6.16.4-rc1 review

index 9c83753e4592..0bdcab2e5cf3 100644
@@ -55,6 +55,7 @@ int mlx5hws_cmd_flow_table_create(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE);
 	MLX5_SET(create_flow_table_in, in, table_type, ft_attr->type);
+	MLX5_SET(create_flow_table_in, in, uid, ft_attr->uid);
 
 	ft_ctx = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context);
 	MLX5_SET(flow_table_context, ft_ctx, level, ft_attr->level);

index fa6bff210266..122ccc671628 100644
@@ -36,6 +36,7 @@ struct mlx5hws_cmd_set_fte_attr {
 struct mlx5hws_cmd_ft_create_attr {
 	u8 type;
 	u8 level;
+	u16 uid;
 	bool rtc_valid;
 	bool decap_en;
 	bool reformat_en;

index bf4643d0ce17..47e3947e7b51 100644
@@ -267,6 +267,7 @@ static int mlx5_cmd_hws_create_flow_table(struct mlx5_flow_root_namespace *ns,
 
 	tbl_attr.type = MLX5HWS_TABLE_TYPE_FDB;
 	tbl_attr.level = ft_attr->level;
+	tbl_attr.uid = ft_attr->uid;
 	tbl = mlx5hws_table_create(ctx, &tbl_attr);
 	if (!tbl) {
 		mlx5_core_err(ns->dev, "Failed creating hws flow_table\n");

index ce28ee1c0e41..6000f2c641e0 100644
@@ -85,6 +85,7 @@ static int hws_matcher_create_end_ft_isolated(struct mlx5hws_matcher *matcher)
 
 	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
 					      tbl,
+					      0,
 					      &matcher->end_ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to create end flow table\n");

@@ -112,7 +113,9 @@ static int hws_matcher_create_end_ft(struct mlx5hws_matcher *matcher)
 	if (mlx5hws_matcher_is_isolated(matcher))
 		ret = hws_matcher_create_end_ft_isolated(matcher);
 	else
-		ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl,
+		ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+						      tbl,
+						      0,
 						      &matcher->end_ft_id);
 
 	if (ret) {

index d8ac6c196211..a2fe2f9e832d 100644
@@ -75,6 +75,7 @@ struct mlx5hws_context_attr {
 struct mlx5hws_table_attr {
 	enum mlx5hws_table_type type;
 	u32 level;
+	u16 uid;
 };
 
 enum mlx5hws_matcher_flow_src {

index 568f691733f3..6113383ae47b 100644
@@ -9,6 +9,7 @@ u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl)
 }
 
 static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl,
+					u16 uid,
 					struct mlx5hws_cmd_ft_create_attr *ft_attr)
 {
 	ft_attr->type = tbl->fw_ft_type;

@@ -16,7 +17,9 @@ static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl,
 		ft_attr->level = tbl->ctx->caps->fdb_ft.max_level - 1;
 	else
 		ft_attr->level = tbl->ctx->caps->nic_ft.max_level - 1;
+
 	ft_attr->rtc_valid = true;
+	ft_attr->uid = uid;
 }
 
 static void hws_table_set_cap_attr(struct mlx5hws_table *tbl,

@@ -119,12 +122,12 @@ static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32
 
 int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev,
 				    struct mlx5hws_table *tbl,
-				    u32 *ft_id)
+				    u16 uid, u32 *ft_id)
 {
 	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
 	int ret;
 
-	hws_table_init_next_ft_attr(tbl, &ft_attr);
+	hws_table_init_next_ft_attr(tbl, uid, &ft_attr);
 	hws_table_set_cap_attr(tbl, &ft_attr);
 
 	ret = mlx5hws_cmd_flow_table_create(mdev, &ft_attr, ft_id);

@@ -189,7 +192,10 @@ static int hws_table_init(struct mlx5hws_table *tbl)
 	}
 
 	mutex_lock(&ctx->ctrl_lock);
-	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &tbl->ft_id);
+	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+					      tbl,
+					      tbl->uid,
+					      &tbl->ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Failed to create flow table object\n");
 		mutex_unlock(&ctx->ctrl_lock);

@@ -239,6 +245,7 @@ struct mlx5hws_table *mlx5hws_table_create(struct mlx5hws_context *ctx,
 	tbl->ctx = ctx;
 	tbl->type = attr->type;
 	tbl->level = attr->level;
+	tbl->uid = attr->uid;
 
 	ret = hws_table_init(tbl);
 	if (ret) {

index 0400cce0c317..1246f9bd8422 100644
@@ -18,6 +18,7 @@ struct mlx5hws_table {
 	enum mlx5hws_table_type type;
 	u32 fw_ft_type;
 	u32 level;
+	u16 uid;
 	struct list_head matchers_list;
 	struct list_head tbl_list_node;
 	struct mlx5hws_default_miss default_miss;

@@ -47,7 +48,7 @@ u32 mlx5hws_table_get_res_fw_ft_type(enum mlx5hws_table_type tbl_type,
 
 int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev,
 				    struct mlx5hws_table *tbl,
-				    u32 *ft_id);
+				    u16 uid, u32 *ft_id);
 
 void mlx5hws_table_destroy_default_ft(struct mlx5hws_table *tbl,
 				      u32 ft_id);

index a4263137fef5..01d522b02947 100644
@@ -173,6 +173,8 @@ static void mlx5_ct_fs_hmfs_fill_rule_actions(struct mlx5_ct_fs_hmfs *fs_hmfs,
 
 	memset(rule_actions, 0, NUM_CT_HMFS_RULES * sizeof(*rule_actions));
 	rule_actions[0].action = mlx5_fc_get_hws_action(fs_hmfs->ctx, attr->counter);
+	rule_actions[0].counter.offset =
+		attr->counter->id - attr->counter->bulk->base_id;
 	/* Modify header is special, it may require extra arguments outside the action itself. */
 	if (mh_action->mh_data) {
 		rule_actions[1].modify_header.offset = mh_action->mh_data->offset;

index dd436bdff0f8..d03f5a8de58d 100644
@@ -311,6 +311,8 @@ static int lan865x_net_open(struct net_device *netdev)
 
 	phy_start(netdev->phydev);
 
+	netif_start_queue(netdev);
+
 	return 0;
 }
 

index d03f5a8de58d..84c41f193561 100644
@@ -32,6 +32,10 @@
 /* MAC Specific Addr 1 Top Reg */
 #define LAN865X_REG_MAC_H_SADDR1	0x00010023
 
+/* MAC TSU Timer Increment Register */
+#define LAN865X_REG_MAC_TSU_TIMER_INCR		0x00010077
+#define MAC_TSU_TIMER_INCR_COUNT_NANOSECONDS	0x0028
+
 struct lan865x_priv {
 	struct work_struct multicast_work;
 	struct net_device *netdev;

@@ -346,6 +350,21 @@ static int lan865x_probe(struct spi_device *spi)
 		goto free_netdev;
 	}
 
+	/* LAN865x Rev.B0/B1 configuration parameters from AN1760
+	 * As per the Configuration Application Note AN1760 published in the
+	 * link, https://www.microchip.com/en-us/application-notes/an1760
+	 * Revision F (DS60001760G - June 2024), configure the MAC to set time
+	 * stamping at the end of the Start of Frame Delimiter (SFD) and set the
+	 * Timer Increment reg to 40 ns to be used as a 25 MHz internal clock.
+	 */
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_TSU_TIMER_INCR,
+				    MAC_TSU_TIMER_INCR_COUNT_NANOSECONDS);
+	if (ret) {
+		dev_err(&spi->dev, "Failed to config TSU Timer Incr reg: %d\n",
+			ret);
+		goto oa_tc6_exit;
+	}
+
 	/* As per the point s3 in the below errata, SPI receive Ethernet frame
 	 * transfer may halt when starting the next frame in the same data block
 	 * (chunk) as the end of a previous frame. The RFA field should be

index e39f86d97002..a80b75f7b061 100644
@@ -27,6 +27,7 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 	struct table_info *next_table;
 	unsigned long tmp_insn_offset;
 	unsigned long tmp_rodata_offset;
+	bool is_valid_list = false;
 
 	rsec = find_section_by_name(file->elf, ".rela.discard.tablejump_annotate");
 	if (!rsec)

@@ -35,6 +36,12 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 	INIT_LIST_HEAD(&table_list);
 
 	for_each_reloc(rsec, reloc) {
+		if (reloc->sym->sec->rodata)
+			continue;
+
+		if (strcmp(insn->sec->name, reloc->sym->sec->name))
+			continue;
+
 		orig_table = malloc(sizeof(struct table_info));
 		if (!orig_table) {
 			WARN("malloc failed");

