is still the same and
+ * the next write location is the end of this event
+ */
if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
unsigned long write_mask =
local_read(&bpage->write) & ~RB_WRITE_MASK;
* to make sure that the next event adds an absolute
* value and does not rely on the saved write stamp, which
* is now going to be bogus.
+ *
+ * By setting the before_stamp to zero, the next event
+ * is not going to use the write_stamp and will instead
+ * create an absolute timestamp. This means there's no
+ * reason to update the wirte_stamp!
*/
rb_time_set(&cpu_buffer->before_stamp, 0);
- /* Something came in, can't discard */
- if (!rb_time_cmpxchg(&cpu_buffer->write_stamp,
- write_stamp, write_stamp - delta))
- return false;
-
/*
* If an event were to come in now, it would see that the
* write_stamp and the before_stamp are different, and assume
* that this event just added itself before updating
* the write stamp. The interrupting event will fix the
- * write stamp for us, and use the before stamp as its delta.
+ * write stamp for us, and use an absolute timestamp.
*/
/*
return;
/*
- * If this interrupted another event,
+ * If this interrupted another event,
*/
if (atomic_inc_return(this_cpu_ptr(&checking)) != 1)
goto out;
* absolute timestamp.
* Don't bother if this is the start of a new page (w == 0).
*/
- if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) {
+ if (!w) {
+ /* Use the sub-buffer timestamp */
+ info->delta = 0;
+ } else if (unlikely(!a_ok || !b_ok || info->before != info->after)) {
info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND;
info->length += RB_LEN_TIME_EXTEND;
} else {
/* See if we shot pass the end of this buffer page */
if (unlikely(write > BUF_PAGE_SIZE)) {
- /* before and after may now different, fix it up*/
- b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- if (a_ok && b_ok && info->before != info->after)
- (void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
- info->before, info->after);
- if (a_ok && b_ok)
- check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
+ check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
return rb_move_tail(cpu_buffer, tail, info);
}
if (likely(tail == w)) {
- u64 save_before;
- bool s_ok;
-
/* Nothing interrupted us between A and C */
/*D*/ rb_time_set(&cpu_buffer->write_stamp, info->ts);
- barrier();
- /*E*/ s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before);
- RB_WARN_ON(cpu_buffer, !s_ok);
+ /*
+ * If something came in between C and D, the write stamp
+ * may now not be in sync. But that's fine as the before_stamp
+ * will be different and then next event will just be forced
+ * to use an absolute timestamp.
+ */
if (likely(!(info->add_timestamp &
(RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE))))
/* This did not interrupt any time update */
else
/* Just use full timestamp for interrupting event */
info->delta = info->ts;
- barrier();
check_buffer(cpu_buffer, info, tail);
- if (unlikely(info->ts != save_before)) {
- /* SLOW PATH - Interrupted between C and E */
-
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- RB_WARN_ON(cpu_buffer, !a_ok);
-
- /* Write stamp must only go forward */
- if (save_before > info->after) {
- /*
- * We do not care about the result, only that
- * it gets updated atomically.
- */
- (void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
- info->after, save_before);
- }
- }
} else {
u64 ts;
/* SLOW PATH - Interrupted between A and C */
int nr_loops = 0;
int add_ts_default;
+ /* ring buffer does cmpxchg, make sure it is safe in NMI context */
+ if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) &&
+ (unlikely(in_nmi()))) {
+ return NULL;
+ }
+
rb_start_commit(cpu_buffer);
/* The commit page can not change after this */
if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
add_ts_default = RB_ADD_STAMP_ABSOLUTE;
info.length += RB_LEN_TIME_EXTEND;
+ if (info.length > BUF_MAX_DATA_SIZE)
+ goto out_fail;
} else {
add_ts_default = RB_ADD_STAMP_NONE;
}
if (!iter)
return NULL;
- iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags);
+ /* Holds the entire event: data and meta data */
+ iter->event = kmalloc(BUF_PAGE_SIZE, flags);
if (!iter->event) {
kfree(iter);
return NULL;
iter->leftover = ret;
} else {
- print_trace_line(iter);
+ ret = print_trace_line(iter);
+ if (ret == TRACE_TYPE_PARTIAL_LINE) {
+ iter->seq.full = 0;
+ trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n");
+ }
ret = trace_print_seq(m, &iter->seq);
/*
* If we overflow the seq_file buffer, then it will
return 0;
}
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp)
+{
+ tracing_release_file_tr(inode, filp);
+ return single_release(inode, filp);
+}
+
static int tracing_mark_open(struct inode *inode, struct file *filp)
{
stream_open(inode, filp);
if (!tr->array_buffer.buffer)
return 0;
- /* Do not allow tracing while resizng ring buffer */
+ /* Do not allow tracing while resizing ring buffer */
tracing_stop_tr(tr);
ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu);
goto out_start;
#ifdef CONFIG_TRACER_MAX_TRACE
- if (!tr->current_trace->use_max_tr)
+ if (!tr->allocated_snapshot)
goto out;
ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);
int tracing_open_generic_tr(struct inode *inode, struct file *filp);
int tracing_open_file_tr(struct inode *inode, struct file *filp);
int tracing_release_file_tr(struct inode *inode, struct file *filp);
+int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
bool tracing_is_disabled(void);
bool tracer_tracing_is_on(struct trace_array *tr);
void tracer_tracing_on(struct trace_array *tr);
{
int ret;
- ret = security_locked_down(LOCKDOWN_TRACEFS);
+ ret = tracing_open_file_tr(inode, file);
if (ret)
return ret;
+ /* Clear private_data to avoid warning in single_open() */
+ file->private_data = NULL;
return single_open(file, hist_show, file);
}
.open = event_hist_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = tracing_single_release_file_tr,
};
#ifdef CONFIG_HIST_TRIGGERS_DEBUG
{
int ret;
- ret = security_locked_down(LOCKDOWN_TRACEFS);
+ ret = tracing_open_file_tr(inode, file);
if (ret)
return ret;
+ /* Clear private_data to avoid warning in single_open() */
+ file->private_data = NULL;
return single_open(file, hist_debug_show, file);
}
.open = event_hist_debug_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = tracing_single_release_file_tr,
};
#endif
{
struct print_entry *field;
struct trace_seq *s = &iter->seq;
+ int max = iter->ent_size - offsetof(struct print_entry, buf);
trace_assign_type(field, iter->ent);
seq_print_ip_sym(s, field->ip, flags);
- trace_seq_printf(s, ": %s", field->buf);
+ trace_seq_printf(s, ": %.*s", max, field->buf);
return trace_handle_return(s);
}
struct trace_event *event)
{
struct print_entry *field;
+ int max = iter->ent_size - offsetof(struct print_entry, buf);
trace_assign_type(field, iter->ent);
- trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
+ trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf);
return trace_handle_return(&iter->seq);
}
endmenu
-config DEBUG_CREDENTIALS
- bool "Debug credential management"
- depends on DEBUG_KERNEL
- help
- Enable this to turn on some debug checking for credential
- management. The additional code keeps track of the number of
- pointers from task_structs to any given cred struct, and checks to
- see that this number never exceeds the usage count of the cred
- struct.
-
- Furthermore, if SELinux is enabled, this also checks that the
- security pointer in the cred struct is never seen to be invalid.
-
- If unsure, say N.
-
source "kernel/rcu/Kconfig.debug"
config DEBUG_WQ_FORCE_RR_CPU
if (!ctx)
return NULL;
+ init_completion(&ctx->kdamond_started);
+
ctx->attrs.sample_interval = 5 * 1000;
ctx->attrs.aggr_interval = 100 * 1000;
ctx->attrs.ops_update_interval = 60 * 1000 * 1000;
mutex_lock(&ctx->kdamond_lock);
if (!ctx->kdamond) {
err = 0;
+ reinit_completion(&ctx->kdamond_started);
ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
nr_running_ctxs);
if (IS_ERR(ctx->kdamond)) {
err = PTR_ERR(ctx->kdamond);
ctx->kdamond = NULL;
+ } else {
+ wait_for_completion(&ctx->kdamond_started);
}
}
mutex_unlock(&ctx->kdamond_lock);
pr_debug("kdamond (%d) starts\n", current->pid);
+ complete(&ctx->kdamond_started);
kdamond_init_intervals_sis(ctx);
if (ctx->ops.init)
}
VM_BUG_ON_FOLIO(folio_test_writeback(folio),
folio);
- truncate_inode_folio(mapping, folio);
+
+ if (!folio_test_large(folio)) {
+ truncate_inode_folio(mapping, folio);
+ } else if (truncate_inode_partial_folio(folio, lstart, lend)) {
+ /*
+ * If we split a page, reset the loop so
+ * that we pick up the new sub pages.