@@ -49,6 +56,22 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 
 		if (reloc_idx(reloc) + 1 == sec_num_entries(rsec))
 			break;
+
+		if (strcmp(insn->sec->name, (reloc + 1)->sym->sec->name)) {
+			list_for_each_entry(orig_table, &table_list, jump_info) {
+				if (orig_table->insn_offset == insn->offset) {
+					is_valid_list = true;
+					break;
+				}
+			}
+
+			if (!is_valid_list) {
+				list_del_init(&table_list);
+				continue;
+			}
+
+			break;
+		}
 	}
 
 	list_for_each_entry(orig_table, &table_list, jump_info) {

index e2f30ff9afde..a43ba7f9f987 100644
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/moduleloader.h>
 #include <linux/ftrace.h>
+#include <linux/sort.h>
 
 Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val)
 {

@@ -61,39 +62,38 @@ Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr v
 	return (Elf_Addr)&plt[nr];
 }
 
-static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y)
-{
-	return x->r_info == y->r_info && x->r_addend == y->r_addend;
-}
+#define cmp_3way(a, b)  ((a) < (b) ? -1 : (a) > (b))
 
-static bool duplicate_rela(const Elf_Rela *rela, int idx)
+static int compare_rela(const void *x, const void *y)
 {
-	int i;
+	int ret;
+	const Elf_Rela *rela_x = x, *rela_y = y;
 
-	for (i = 0; i < idx; i++) {
-		if (is_rela_equal(&rela[i], &rela[idx]))
-			return true;
-	}
+	ret = cmp_3way(rela_x->r_info, rela_y->r_info);
+	if (ret == 0)
+		ret = cmp_3way(rela_x->r_addend, rela_y->r_addend);
 
-	return false;
+	return ret;
 }
 
 static void count_max_entries(Elf_Rela *relas, int num,
 			      unsigned int *plts, unsigned int *gots)
 {
-	unsigned int i, type;
+	unsigned int i;
+
+	sort(relas, num, sizeof(Elf_Rela), compare_rela, NULL);
 
 	for (i = 0; i < num; i++) {
-		type = ELF_R_TYPE(relas[i].r_info);
-		switch (type) {
+		if (i && !compare_rela(&relas[i-1], &relas[i]))
+			continue;
+
+		switch (ELF_R_TYPE(relas[i].r_info)) {
 		case R_LARCH_SOP_PUSH_PLT_PCREL:
 		case R_LARCH_B26:
-			if (!duplicate_rela(relas, i))
-				(*plts)++;
+			(*plts)++;
 			break;
 		case R_LARCH_GOT_PC_HI20:
-			if (!duplicate_rela(relas, i))
-				(*gots)++;
+			(*gots)++;
 			break;
 		default:
 			break; /* Do nothing. */

index e17c4cadd04d..f44aabde805e 100644
@@ -107,8 +107,8 @@
 #define CS35L56_DSP1_PMEM_5114				0x3804FE8
 
 #define CS35L63_DSP1_FW_VER				CS35L56_DSP1_FW_VER
-#define CS35L63_DSP1_HALO_STATE				0x280396C
-#define CS35L63_DSP1_PM_CUR_STATE			0x28042C8
+#define CS35L63_DSP1_HALO_STATE				0x2803C04
+#define CS35L63_DSP1_PM_CUR_STATE			0x2804518
 #define CS35L63_PROTECTION_STATUS			0x340009C
 #define CS35L63_TRANSDUCER_ACTUAL_PS			0x34000F4
 #define CS35L63_MAIN_RENDER_USER_MUTE			0x3400020

index f44aabde805e..7c8bbe8ad1e2 100644
@@ -306,6 +306,7 @@ struct cs35l56_base {
 	struct gpio_desc *reset_gpio;
 	struct cs35l56_spi_payload *spi_payload_buf;
 	const struct cs35l56_fw_reg *fw_reg;
+	const struct cirrus_amp_cal_controls *calibration_controls;
 };
 
 static inline bool cs35l56_is_otp_register(unsigned int reg)

index ba653f6ccfae..850fcf385996 100644
@@ -838,6 +838,15 @@ const struct cirrus_amp_cal_controls cs35l56_calibration_controls = {
 };
 EXPORT_SYMBOL_NS_GPL(cs35l56_calibration_controls, "SND_SOC_CS35L56_SHARED");
 
+static const struct cirrus_amp_cal_controls cs35l63_calibration_controls = {
+	.alg_id =	0xbf210,
+	.mem_region =	WMFW_ADSP2_YM,
+	.ambient =	"CAL_AMBIENT",
+	.calr =		"CAL_R",
+	.status =	"CAL_STATUS",
+	.checksum =	"CAL_CHECKSUM",
+};
+
 int cs35l56_get_calibration(struct cs35l56_base *cs35l56_base)
 {
 	u64 silicon_uid = 0;

@@ -912,19 +921,31 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_read_prot_status, "SND_SOC_CS35L56_SHARED");
 void cs35l56_log_tuning(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_dsp)
 {
 	__be32 pid, sid, tid;
+	unsigned int alg_id;
 	int ret;
 
+	switch (cs35l56_base->type) {
+	case 0x54:
+	case 0x56:
+	case 0x57:
+		alg_id = 0x9f212;
+		break;
+	default:
+		alg_id = 0xbf212;
+		break;
+	}
+
 	scoped_guard(mutex, &cs_dsp->pwr_lock) {
 		ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_PRJCT_ID",
-							    WMFW_ADSP2_XM, 0x9f212),
+							    WMFW_ADSP2_XM, alg_id),
 					     0, &pid, sizeof(pid));
 		if (!ret)
 			ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_CHNNL_ID",
-								    WMFW_ADSP2_XM, 0x9f212),
+								    WMFW_ADSP2_XM, alg_id),
 						     0, &sid, sizeof(sid));
 		if (!ret)
 			ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_SNPSHT_ID",
-								    WMFW_ADSP2_XM, 0x9f212),
+								    WMFW_ADSP2_XM, alg_id),
 						     0, &tid, sizeof(tid));
 	}
 

@@ -974,8 +995,10 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 	case 0x35A54:
 	case 0x35A56:
 	case 0x35A57:
+		cs35l56_base->calibration_controls = &cs35l56_calibration_controls;
 		break;
 	case 0x35A630:
+		cs35l56_base->calibration_controls = &cs35l63_calibration_controls;
 		devid = devid >> 4;
 		break;
 	default:

index 1b42586794ad..76306282b2e6 100644
@@ -695,7 +695,7 @@ static int cs35l56_write_cal(struct cs35l56_private *cs35l56)
 		return ret;
 
 	ret = cs_amp_write_cal_coeffs(&cs35l56->dsp.cs_dsp,
-				      &cs35l56_calibration_controls,
+				      cs35l56->base.calibration_controls,
 				      &cs35l56->base.cal_data);
 
 	wm_adsp_stop(&cs35l56->dsp);

index fa9693af3722..d7fa12d287e0 100644
@@ -394,74 +394,6 @@ static int cs35l56_sdw_update_status(struct sdw_slave *peripheral,
 	return 0;
 }
 
-static int cs35l63_sdw_kick_divider(struct cs35l56_private *cs35l56,
-				    struct sdw_slave *peripheral)
-{
-	unsigned int curr_scale_reg, next_scale_reg;
-	int curr_scale, next_scale, ret;
-
-	if (!cs35l56->base.init_done)
-		return 0;
-
-	if (peripheral->bus->params.curr_bank) {
-		curr_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B1;
-		next_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B0;
-	} else {
-		curr_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B0;
-		next_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B1;
-	}
-
-	/*
-	 * Current clock scale value must be different to new value.
-	 * Modify current to guarantee this. If next still has the dummy
-	 * value we wrote when it was current, the core code has not set
-	 * a new scale so restore its original good value
-	 */
-	curr_scale = sdw_read_no_pm(peripheral, curr_scale_reg);
-	if (curr_scale < 0) {
-		dev_err(cs35l56->base.dev, "Failed to read current clock scale: %d\n", curr_scale);
-		return curr_scale;
-	}
-
-	next_scale = sdw_read_no_pm(peripheral, next_scale_reg);
-	if (next_scale < 0) {
-		dev_err(cs35l56->base.dev, "Failed to read next clock scale: %d\n", next_scale);
-		return next_scale;
-	}
-
-	if (next_scale == CS35L56_SDW_INVALID_BUS_SCALE) {
-		next_scale = cs35l56->old_sdw_clock_scale;
-		ret = sdw_write_no_pm(peripheral, next_scale_reg, next_scale);
-		if (ret < 0) {
-			dev_err(cs35l56->base.dev, "Failed to modify current clock scale: %d\n",
-				ret);
-			return ret;
-		}
-	}
-
-	cs35l56->old_sdw_clock_scale = curr_scale;
-	ret = sdw_write_no_pm(peripheral, curr_scale_reg, CS35L56_SDW_INVALID_BUS_SCALE);
-	if (ret < 0) {
-		dev_err(cs35l56->base.dev, "Failed to modify current clock scale: %d\n", ret);
-		return ret;
-	}
-
-	dev_dbg(cs35l56->base.dev, "Next bus scale: %#x\n", next_scale);
-
-	return 0;
-}
-
-static int cs35l56_sdw_bus_config(struct sdw_slave *peripheral,
-				  struct sdw_bus_params *params)
-{
-	struct cs35l56_private *cs35l56 = dev_get_drvdata(&peripheral->dev);
-
-	if ((cs35l56->base.type == 0x63) && (cs35l56->base.rev < 0xa1))
-		return cs35l63_sdw_kick_divider(cs35l56, peripheral);
-
-	return 0;
-}
-
 static int __maybe_unused cs35l56_sdw_clk_stop(struct sdw_slave *peripheral,
 					       enum sdw_clk_stop_mode mode,
 					       enum sdw_clk_stop_type type)

@@ -477,7 +409,6 @@ static const struct sdw_slave_ops cs35l56_sdw_ops = {
 	.read_prop = cs35l56_sdw_read_prop,
 	.interrupt_callback = cs35l56_sdw_interrupt,
 	.update_status = cs35l56_sdw_update_status,
-	.bus_config = cs35l56_sdw_bus_config,
 #ifdef DEBUG
 	.clk_stop = cs35l56_sdw_clk_stop,
 #endif

index bd77a57249d7..40a1800a4585 100644
@@ -20,8 +20,6 @@
 #define CS35L56_SDW_GEN_INT_MASK_1	0xc1
 #define CS35L56_SDW_INT_MASK_CODEC_IRQ	BIT(0)
 
-#define CS35L56_SDW_INVALID_BUS_SCALE	0xf
-
 #define CS35L56_RX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE)
 #define CS35L56_TX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE \
 			    | SNDRV_PCM_FMTBIT_S32_LE)

@@ -52,7 +50,6 @@ struct cs35l56_private {
 	u8 asp_slot_count;
 	bool tdm_mode;
 	bool sysclk_set;
-	u8 old_sdw_clock_scale;
 	u8 sdw_link_num;
 	u8 sdw_unique_id;
 };

index 1d073acd05a7..cea3de4dce8c 100644
@@ -530,6 +530,9 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l
 			 lowcore_address + sizeof(struct lowcore),
 			 POPULATE_LOWCORE);
 	for_each_physmem_usable_range(i, &start, &end) {
+		/* Do not map lowcore with identity mapping */
+		if (!start)
+			start = sizeof(struct lowcore);
 		pgtable_populate((unsigned long)__identity_va(start),
 				 (unsigned long)__identity_va(end),
 				 POPULATE_IDENTITY);

index a75f865d6fb9..3cf9894999da 100644
@@ -9,7 +9,7 @@
 
 static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s)
 {
-	int ipnum, cpu, cpuid, irq_index, irq_mask, irq;
+	int ipnum, cpu, cpuid, irq;
 	struct kvm_vcpu *vcpu;
 
 	for (irq = 0; irq < EIOINTC_IRQS; irq++) {

@@ -18,8 +18,6 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s)
 			ipnum = count_trailing_zeros(ipnum);
 			ipnum = (ipnum >= 0 && ipnum < 4) ? ipnum : 0;
 		}
-		irq_index = irq / 32;
-		irq_mask = BIT(irq & 0x1f);
 
 		cpuid = s->coremap.reg_u8[irq];
 		vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid);

@@ -27,16 +25,16 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s)
 			continue;
 
 		cpu = vcpu->vcpu_id;
-		if (!!(s->coreisr.reg_u32[cpu][irq_index] & irq_mask))
-			set_bit(irq, s->sw_coreisr[cpu][ipnum]);
+		if (test_bit(irq, (unsigned long *)s->coreisr.reg_u32[cpu]))
+			__set_bit(irq, s->sw_coreisr[cpu][ipnum]);
 		else
-			clear_bit(irq, s->sw_coreisr[cpu][ipnum]);
+			__clear_bit(irq, s->sw_coreisr[cpu][ipnum]);
 	}
 }
 
 static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 {
-	int ipnum, cpu, found, irq_index, irq_mask;
+	int ipnum, cpu, found;
 	struct kvm_vcpu *vcpu;
 	struct kvm_interrupt vcpu_irq;
 

@@ -48,19 +46,16 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 
 	cpu = s->sw_coremap[irq];
 	vcpu = kvm_get_vcpu(s->kvm, cpu);
-	irq_index = irq / 32;
-	irq_mask = BIT(irq & 0x1f);
-
 	if (level) {
 		/* if not enable return false */
-		if (((s->enable.reg_u32[irq_index]) & irq_mask) == 0)
+		if (!test_bit(irq, (unsigned long *)s->enable.reg_u32))
 			return;
-		s->coreisr.reg_u32[cpu][irq_index] |= irq_mask;
+		__set_bit(irq, (unsigned long *)s->coreisr.reg_u32[cpu]);
 		found = find_first_bit(s->sw_coreisr[cpu][ipnum], EIOINTC_IRQS);
-		set_bit(irq, s->sw_coreisr[cpu][ipnum]);
+		__set_bit(irq, s->sw_coreisr[cpu][ipnum]);
 	} else {
-		s->coreisr.reg_u32[cpu][irq_index] &= ~irq_mask;
-		clear_bit(irq, s->sw_coreisr[cpu][ipnum]);
+		__clear_bit(irq, (unsigned long *)s->coreisr.reg_u32[cpu]);
+		__clear_bit(irq, s->sw_coreisr[cpu][ipnum]);
 		found = find_first_bit(s->sw_coreisr[cpu][ipnum], EIOINTC_IRQS);
 	}
 

@@ -110,8 +105,8 @@ void eiointc_set_irq(struct loongarch_eiointc *s, int irq, int level)
 	unsigned long flags;
 	unsigned long *isr = (unsigned long *)s->isr.reg_u8;
 
-	level ? set_bit(irq, isr) : clear_bit(irq, isr);
 	spin_lock_irqsave(&s->lock, flags);
+	level ? __set_bit(irq, isr) : __clear_bit(irq, isr);
 	eiointc_update_irq(s, irq, level);
 	spin_unlock_irqrestore(&s->lock, flags);
 }

index 3cf9894999da..0207cfe1dbd6 100644
@@ -45,7 +45,12 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 	}
 
 	cpu = s->sw_coremap[irq];
-	vcpu = kvm_get_vcpu(s->kvm, cpu);
+	vcpu = kvm_get_vcpu_by_id(s->kvm, cpu);
+	if (unlikely(vcpu == NULL)) {
+		kvm_err("%s: invalid target cpu: %d\n", __func__, cpu);
+		return;
+	}
+
 	if (level) {
 		/* if not enable return false */
 		if (!test_bit(irq, (unsigned long *)s->enable.reg_u32))

index 6a13d2f44575..4859e320e3a1 100644
@@ -318,7 +318,7 @@ static int kvm_ipi_regs_access(struct kvm_device *dev,
 	cpu = (attr->attr >> 16) & 0x3ff;
 	addr = attr->attr & 0xff;
 
-	vcpu = kvm_get_vcpu(dev->kvm, cpu);
+	vcpu = kvm_get_vcpu_by_id(dev->kvm, cpu);
 	if (unlikely(vcpu == NULL)) {
 		kvm_err("%s: invalid target cpu: %d\n", __func__, cpu);
 		return -EINVAL;

index ac58964b2f08..7b941505a9d0 100644
@@ -398,7 +398,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	dma_addr_t dma;
 	u32 cmd_type;
 
-	while (budget-- > 0) {
+	while (likely(budget)) {
 		if (unlikely(!ixgbe_desc_unused(xdp_ring))) {
 			work_done = false;
 			break;