+ * Otherwise the THP was entirely
+ * dropped or the target range was
+ * zeroed, so just continue the loop as
+ * is.
+ */
+ if (!folio_test_large(folio)) {
+ folio_unlock(folio);
+ index = start;
+ break;
+ }
+ }
}
folio_unlock(folio);
}
else
VM_WARN_ON_ONCE(true);
+ WRITE_ONCE(lruvec->lrugen.seg, seg);
+ WRITE_ONCE(lruvec->lrugen.gen, new);
+
hlist_nulls_del_rcu(&lruvec->lrugen.list);
if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD)
pgdat->memcg_lru.nr_memcgs[old]--;
pgdat->memcg_lru.nr_memcgs[new]++;
- lruvec->lrugen.gen = new;
- WRITE_ONCE(lruvec->lrugen.seg, seg);
-
if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq))
WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
gen = get_memcg_gen(pgdat->memcg_lru.seq);
+ lruvec->lrugen.gen = gen;
+
hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]);
pgdat->memcg_lru.nr_memcgs[gen]++;
- lruvec->lrugen.gen = gen;
-
spin_unlock_irq(&pgdat->memcg_lru.lock);
}
}
}
/* protected */
- if (tier > tier_idx) {
+ if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) {
int hist = lru_hist_from_seq(lrugen->min_seq[type]);
gen = folio_inc_gen(lruvec, folio, false);
}
/* try to scrape all its memory if this memcg was deleted */
- *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
+ if (!mem_cgroup_online(memcg)) {
+ *nr_to_scan = total;
+ return false;
+ }
+
+ *nr_to_scan = total >> sc->priority;
/*
* The aging tries to be lazy to reduce the overhead, while the eviction
DEFINE_MAX_SEQ(lruvec);
if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
- return 0;
+ return -1;
if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
return nr_to_scan;
return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0;
}
-static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
{
+ int i;
+ enum zone_watermarks mark;
+
/* don't abort memcg reclaim to ensure fairness */
if (!root_reclaim(sc))
- return -1;
+ return false;
+
+ if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order)))
+ return true;
+
+ /* check the order to exclude compaction-induced reclaim */
+ if (!current_is_kswapd() || sc->order)
+ return false;
+
+ mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ?
+ WMARK_PROMO : WMARK_HIGH;
+
+ for (i = 0; i <= sc->reclaim_idx; i++) {
+ struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
+ unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH;
+
+ if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0))
+ return false;
+ }
- return max(sc->nr_to_reclaim, compact_gap(sc->order));
+ /* kswapd should abort if all eligible zones are safe */
+ return true;
}
static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
long nr_to_scan;
unsigned long scanned = 0;
- unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
int swappiness = get_swappiness(lruvec, sc);
/* clean file folios are more likely to exist */
if (scanned >= nr_to_scan)
break;
- if (sc->nr_reclaimed >= nr_to_reclaim)
+ if (should_abort_scan(lruvec, sc))
break;
cond_resched();
}
- /* whether try_to_inc_max_seq() was successful */
+ /* whether this lruvec should be rotated */
return nr_to_scan < 0;
}
bool success;
unsigned long scanned = sc->nr_scanned;
unsigned long reclaimed = sc->nr_reclaimed;
- int seg = lru_gen_memcg_seg(lruvec);
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
- /* see the comment on MEMCG_NR_GENS */
- if (!lruvec_is_sizable(lruvec, sc))
- return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
-
mem_cgroup_calculate_protection(NULL, memcg);
if (mem_cgroup_below_min(NULL, memcg))
if (mem_cgroup_below_low(NULL, memcg)) {
/* see the comment on MEMCG_NR_GENS */
- if (seg != MEMCG_LRU_TAIL)
+ if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL)
return MEMCG_LRU_TAIL;
memcg_memory_event(memcg, MEMCG_LOW);
flush_reclaim_state(sc);
- return success ? MEMCG_LRU_YOUNG : 0;
+ if (success && mem_cgroup_online(memcg))
+ return MEMCG_LRU_YOUNG;
+
+ if (!success && lruvec_is_sizable(lruvec, sc))
+ return 0;
+
+ /* one retry if offlined or too small */
+ return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ?
+ MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
}
#ifdef CONFIG_MEMCG
struct lruvec *lruvec;
struct lru_gen_folio *lrugen;
struct mem_cgroup *memcg;
- const struct hlist_nulls_node *pos;
- unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+ struct hlist_nulls_node *pos;
+ gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
bin = first_bin = get_random_u32_below(MEMCG_NR_BINS);
restart:
op = 0;
memcg = NULL;
- gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
rcu_read_lock();
}
mem_cgroup_put(memcg);
+ memcg = NULL;
+
+ if (gen != READ_ONCE(lrugen->gen))
+ continue;
lruvec = container_of(lrugen, struct lruvec, lrugen);
memcg = lruvec_memcg(lruvec);
rcu_read_lock();
- if (sc->nr_reclaimed >= nr_to_reclaim)
+ if (should_abort_scan(lruvec, sc))
break;
}
mem_cgroup_put(memcg);
- if (sc->nr_reclaimed >= nr_to_reclaim)
+ if (!is_a_nulls(pos))
return;
/* restart if raced with lru_gen_rotate_memcg() */
if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
return;
/*
- * Determine the initial priority based on ((total / MEMCG_NR_GENS) >>
- * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the
- * estimated reclaimed_to_scanned_ratio = inactive / total.
+ * Determine the initial priority based on
+ * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim,
+ * where reclaimed_to_scanned_ratio = inactive / total.
*/
reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
if (get_swappiness(lruvec, sc))
reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
- reclaimable /= MEMCG_NR_GENS;
-
/* round down reclaimable and round up sc->nr_to_reclaim */
priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
* 1. For pages accessed through page tables, hotter pages pushed out
* hot pages which refaulted immediately.
* 2. For pages accessed multiple times through file descriptors,
- * numbers of accesses might have been out of the range.
+ * they would have been protected by sort_folio().
*/
- if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
- folio_set_workingset(folio);
+ if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) {
+ set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset));
mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
}
unlock:
break;
}
case TIOCINQ: {
- /*
- * These two are safe on a single CPU system as only
- * user tasks fiddle here
- */
- struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+ struct sk_buff *skb;
long amount = 0;
+ spin_lock_irq(&sk->sk_receive_queue.lock);
+ skb = skb_peek(&sk->sk_receive_queue);
if (skb)
amount = skb->len - sizeof(struct ddpehdr);
+ spin_unlock_irq(&sk->sk_receive_queue.lock);
rc = put_user(amount, (int __user *)argp);
break;
}
case SIOCINQ:
{
struct sk_buff *skb;
+ int amount;
if (sock->state != SS_CONNECTED) {
error = -EINVAL;
goto done;
}
+ spin_lock_irq(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
- error = put_user(skb ? skb->len : 0,
- (int __user *)argp) ? -EFAULT : 0;
+ amount = skb ? skb->len : 0;
+ spin_unlock_irq(&sk->sk_receive_queue.lock);
+ error = put_user(amount, (int __user *)argp) ? -EFAULT : 0;
goto done;
}
case ATM_SETSC:
{
int max_clean = atomic_read(&tbl->gc_entries) -
READ_ONCE(tbl->gc_thresh2);
+ u64 tmax = ktime_get_ns() + NSEC_PER_MSEC;
unsigned long tref = jiffies - 5 * HZ;
struct neighbour *n, *tmp;
int shrunk = 0;
+ int loop = 0;
NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);
shrunk++;
if (shrunk >= max_clean)
break;
+ if (++loop == 16) {
+ if (ktime_get_ns() > tmax)
+ goto unlock;
+ loop = 0;
+ }
}
}
WRITE_ONCE(tbl->last_flush, jiffies);
-
+unlock:
write_unlock_bh(&tbl->lock);
return shrunk;
/* GSO partial only requires that we trim off any excess that
* doesn't fit into an MSS sized block, so take care of that
* now.