@@ -433,6 +433,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 		xdp_ring->next_to_use++;
 		if (xdp_ring->next_to_use == xdp_ring->count)
 			xdp_ring->next_to_use = 0;
+
+		budget--;
 	}
 
 	if (tx_desc) {

index 031c332f66c4..1b4465d6b2b7 100644
@@ -7115,6 +7115,13 @@ static int igc_probe(struct pci_dev *pdev,
 	adapter->port_num = hw->bus.func;
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
+	/* PCI config space info */
+	hw->vendor_id = pdev->vendor;
+	hw->device_id = pdev->device;
+	hw->revision_id = pdev->revision;
+	hw->subsystem_vendor_id = pdev->subsystem_vendor;
+	hw->subsystem_device_id = pdev->subsystem_device;
+
 	/* Disable ASPM L1.2 on I226 devices to avoid packet loss */
 	if (igc_is_device_id_i226(hw))
 		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);

@@ -7141,13 +7148,6 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->mem_start = pci_resource_start(pdev, 0);
 	netdev->mem_end = pci_resource_end(pdev, 0);
 
-	/* PCI config space info */
-	hw->vendor_id = pdev->vendor;
-	hw->device_id = pdev->device;
-	hw->revision_id = pdev->revision;
-	hw->subsystem_vendor_id = pdev->subsystem_vendor;
-	hw->subsystem_device_id = pdev->subsystem_device;
-
 	/* Copy the default MAC and PHY function pointers */
 	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
 	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));

index 7c142c17b3f6..adef7aa327ce 100644
@@ -2347,6 +2347,12 @@ static void ksz_update_port_member(struct ksz_device *dev, int port)
 		dev->dev_ops->cfg_port_member(dev, i, val | cpu_port);
 	}
 
+	/* HSR ports are setup once so need to use the assigned membership
+	 * when the port is enabled.
+	 */
+	if (!port_member && p->stp_state == BR_STATE_FORWARDING &&
+	    (dev->hsr_ports & BIT(port)))
+		port_member = dev->hsr_ports;
 	dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port);
 }
 

index 48dd8c88903f..aa9f31e4415a 100644
@@ -1747,7 +1747,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	ktime_t now = ktime_get();
 	struct cake_tin_data *b;
 	struct cake_flow *flow;
-	u32 idx;
+	u32 idx, tin;
 
 	/* choose flow to insert into */
 	idx = cake_classify(sch, &b, skb, q->flow_mode, &ret);

@@ -1757,6 +1757,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		__qdisc_drop(skb, to_free);
 		return ret;
 	}
+	tin = (u32)(b - q->tins);
 	idx--;
 	flow = &b->flows[idx];
 

@@ -1924,13 +1925,22 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		q->buffer_max_used = q->buffer_used;
 
 	if (q->buffer_used > q->buffer_limit) {
+		bool same_flow = false;
 		u32 dropped = 0;
+		u32 drop_id;
 
 		while (q->buffer_used > q->buffer_limit) {
 			dropped++;
-			cake_drop(sch, to_free);
+			drop_id = cake_drop(sch, to_free);
+
+			if ((drop_id >> 16) == tin &&
+			    (drop_id & 0xFFFF) == idx)
+				same_flow = true;
 		}
 		b->drop_overlimit += dropped;
+
+		if (same_flow)
+			return NET_XMIT_CN;
 	}
 	return NET_XMIT_SUCCESS;
 }

index c968ea763774..b5e40c51655a 100644
@@ -592,7 +592,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff)
  */
 static inline void htb_activate(struct htb_sched *q, struct htb_class *cl)
 {
-	WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen);
+	WARN_ON(cl->level || !cl->leaf.q);
 
 	if (!cl->prio_activity) {
 		cl->prio_activity = 1 << cl->prio;

index 8072183c33d3..a352247519be 100644
@@ -2139,14 +2139,14 @@ static int snd_utimer_create(struct snd_timer_uinfo *utimer_info,
 		goto err_take_id;
 	}
 
+	utimer->id = utimer_id;
+
 	utimer->name = kasprintf(GFP_KERNEL, "snd-utimer%d", utimer_id);
 	if (!utimer->name) {
 		err = -ENOMEM;
 		goto err_get_name;
 	}
 
-	utimer->id = utimer_id;
-
 	tid.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION;
 	tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL;
 	tid.card = -1;

index c6807e473ab7..a51305423d28 100644
@@ -2869,6 +2869,31 @@ void bond_3ad_update_lacp_rate(struct bonding *bond)
 	spin_unlock_bh(&bond->mode_lock);
 }
 
+/**
+ * bond_3ad_update_lacp_active - change the lacp active
+ * @bond: bonding struct
+ *
+ * Update actor_oper_port_state when lacp_active is modified.
+ */
+void bond_3ad_update_lacp_active(struct bonding *bond)
+{
+	struct port *port = NULL;
+	struct list_head *iter;
+	struct slave *slave;
+	int lacp_active;
+
+	lacp_active = bond->params.lacp_active;
+	spin_lock_bh(&bond->mode_lock);
+	bond_for_each_slave(bond, slave, iter) {
+		port = &(SLAVE_AD_INFO(slave)->port);
+		if (lacp_active)
+			port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY;
+		else
+			port->actor_oper_port_state &= ~LACP_STATE_LACP_ACTIVITY;
+	}
+	spin_unlock_bh(&bond->mode_lock);
+}
+
 size_t bond_3ad_stats_size(void)
 {
 	return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */

index 91893c29b899..28c53f1b1382 100644
@@ -1637,6 +1637,7 @@ static int bond_option_lacp_active_set(struct bonding *bond,
 	netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n",
 		   newval->string, newval->value);
 	bond->params.lacp_active = newval->value;
+	bond_3ad_update_lacp_active(bond);
 
 	return 0;
 }

index 2053cd8e788a..dba369a2cf27 100644
@@ -307,6 +307,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
 			 struct slave *slave);
 int bond_3ad_set_carrier(struct bonding *bond);
 void bond_3ad_update_lacp_rate(struct bonding *bond);
+void bond_3ad_update_lacp_active(struct bonding *bond);
 void bond_3ad_update_ad_actor_settings(struct bonding *bond);
 int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats);
 size_t bond_3ad_stats_size(void);

index a51305423d28..4c2560ae8866 100644
@@ -95,13 +95,13 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker);
 static void ad_mux_machine(struct port *port, bool *update_slave_arr);
 static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port);
 static void ad_tx_machine(struct port *port);
-static void ad_periodic_machine(struct port *port, struct bond_params *bond_params);
+static void ad_periodic_machine(struct port *port);
 static void ad_port_selection_logic(struct port *port, bool *update_slave_arr);
 static void ad_agg_selection_logic(struct aggregator *aggregator,
 				   bool *update_slave_arr);
 static void ad_clear_agg(struct aggregator *aggregator);
 static void ad_initialize_agg(struct aggregator *aggregator);
-static void ad_initialize_port(struct port *port, int lacp_fast);
+static void ad_initialize_port(struct port *port, const struct bond_params *bond_params);
 static void ad_enable_collecting(struct port *port);
 static void ad_disable_distributing(struct port *port,
 				    bool *update_slave_arr);

@@ -1296,10 +1296,16 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			 * case of EXPIRED even if LINK_DOWN didn't arrive for
 			 * the port.
 			 */
-			port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION;
 			port->sm_vars &= ~AD_PORT_MATCHED;
+			/* Based on IEEE 8021AX-2014, Figure 6-18 - Receive
+			 * machine state diagram, the statue should be
+			 * Partner_Oper_Port_State.Synchronization = FALSE;
+			 * Partner_Oper_Port_State.LACP_Timeout = Short Timeout;
+			 * start current_while_timer(Short Timeout);
+			 * Actor_Oper_Port_State.Expired = TRUE;
+			 */
+			port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION;
 			port->partner_oper.port_state |= LACP_STATE_LACP_TIMEOUT;
-			port->partner_oper.port_state |= LACP_STATE_LACP_ACTIVITY;
 			port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT));
 			port->actor_oper_port_state |= LACP_STATE_EXPIRED;
 			port->sm_vars |= AD_PORT_CHURNED;

@@ -1405,11 +1411,10 @@ static void ad_tx_machine(struct port *port)
 /**
  * ad_periodic_machine - handle a port's periodic state machine
  * @port: the port we're looking at
- * @bond_params: bond parameters we will use
  *
  * Turn ntt flag on priodically to perform periodic transmission of lacpdu's.
  */
-static void ad_periodic_machine(struct port *port, struct bond_params *bond_params)
+static void ad_periodic_machine(struct port *port)
 {
 	periodic_states_t last_state;
 

@@ -1418,8 +1423,7 @@ static void ad_periodic_machine(struct port *port, struct bond_params *bond_para
 
 	/* check if port was reinitialized */
 	if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) ||
-	    (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) ||
-	    !bond_params->lacp_active) {
+	    (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY))) {
 		port->sm_periodic_state = AD_NO_PERIODIC;
 	}
 	/* check if state machine should change state */

@@ -1943,16 +1947,16 @@ static void ad_initialize_agg(struct aggregator *aggregator)
 /**
  * ad_initialize_port - initialize a given port's parameters
  * @port: the port we're looking at
- * @lacp_fast: boolean. whether fast periodic should be used
+ * @bond_params: bond parameters we will use
  */
-static void ad_initialize_port(struct port *port, int lacp_fast)
+static void ad_initialize_port(struct port *port, const struct bond_params *bond_params)
 {
 	static const struct port_params tmpl = {
 		.system_priority = 0xffff,
 		.key             = 1,
 		.port_number     = 1,
 		.port_priority   = 0xff,
-		.port_state      = 1,
+		.port_state      = 0,
 	};
 	static const struct lacpdu lacpdu = {
 		.subtype		= 0x01,

@@ -1970,12 +1974,14 @@ static void ad_initialize_port(struct port *port, int lacp_fast)
 		port->actor_port_priority = 0xff;
 		port->actor_port_aggregator_identifier = 0;
 		port->ntt = false;
-		port->actor_admin_port_state = LACP_STATE_AGGREGATION |
-					       LACP_STATE_LACP_ACTIVITY;
-		port->actor_oper_port_state  = LACP_STATE_AGGREGATION |
-					       LACP_STATE_LACP_ACTIVITY;
+		port->actor_admin_port_state = LACP_STATE_AGGREGATION;
+		port->actor_oper_port_state  = LACP_STATE_AGGREGATION;
+		if (bond_params->lacp_active) {
+			port->actor_admin_port_state |= LACP_STATE_LACP_ACTIVITY;
+			port->actor_oper_port_state  |= LACP_STATE_LACP_ACTIVITY;
+		}
 
-		if (lacp_fast)
+		if (bond_params->lacp_fast)
 			port->actor_oper_port_state |= LACP_STATE_LACP_TIMEOUT;
 
 		memcpy(&port->partner_admin, &tmpl, sizeof(tmpl));

@@ -2187,7 +2193,7 @@ void bond_3ad_bind_slave(struct slave *slave)
 		/* port initialization */
 		port = &(SLAVE_AD_INFO(slave)->port);
 
-		ad_initialize_port(port, bond->params.lacp_fast);
+		ad_initialize_port(port, &bond->params);
 
 		port->slave = slave;
 		port->actor_port_number = SLAVE_AD_INFO(slave)->id;

@@ -2499,7 +2505,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		}
 
 		ad_rx_machine(NULL, port);
-		ad_periodic_machine(port, &bond->params);
+		ad_periodic_machine(port);
 		ad_port_selection_logic(port, &update_slave_arr);
 		ad_mux_machine(port, &update_slave_arr);
 		ad_tx_machine(port);

index 7832fe8fc202..af6e4d4c0ece 100644
@@ -726,10 +726,8 @@ static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe,
 			continue;
 		}
 
-		if (commit_done || !airoha_ppe_foe_compare_entry(e, hwe)) {
-			e->hash = 0xffff;
+		if (!airoha_ppe_foe_compare_entry(e, hwe))
 			continue;
-		}
 
 		airoha_ppe_foe_commit_entry(ppe, &e->data, hash);
 		commit_done = true;

index d68da9e92e1e..9483c529c958 100644
@@ -7229,22 +7229,16 @@ static void bfq_init_root_group(struct bfq_group *root_group,
 	root_group->sched_data.bfq_class_idle_last_service = jiffies;
 }
 
-static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
+static int bfq_init_queue(struct request_queue *q, struct elevator_queue *eq)
 {
 	struct bfq_data *bfqd;
-	struct elevator_queue *eq;
 	unsigned int i;
 	struct blk_independent_access_ranges *ia_ranges = q->disk->ia_ranges;
 
-	eq = elevator_alloc(q, e);
-	if (!eq)
-		return -ENOMEM;
-
 	bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
-	if (!bfqd) {
-		kobject_put(&eq->kobj);
+	if (!bfqd)
 		return -ENOMEM;
-	}
+
 	eq->elevator_data = bfqd;
 
 	spin_lock_irq(&q->queue_lock);

@@ -7402,7 +7396,6 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 
 out_free:
 	kfree(bfqd);
-	kobject_put(&eq->kobj);
 	return -ENOMEM;
 }
 

index 55a0fd105147..359e0704e09b 100644
@@ -475,10 +475,14 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth,
 				   BLKDEV_DEFAULT_RQ);
 
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
 	if (blk_mq_is_shared_tags(flags)) {
 		ret = blk_mq_init_sched_shared_tags(q);
 		if (ret)
-			return ret;
+			goto err_put_elevator;
 	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {

@@ -487,7 +491,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 			goto err_free_map_and_rqs;
 	}
 
-	ret = e->ops.init_sched(q, e);
+	ret = e->ops.init_sched(q, eq);
 	if (ret)
 		goto err_free_map_and_rqs;
 

@@ -508,7 +512,8 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 err_free_map_and_rqs:
 	blk_mq_sched_free_rqs(q);
 	blk_mq_sched_tags_teardown(q, flags);
-
+err_put_elevator:
+	kobject_put(&eq->kobj);
 	q->elevator = NULL;
 	return ret;
 }

index 88f8f36bed98..939b0c590fbe 100644
@@ -148,7 +148,6 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
 
 	return eq;
 }
-EXPORT_SYMBOL(elevator_alloc);
 
 static void elevator_release(struct kobject *kobj)
 {

index a07ce773a38f..a4de5f9ad790 100644
@@ -24,7 +24,7 @@ struct blk_mq_alloc_data;
 struct blk_mq_hw_ctx;
 
 struct elevator_mq_ops {
-	int (*init_sched)(struct request_queue *, struct elevator_type *);
+	int (*init_sched)(struct request_queue *, struct elevator_queue *);
 	void (*exit_sched)(struct elevator_queue *);
 	int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
 	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);

index bfd9a40bb33d..70cbc7b2deb4 100644
@@ -399,20 +399,13 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
 	return ERR_PTR(ret);
 }
 
-static int kyber_init_sched(struct request_queue *q, struct elevator_type *e)
+static int kyber_init_sched(struct request_queue *q, struct elevator_queue *eq)
 {
 	struct kyber_queue_data *kqd;
-	struct elevator_queue *eq;
-
-	eq = elevator_alloc(q, e);
-	if (!eq)
-		return -ENOMEM;
 
 	kqd = kyber_queue_data_alloc(q);
-	if (IS_ERR(kqd)) {
-		kobject_put(&eq->kobj);
+	if (IS_ERR(kqd))
 		return PTR_ERR(kqd);
-	}
 
 	blk_stat_enable_accounting(q);
 

index 9ab6c6256695..b9b7cdf1d3c9 100644
@@ -554,20 +554,14 @@ static void dd_exit_sched(struct elevator_queue *e)
 /*
  * initialize elevator private data (deadline_data).
  */
-static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
+static int dd_init_sched(struct request_queue *q, struct elevator_queue *eq)
 {
 	struct deadline_data *dd;
-	struct elevator_queue *eq;
 	enum dd_prio prio;
-	int ret = -ENOMEM;
-
-	eq = elevator_alloc(q, e);
-	if (!eq)
-		return ret;
 
 	dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
 	if (!dd)
-		goto put_eq;
+		return -ENOMEM;
 
 	eq->elevator_data = dd;
 

@@ -594,10 +588,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
 
 	q->elevator = eq;
 	return 0;
-
-put_eq:
-	kobject_put(&eq->kobj);
-	return ret;
 }
 
 /*

index 359e0704e09b..2d6d1ebdd8fb 100644
@@ -374,64 +374,17 @@ bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge);
 