+ * Cap len to not accidentally hit GSO_BY_FRAGS.
*/
- partial_segs = len / mss;
+ partial_segs = min(len, GSO_BY_FRAGS - 1) / mss;
if (partial_segs > 1)
mss *= partial_segs;
else
* up to bandwidth of 18Gigabit/sec. 8) ]
*/
+/* Estimates max number of increments of remote peer TSval in
+ * a replay window (based on our current RTO estimation).
+ */
+static u32 tcp_tsval_replay(const struct sock *sk)
+{
+ /* If we use usec TS resolution,
+ * then expect the remote peer to use the same resolution.
+ */
+ if (tcp_sk(sk)->tcp_usec_ts)
+ return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ);
+
+ /* RFC 7323 recommends a TSval clock between 1ms and 1sec.
+ * We know that some OS (including old linux) can use 1200 Hz.
+ */
+ return inet_csk(sk)->icsk_rto * 1200 / HZ;
+}
+
static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
{
const struct tcp_sock *tp = tcp_sk(sk);
u32 seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
- return (/* 1. Pure ACK with correct sequence number. */
+ return /* 1. Pure ACK with correct sequence number. */
(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&
/* 2. ... and duplicate ACK. */
!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&
/* 4. ... and sits in replay window. */
- (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
+ (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <=
+ tcp_tsval_replay(sk);
}
static inline bool tcp_paws_discard(const struct sock *sk,
if (skb_still_in_host_queue(sk, skb))
return -EBUSY;
+start:
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+ TCP_SKB_CB(skb)->seq++;
+ goto start;
+ }
if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
WARN_ON_ONCE(1);
return -EINVAL;
pmsg->prefix_len = pinfo->prefix_len;
pmsg->prefix_type = pinfo->type;
pmsg->prefix_pad3 = 0;
- pmsg->prefix_flags = 0;
- if (pinfo->onlink)
- pmsg->prefix_flags |= IF_PREFIX_ONLINK;
- if (pinfo->autoconf)
- pmsg->prefix_flags |= IF_PREFIX_AUTOCONF;
+ pmsg->prefix_flags = pinfo->flags;
if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix))
goto nla_put_failure;
case TIOCINQ: {
struct sk_buff *skb;
long amount = 0L;
- /* These two are safe on a single CPU system as only user tasks fiddle here */
+
+ spin_lock_irq(&sk->sk_receive_queue.lock);
if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL)
amount = skb->len;
+ spin_unlock_irq(&sk->sk_receive_queue.lock);
return put_user(amount, (unsigned int __user *) argp);
}
!test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
}
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_get(struct nf_flowtable *ft)
+{
+ struct tcf_ct_flow_table *ct_ft =
+ container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+ tcf_ct_flow_table_get_ref(ct_ft);
+}
+
+static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_put(struct nf_flowtable *ft)
+{
+ struct tcf_ct_flow_table *ct_ft =
+ container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+ tcf_ct_flow_table_put(ct_ft);
+}
+
static struct nf_flowtable_type flowtable_ct = {
.gc = tcf_ct_flow_is_outdated,
.action = tcf_ct_flow_table_fill_actions,
+ .get = tcf_ct_nf_get,
+ .put = tcf_ct_nf_put,
.owner = THIS_MODULE,
};
return err;
}
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft)
+{
+ refcount_inc(&ct_ft->ref);
+}
+
static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
{
- struct flow_block_cb *block_cb, *tmp_cb;
struct tcf_ct_flow_table *ct_ft;
struct flow_block *block;
rwork);
nf_flow_table_free(&ct_ft->nf_ft);
- /* Remove any remaining callbacks before cleanup */
block = &ct_ft->nf_ft.flow_block;
down_write(&ct_ft->nf_ft.flow_block_lock);
- list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
- list_del(&block_cb->list);
- flow_block_cb_free(block_cb);
- }
+ WARN_ON(!list_empty(&block->cb_list));
up_write(&ct_ft->nf_ft.flow_block_lock);
kfree(ct_ft);