-static int blk_mq_sched_alloc_map_and_rqs(struct request_queue *q,
-					  struct blk_mq_hw_ctx *hctx,
-					  unsigned int hctx_idx)
-{
-	if (blk_mq_is_shared_tags(q->tag_set->flags)) {
-		hctx->sched_tags = q->sched_shared_tags;
-		return 0;
-	}
-
-	hctx->sched_tags = blk_mq_alloc_map_and_rqs(q->tag_set, hctx_idx,
-						    q->nr_requests);
-
-	if (!hctx->sched_tags)
-		return -ENOMEM;
-	return 0;
-}
-
-static void blk_mq_exit_sched_shared_tags(struct request_queue *queue)
-{
-	blk_mq_free_rq_map(queue->sched_shared_tags);
-	queue->sched_shared_tags = NULL;
-}
-
 /* called in queue's release handler, tagset has gone away */
 static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int flags)
 {
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
 
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (hctx->sched_tags) {
-			if (!blk_mq_is_shared_tags(flags))
-				blk_mq_free_rq_map(hctx->sched_tags);
-			hctx->sched_tags = NULL;
-		}
-	}
+	queue_for_each_hw_ctx(q, hctx, i)
+		hctx->sched_tags = NULL;
 
 	if (blk_mq_is_shared_tags(flags))
-		blk_mq_exit_sched_shared_tags(q);
-}
-
-static int blk_mq_init_sched_shared_tags(struct request_queue *queue)
-{
-	struct blk_mq_tag_set *set = queue->tag_set;
-
-	/*
-	 * Set initial depth at max so that we don't need to reallocate for
-	 * updating nr_requests.
-	 */
-	queue->sched_shared_tags = blk_mq_alloc_map_and_rqs(set,
-						BLK_MQ_NO_HCTX_IDX,
-						MAX_SCHED_RQ);
-	if (!queue->sched_shared_tags)
-		return -ENOMEM;
-
-	blk_mq_tag_update_sched_shared_tags(queue);
-
-	return 0;
+		q->sched_shared_tags = NULL;
 }
 
 void blk_mq_sched_reg_debugfs(struct request_queue *q)

@@ -458,8 +411,75 @@ void blk_mq_sched_unreg_debugfs(struct request_queue *q)
 	mutex_unlock(&q->debugfs_mutex);
 }
 
+void blk_mq_free_sched_tags(struct elevator_tags *et,
+		struct blk_mq_tag_set *set)
+{
+	unsigned long i;
+
+	/* Shared tags are stored at index 0 in @tags. */
+	if (blk_mq_is_shared_tags(set->flags))
+		blk_mq_free_map_and_rqs(set, et->tags[0], BLK_MQ_NO_HCTX_IDX);
+	else {
+		for (i = 0; i < et->nr_hw_queues; i++)
+			blk_mq_free_map_and_rqs(set, et->tags[i], i);
+	}
+
+	kfree(et);
+}
+
+struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set,
+		unsigned int nr_hw_queues)
+{
+	unsigned int nr_tags;
+	int i;
+	struct elevator_tags *et;
+	gfp_t gfp = GFP_NOIO | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY;
+
+	if (blk_mq_is_shared_tags(set->flags))
+		nr_tags = 1;
+	else
+		nr_tags = nr_hw_queues;
+
+	et = kmalloc(sizeof(struct elevator_tags) +
+			nr_tags * sizeof(struct blk_mq_tags *), gfp);
+	if (!et)
+		return NULL;
+	/*
+	 * Default to double of smaller one between hw queue_depth and
+	 * 128, since we don't split into sync/async like the old code
+	 * did. Additionally, this is a per-hw queue depth.
+	 */
+	et->nr_requests = 2 * min_t(unsigned int, set->queue_depth,
+			BLKDEV_DEFAULT_RQ);
+	et->nr_hw_queues = nr_hw_queues;
+
+	if (blk_mq_is_shared_tags(set->flags)) {
+		/* Shared tags are stored at index 0 in @tags. */
+		et->tags[0] = blk_mq_alloc_map_and_rqs(set, BLK_MQ_NO_HCTX_IDX,
+					MAX_SCHED_RQ);
+		if (!et->tags[0])
+			goto out;
+	} else {
+		for (i = 0; i < et->nr_hw_queues; i++) {
+			et->tags[i] = blk_mq_alloc_map_and_rqs(set, i,
+					et->nr_requests);
+			if (!et->tags[i])
+				goto out_unwind;
+		}
+	}
+
+	return et;
+out_unwind:
+	while (--i >= 0)
+		blk_mq_free_map_and_rqs(set, et->tags[i], i);
+out:
+	kfree(et);
+	return NULL;
+}
+
 /* caller must have a reference to @e, will grab another one if successful */
-int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e,
+		struct elevator_tags *et)
 {
 	unsigned int flags = q->tag_set->flags;
 	struct blk_mq_hw_ctx *hctx;

@@ -467,40 +487,33 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	unsigned long i;
 	int ret;
 
-	/*
-	 * Default to double of smaller one between hw queue_depth and 128,
-	 * since we don't split into sync/async like the old code did.
-	 * Additionally, this is a per-hw queue depth.
-	 */
-	q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth,
-				   BLKDEV_DEFAULT_RQ);
-
-	eq = elevator_alloc(q, e);
+	eq = elevator_alloc(q, e, et);
 	if (!eq)
 		return -ENOMEM;
 
+	q->nr_requests = et->nr_requests;
+
 	if (blk_mq_is_shared_tags(flags)) {
-		ret = blk_mq_init_sched_shared_tags(q);
-		if (ret)
-			goto err_put_elevator;
+		/* Shared tags are stored at index 0 in @et->tags. */
+		q->sched_shared_tags = et->tags[0];
+		blk_mq_tag_update_sched_shared_tags(q);
 	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		ret = blk_mq_sched_alloc_map_and_rqs(q, hctx, i);
-		if (ret)
-			goto err_free_map_and_rqs;
+		if (blk_mq_is_shared_tags(flags))
+			hctx->sched_tags = q->sched_shared_tags;
+		else
+			hctx->sched_tags = et->tags[i];
 	}
 
 	ret = e->ops.init_sched(q, eq);
 	if (ret)
-		goto err_free_map_and_rqs;
+		goto out;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (e->ops.init_hctx) {
 			ret = e->ops.init_hctx(hctx, i);
 			if (ret) {
-				eq = q->elevator;
-				blk_mq_sched_free_rqs(q);
 				blk_mq_exit_sched(q, eq);
 				kobject_put(&eq->kobj);
 				return ret;

@@ -509,10 +522,8 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	}
 	return 0;
 
-err_free_map_and_rqs:
-	blk_mq_sched_free_rqs(q);
+out:
 	blk_mq_sched_tags_teardown(q, flags);
-err_put_elevator:
 	kobject_put(&eq->kobj);
 	q->elevator = NULL;
 	return ret;

index 1326526bb733..0cde00cd1c47 100644
@@ -18,10 +18,16 @@ void __blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 
-int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e,
+		struct elevator_tags *et);
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
 void blk_mq_sched_free_rqs(struct request_queue *q);
 
+struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set,
+		unsigned int nr_hw_queues);
+void blk_mq_free_sched_tags(struct elevator_tags *et,
+		struct blk_mq_tag_set *set);
+
 static inline void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {
 	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))

index 939b0c590fbe..e9dc837b7b70 100644
@@ -54,6 +54,8 @@ struct elv_change_ctx {
 	struct elevator_queue *old;
 	/* for registering new elevator */
 	struct elevator_queue *new;
+	/* holds sched tags data */
+	struct elevator_tags *et;
 };
 
 static DEFINE_SPINLOCK(elv_list_lock);

@@ -132,7 +134,7 @@ static struct elevator_type *elevator_find_get(const char *name)
 static const struct kobj_type elv_ktype;
 
 struct elevator_queue *elevator_alloc(struct request_queue *q,
-				  struct elevator_type *e)
+		struct elevator_type *e, struct elevator_tags *et)
 {
 	struct elevator_queue *eq;
 

@@ -145,6 +147,7 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
 	kobject_init(&eq->kobj, &elv_ktype);
 	mutex_init(&eq->sysfs_lock);
 	hash_init(eq->hash);
+	eq->et = et;
 
 	return eq;
 }

@@ -165,7 +168,6 @@ static void elevator_exit(struct request_queue *q)
 	lockdep_assert_held(&q->elevator_lock);
 
 	ioc_clear_queue(q);
-	blk_mq_sched_free_rqs(q);
 
 	mutex_lock(&e->sysfs_lock);
 	blk_mq_exit_sched(q, e);