static struct cred machine_cred = {
.usage = ATOMIC_INIT(1),
-#ifdef CONFIG_DEBUG_CREDENTIALS
- .magic = CRED_MAGIC,
-#endif
};
/*
struct virtio_vsock_sock *vvs = vsk->trans;
s64 bytes;
- bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
+ bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
if (bytes < 0)
bytes = 0;
CMS_NOSMIMECAP | use_keyid |
use_signed_attrs),
"CMS_add1_signer");
- ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0,
+ ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) != 1,
"CMS_final");
#else
b = BIO_new_file(sig_file_name, "wb");
ERR(!b, "%s", sig_file_name);
#ifndef USE_PKCS7
- ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0,
+ ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) != 1,
"%s", sig_file_name);
#else
- ERR(i2d_PKCS7_bio(b, pkcs7) < 0,
+ ERR(i2d_PKCS7_bio(b, pkcs7) != 1,
"%s", sig_file_name);
#endif
BIO_free(b);
if (!raw_sig) {
#ifndef USE_PKCS7
- ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name);
+ ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) != 1, "%s", dest_name);
#else
- ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name);
+ ERR(i2d_PKCS7_bio(bd, pkcs7) != 1, "%s", dest_name);
#endif
} else {
BIO *b;
ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name);
ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name);
- ERR(BIO_free(bd) < 0, "%s", dest_name);
+ ERR(BIO_free(bd) != 1, "%s", dest_name);
/* Finally, if we're signing in place, replace the original. */
if (replace_orig)
struct inode_security_struct *isec;
u32 sid;
- validate_creds(cred);
-
if (unlikely(IS_PRIVATE(inode)))
return 0;
struct inode_security_struct *isec;
u32 sid;
- validate_creds(cred);
-
ad.type = LSM_AUDIT_DATA_DENTRY;
ad.u.dentry = dentry;
sid = cred_sid(cred);
if (!mask)
return 0;
- validate_creds(cred);
-
if (unlikely(IS_PRIVATE(inode)))
return 0;
SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1),
+ SND_PCI_QUIRK(0x1043, 0x86ae, "ASUS", 1), /* Z170 PRO */
+ SND_PCI_QUIRK(0x1043, 0x86c7, "ASUS", 1), /* Z170M PLUS */
SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1),
+ SND_PCI_QUIRK(0x8086, 0x2060, "Intel NUC5CPYB", 1),
SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1),
{}
};
SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
+ SND_PCI_QUIRK(0x103c, 0x84ae, "HP 15-db0403ng", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN),
SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360),
status = efi.get_variable(efi_name, &efi_guid, &attr,
&tas_priv->cali_data.total_sz,
tas_priv->cali_data.data);
- if (status != EFI_SUCCESS)
- return -EINVAL;
}
+ if (status != EFI_SUCCESS)
+ return -EINVAL;
tmp_val = (unsigned int *)tas_priv->cali_data.data;
tas2781_save_calibration(tas_priv);
out:
- if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) {
- /*If DSP FW fail, kcontrol won't be created */
- tasdevice_config_info_remove(tas_priv);
- tasdevice_dsp_remove(tas_priv);
- }
mutex_unlock(&tas_priv->codec_lock);
if (fmw)
release_firmware(fmw);
{
struct tasdevice_priv *tas_priv = dev_get_drvdata(dev);
struct hda_component *comps = master_data;
+ comps = &comps[tas_priv->index];
- if (comps[tas_priv->index].dev == dev)
- memset(&comps[tas_priv->index], 0, sizeof(*comps));
+ if (comps->dev == dev) {
+ comps->dev = NULL;
+ memset(comps->name, 0, sizeof(comps->name));
+ comps->playback_hook = NULL;
+ }
tasdevice_config_info_remove(tas_priv);
tasdevice_dsp_remove(tas_priv);
pm_runtime_put_autosuspend(tas_priv->dev);
+ tas2781_reset(tas_priv);
+
ret = component_add(tas_priv->dev, &tas2781_hda_comp_ops);
if (ret) {
dev_err(tas_priv->dev, "Register component failed: %d\n", ret);
pm_runtime_disable(tas_priv->dev);
- goto err;
}
- tas2781_reset(tas_priv);
err:
if (ret)
tas2781_hda_remove(&clt->dev);
*
* Yes, this is unfortunate. A better solution is in the works.