@@ -591,7 +593,7 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx)
 	}
 
 	if (new_e) {
-		ret = blk_mq_init_sched(q, new_e);
+		ret = blk_mq_init_sched(q, new_e, ctx->et);
 		if (ret)
 			goto out_unfreeze;
 		ctx->new = q->elevator;

@@ -626,8 +628,10 @@ static void elv_exit_and_release(struct request_queue *q)
 	elevator_exit(q);
 	mutex_unlock(&q->elevator_lock);
 	blk_mq_unfreeze_queue(q, memflags);
-	if (e)
+	if (e) {
+		blk_mq_free_sched_tags(e->et, q->tag_set);
 		kobject_put(&e->kobj);
+	}
 }
 
 static int elevator_change_done(struct request_queue *q,

@@ -640,6 +644,7 @@ static int elevator_change_done(struct request_queue *q,
 				&ctx->old->flags);
 
 		elv_unregister_queue(q, ctx->old);
+		blk_mq_free_sched_tags(ctx->old->et, q->tag_set);
 		kobject_put(&ctx->old->kobj);
 		if (enable_wbt)
 			wbt_enable_default(q->disk);

@@ -658,9 +663,16 @@ static int elevator_change_done(struct request_queue *q,
 static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
 {
 	unsigned int memflags;
+	struct blk_mq_tag_set *set = q->tag_set;
 	int ret = 0;
 
-	lockdep_assert_held(&q->tag_set->update_nr_hwq_lock);
+	lockdep_assert_held(&set->update_nr_hwq_lock);
+
+	if (strncmp(ctx->name, "none", 4)) {
+		ctx->et = blk_mq_alloc_sched_tags(set, set->nr_hw_queues);
+		if (!ctx->et)
+			return -ENOMEM;
+	}
 
 	memflags = blk_mq_freeze_queue(q);
 	/*

@@ -680,6 +692,11 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
 	blk_mq_unfreeze_queue(q, memflags);
 	if (!ret)
 		ret = elevator_change_done(q, ctx);
+	/*
+	 * Free sched tags if it's allocated but we couldn't switch elevator.
+	 */
+	if (ctx->et && !ctx->new)
+		blk_mq_free_sched_tags(ctx->et, set);
 
 	return ret;
 }

@@ -690,6 +707,7 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
  */
 void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e)
 {
+	struct blk_mq_tag_set *set = q->tag_set;
 	struct elv_change_ctx ctx = {};
 	int ret = -ENODEV;
 

@@ -697,15 +715,25 @@ void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e)
 
 	if (e && !blk_queue_dying(q) && blk_queue_registered(q)) {
 		ctx.name = e->elevator_name;
-
+		ctx.et = blk_mq_alloc_sched_tags(set, set->nr_hw_queues);
+		if (!ctx.et) {
+			WARN_ON_ONCE(1);
+			goto unfreeze;
+		}
 		mutex_lock(&q->elevator_lock);
 		/* force to reattach elevator after nr_hw_queue is updated */
 		ret = elevator_switch(q, &ctx);
 		mutex_unlock(&q->elevator_lock);
 	}
+unfreeze:
 	blk_mq_unfreeze_queue_nomemrestore(q);
 	if (!ret)
 		WARN_ON_ONCE(elevator_change_done(q, &ctx));
+	/*
+	 * Free sched tags if it's allocated but we couldn't switch elevator.
+	 */
+	if (ctx.et && !ctx.new)
+		blk_mq_free_sched_tags(ctx.et, set);
 }
 
 /*

index a4de5f9ad790..adc5c157e17e 100644
@@ -23,6 +23,15 @@ enum elv_merge {
 struct blk_mq_alloc_data;
 struct blk_mq_hw_ctx;
 
+struct elevator_tags {
+	/* num. of hardware queues for which tags are allocated */
+	unsigned int nr_hw_queues;
+	/* depth used while allocating tags */
+	unsigned int nr_requests;
+	/* shared tag is stored at index 0 */
+	struct blk_mq_tags *tags[];
+};
+
 struct elevator_mq_ops {
 	int (*init_sched)(struct request_queue *, struct elevator_queue *);
 	void (*exit_sched)(struct elevator_queue *);

@@ -113,6 +122,7 @@ struct request *elv_rqhash_find(struct request_queue *q, sector_t offset);
 struct elevator_queue
 {
 	struct elevator_type *type;
+	struct elevator_tags *et;
 	void *elevator_data;
 	struct kobject kobj;
 	struct mutex sysfs_lock;

@@ -152,8 +162,8 @@ ssize_t elv_iosched_show(struct gendisk *disk, char *page);
 ssize_t elv_iosched_store(struct gendisk *disk, const char *page, size_t count);
 
 extern bool elv_bio_merge_ok(struct request *, struct bio *);
-extern struct elevator_queue *elevator_alloc(struct request_queue *,
-					struct elevator_type *);
+struct elevator_queue *elevator_alloc(struct request_queue *,
+		struct elevator_type *, struct elevator_tags *);
 
 /*
  * Helper functions.

index 2d6d1ebdd8fb..e2ce4a28e6c9 100644
@@ -427,6 +427,32 @@ void blk_mq_free_sched_tags(struct elevator_tags *et,
 	kfree(et);
 }
 
+void blk_mq_free_sched_tags_batch(struct xarray *et_table,
+		struct blk_mq_tag_set *set)
+{
+	struct request_queue *q;
+	struct elevator_tags *et;
+
+	lockdep_assert_held_write(&set->update_nr_hwq_lock);
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		/*
+		 * Accessing q->elevator without holding q->elevator_lock is
+		 * safe because we're holding here set->update_nr_hwq_lock in
+		 * the writer context. So, scheduler update/switch code (which
+		 * acquires the same lock but in the reader context) can't run
+		 * concurrently.
+		 */
+		if (q->elevator) {
+			et = xa_load(et_table, q->id);
+			if (unlikely(!et))
+				WARN_ON_ONCE(1);
+			else
+				blk_mq_free_sched_tags(et, set);
+		}
+	}
+}
+
 struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set,
 		unsigned int nr_hw_queues)
 {

@@ -477,6 +503,45 @@ struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set,
 	return NULL;
 }
 
+int blk_mq_alloc_sched_tags_batch(struct xarray *et_table,
+		struct blk_mq_tag_set *set, unsigned int nr_hw_queues)
+{
+	struct request_queue *q;
+	struct elevator_tags *et;
+	gfp_t gfp = GFP_NOIO | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY;
+
+	lockdep_assert_held_write(&set->update_nr_hwq_lock);
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		/*
+		 * Accessing q->elevator without holding q->elevator_lock is
+		 * safe because we're holding here set->update_nr_hwq_lock in
+		 * the writer context. So, scheduler update/switch code (which
+		 * acquires the same lock but in the reader context) can't run
+		 * concurrently.
+		 */
+		if (q->elevator) {
+			et = blk_mq_alloc_sched_tags(set, nr_hw_queues);
+			if (!et)
+				goto out_unwind;
+			if (xa_insert(et_table, q->id, et, gfp))
+				goto out_free_tags;
+		}
+	}
+	return 0;
+out_free_tags:
+	blk_mq_free_sched_tags(et, set);
+out_unwind:
+	list_for_each_entry_continue_reverse(q, &set->tag_list, tag_set_list) {
+		if (q->elevator) {
+			et = xa_load(et_table, q->id);
+			if (et)
+				blk_mq_free_sched_tags(et, set);
+		}
+	}
+	return -ENOMEM;
+}
+
 /* caller must have a reference to @e, will grab another one if successful */
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e,
 		struct elevator_tags *et)

index 0cde00cd1c47..b554e1d55950 100644
@@ -25,8 +25,12 @@ void blk_mq_sched_free_rqs(struct request_queue *q);
 
 struct elevator_tags *blk_mq_alloc_sched_tags(struct blk_mq_tag_set *set,
 		unsigned int nr_hw_queues);
+int blk_mq_alloc_sched_tags_batch(struct xarray *et_table,
+		struct blk_mq_tag_set *set, unsigned int nr_hw_queues);
 void blk_mq_free_sched_tags(struct elevator_tags *et,
 		struct blk_mq_tag_set *set);
+void blk_mq_free_sched_tags_batch(struct xarray *et_table,
+		struct blk_mq_tag_set *set);
 
 static inline void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {

index 32d11305d51b..4cb2f5ca8656 100644
@@ -4972,12 +4972,13 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
  * Switch back to the elevator type stored in the xarray.
  */
 static void blk_mq_elv_switch_back(struct request_queue *q,
-		struct xarray *elv_tbl)
+		struct xarray *elv_tbl, struct xarray *et_tbl)
 {
 	struct elevator_type *e = xa_load(elv_tbl, q->id);
+	struct elevator_tags *t = xa_load(et_tbl, q->id);
 