*/
-NORETURN(__invalid_creds)
NORETURN(__kunit_abort)
NORETURN(__module_put_and_kthread_exit)
NORETURN(__reiserfs_panic)
cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
cxl_core-y += config_check.o
cxl_core-y += cxl_core_test.o
+cxl_core-y += cxl_core_exports.o
obj-m += test/
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include "cxl.h"
+
+/* Exporting of cxl_core symbols that are only used by cxl_test */
+EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, CXL);
return 0;
dev_dbg(&port->dev, "%s commit\n", dev_name(&cxld->dev));
- if (port->commit_end + 1 != id) {
+ if (cxl_num_decoders_committed(port) != id) {
dev_dbg(&port->dev,
"%s: out of order commit, expected decoder%d.%d\n",
- dev_name(&cxld->dev), port->id, port->commit_end + 1);
+ dev_name(&cxld->dev), port->id,
+ cxl_num_decoders_committed(port));
return -EBUSY;
}
abs_objtree := $(realpath $(abs_objtree))
BUILD := $(abs_objtree)/kselftest
KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include
- KHDR_DIR := ${abs_objtree}/usr/include
else
BUILD := $(CURDIR)
abs_srctree := $(shell cd $(top_srcdir) && pwd)
KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include
- KHDR_DIR := ${abs_srctree}/usr/include
DEFAULT_INSTALL_HDR_PATH := 1
endif
# all isn't the first target in the file.
.DEFAULT_GOAL := all
-all: kernel_header_files
+all:
@ret=1; \
for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
ret=$$((ret * $$?)); \
done; exit $$ret;
-kernel_header_files:
- @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \
- if [ $$? -ne 0 ]; then \
- RED='\033[1;31m'; \
- NOCOLOR='\033[0m'; \
- echo; \
- echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \
- echo "Please run this and try again:"; \
- echo; \
- echo " cd $(top_srcdir)"; \
- echo " make headers"; \
- echo; \
- exit 1; \
- fi
-
-.PHONY: kernel_header_files
-
run_tests: all
@for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
CONFIG_CRYPTO_XXHASH=y
CONFIG_DCB=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
CONFIG_DEBUG_INFO_BTF=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_CRYPTO_XXHASH=y
CONFIG_DCB=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_DEFAULT_FQ_CODEL=y
selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST))))
top_srcdir = $(selfdir)/../../..
-ifeq ("$(origin O)", "command line")
- KBUILD_OUTPUT := $(O)
+ifeq ($(KHDR_INCLUDES),)
+KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include
endif
-ifneq ($(KBUILD_OUTPUT),)
- # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot
- # expand a shell special character '~'. We use a somewhat tedious way here.
- abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd)
- $(if $(abs_objtree),, \
- $(error failed to create output directory "$(KBUILD_OUTPUT)"))
- # $(realpath ...) resolves symlinks
- abs_objtree := $(realpath $(abs_objtree))
- KHDR_DIR := ${abs_objtree}/usr/include
-else
- abs_srctree := $(shell cd $(top_srcdir) && pwd)
- KHDR_DIR := ${abs_srctree}/usr/include
-endif
-
-KHDR_INCLUDES := -isystem $(KHDR_DIR)
-
# The following are built by lib.mk common compile rules.
# TEST_CUSTOM_PROGS should be used by tests that require
# custom build rule and prevent common build rule use.
TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
-all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \
- $(TEST_GEN_FILES)
-
-kernel_header_files:
- @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \
- if [ $$? -ne 0 ]; then \
- RED='\033[1;31m'; \
- NOCOLOR='\033[0m'; \
- echo; \
- echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \
- echo "Please run this and try again:"; \
- echo; \
- echo " cd $(top_srcdir)"; \
- echo " make headers"; \
- echo; \
- exit 1; \
- fi
-
-.PHONY: kernel_header_files
+all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
define RUN_TESTS
BASE_DIR="$(selfdir)"; \
{
int err;
+ ksft_print_header();
+
pagesize = getpagesize();
thpsize = read_pmd_pagesize();
if (thpsize)
ARRAY_SIZE(hugetlbsizes));
detect_huge_zeropage();
- ksft_print_header();
ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() +
ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() +
ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case());
projects / thirdparty / linux.git / commitdiff