 	/* The elv_update_nr_hw_queues unfreezes the queue. */
-	elv_update_nr_hw_queues(q, e);
+	elv_update_nr_hw_queues(q, e, t);
 
 	/* Drop the reference acquired in blk_mq_elv_switch_none. */
 	if (e)

@@ -5029,7 +5030,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	int prev_nr_hw_queues = set->nr_hw_queues;
 	unsigned int memflags;
 	int i;
-	struct xarray elv_tbl;
+	struct xarray elv_tbl, et_tbl;
 
 	lockdep_assert_held(&set->tag_list_lock);
 

@@ -5042,6 +5043,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	memflags = memalloc_noio_save();
 
+	xa_init(&et_tbl);
+	if (blk_mq_alloc_sched_tags_batch(&et_tbl, set, nr_hw_queues) < 0)
+		goto out_memalloc_restore;
+
 	xa_init(&elv_tbl);
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {

@@ -5085,7 +5090,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 switch_back:
 	/* The blk_mq_elv_switch_back unfreezes queue for us. */
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
-		blk_mq_elv_switch_back(q, &elv_tbl);
+		blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl);
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_sysfs_register_hctxs(q);

@@ -5096,7 +5101,8 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	}
 
 	xa_destroy(&elv_tbl);
-
+	xa_destroy(&et_tbl);
+out_memalloc_restore:
 	memalloc_noio_restore(memflags);
 
 	/* Free the excess tags when nr_hw_queues shrink. */

index 4746a7704856..5d9ca8c95193 100644
@@ -12,6 +12,7 @@
 #include "blk-crypto-internal.h"
 
 struct elevator_type;
+struct elevator_tags;
 
 #define	BLK_DEV_MAX_SECTORS	(LLONG_MAX >> 9)
 #define	BLK_MIN_SEGMENT_SIZE	4096

@@ -322,7 +323,8 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
 
 bool blk_insert_flush(struct request *rq);
 
-void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e);
+void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e,
+		struct elevator_tags *t);
 void elevator_set_default(struct request_queue *q);
 void elevator_set_none(struct request_queue *q);
 

index e9dc837b7b70..fe96c6f4753c 100644
@@ -705,7 +705,8 @@ static int elevator_change(struct request_queue *q, struct elv_change_ctx *ctx)
  * The I/O scheduler depends on the number of hardware queues, this forces a
  * reattachment when nr_hw_queues changes.
  */
-void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e)
+void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e,
+		struct elevator_tags *t)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
 	struct elv_change_ctx ctx = {};

@@ -715,25 +716,21 @@ void elv_update_nr_hw_queues(struct request_queue *q, struct elevator_type *e)
 
 	if (e && !blk_queue_dying(q) && blk_queue_registered(q)) {
 		ctx.name = e->elevator_name;
-		ctx.et = blk_mq_alloc_sched_tags(set, set->nr_hw_queues);
-		if (!ctx.et) {
-			WARN_ON_ONCE(1);
-			goto unfreeze;
-		}
+		ctx.et = t;
+
 		mutex_lock(&q->elevator_lock);
 		/* force to reattach elevator after nr_hw_queue is updated */
 		ret = elevator_switch(q, &ctx);
 		mutex_unlock(&q->elevator_lock);
 	}
-unfreeze:
 	blk_mq_unfreeze_queue_nomemrestore(q);
 	if (!ret)
 		WARN_ON_ONCE(elevator_change_done(q, &ctx));
 	/*
 	 * Free sched tags if it's allocated but we couldn't switch elevator.
 	 */
-	if (ctx.et && !ctx.new)
-		blk_mq_free_sched_tags(ctx.et, set);
+	if (t && !ctx.new)
+		blk_mq_free_sched_tags(t, set);
 }
 
 /*

index 4cb2f5ca8656..355db0abe44b 100644
@@ -5031,6 +5031,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	unsigned int memflags;
 	int i;
 	struct xarray elv_tbl, et_tbl;
+	bool queues_frozen = false;
 
 	lockdep_assert_held(&set->tag_list_lock);
 

@@ -5054,9 +5055,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister_hctxs(q);
 	}
 
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
-		blk_mq_freeze_queue_nomemsave(q);
-
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done

@@ -5066,6 +5064,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		if (blk_mq_elv_switch_none(q, &elv_tbl))
 			goto switch_back;
 
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_freeze_queue_nomemsave(q);
+	queues_frozen = true;
 	if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
 		goto switch_back;
 

@@ -5089,8 +5090,12 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	}
 switch_back:
 	/* The blk_mq_elv_switch_back unfreezes queue for us. */
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		/* switch_back expects queue to be frozen */
+		if (!queues_frozen)
+			blk_mq_freeze_queue_nomemsave(q);
 		blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl);
+	}
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_sysfs_register_hctxs(q);

index 848591fb3c57..b1e24bb85ad2 100644
@@ -374,6 +374,7 @@ void rq_qos_del(struct rq_qos *rqos)
 	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
 		if (*cur == rqos) {
 			*cur = rqos->next;
+			static_branch_dec(&block_rq_qos);
 			break;
 		}
 	}

index 39749f4066fb..28125fc49eff 100644
@@ -142,8 +142,14 @@ static inline void rq_qos_done_bio(struct bio *bio)
 	    bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) ||
 			     bio_flagged(bio, BIO_QOS_MERGED))) {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-		if (q->rq_qos)
-			__rq_qos_done_bio(q->rq_qos, bio);
+
+		/*
+		 * If a bio has BIO_QOS_xxx set, it implicitly implies that
+		 * q->rq_qos is present. So, we skip re-checking q->rq_qos
+		 * here as an extra optimization and directly call
+		 * __rq_qos_done_bio().
+		 */
+		__rq_qos_done_bio(q->rq_qos, bio);
 	}
 }
 

index 29b3540dd180..bdcb27ab5606 100644
@@ -95,6 +95,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(SQ_SCHED),
 	QUEUE_FLAG_NAME(DISABLE_WBT_DEF),
 	QUEUE_FLAG_NAME(NO_ELV_SWITCH),
+	QUEUE_FLAG_NAME(QOS_ENABLED),
 };
 #undef QUEUE_FLAG_NAME
 

index b1e24bb85ad2..654478dfbc20 100644
@@ -2,8 +2,6 @@
 
 #include "blk-rq-qos.h"
 
-__read_mostly DEFINE_STATIC_KEY_FALSE(block_rq_qos);
-
 /*
  * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
  * false if 'v' + 1 would be bigger than 'below'.

@@ -319,8 +317,8 @@ void rq_qos_exit(struct request_queue *q)
 		struct rq_qos *rqos = q->rq_qos;
 		q->rq_qos = rqos->next;
 		rqos->ops->exit(rqos);
-		static_branch_dec(&block_rq_qos);
 	}
+	blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q);
 	mutex_unlock(&q->rq_qos_mutex);
 }
 

@@ -346,7 +344,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 		goto ebusy;
 	rqos->next = q->rq_qos;
 	q->rq_qos = rqos;
-	static_branch_inc(&block_rq_qos);
+	blk_queue_flag_set(QUEUE_FLAG_QOS_ENABLED, q);
 
 	blk_mq_unfreeze_queue(q, memflags);
 

@@ -374,10 +372,11 @@ void rq_qos_del(struct rq_qos *rqos)
 	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
 		if (*cur == rqos) {
 			*cur = rqos->next;
-			static_branch_dec(&block_rq_qos);
 			break;
 		}
 	}
+	if (!q->rq_qos)
+		blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q);
 	blk_mq_unfreeze_queue(q, memflags);
 
 	mutex_lock(&q->debugfs_mutex);

108 lines not on this page · raw message

index 620345ce3aaa..3921188c9e13 100644
@@ -652,6 +652,7 @@ enum {
 	QUEUE_FLAG_SQ_SCHED,		/* single queue style io dispatch */
 	QUEUE_FLAG_DISABLE_WBT_DEF,	/* for sched to disable/enable wbt */
 	QUEUE_FLAG_NO_ELV_SWITCH,	/* can't switch elevator any more */
+	QUEUE_FLAG_QOS_ENABLED,		/* qos is enabled */
 	QUEUE_FLAG_MAX
 };
 

index 1b765045aa63..b56395ac5a74 100644
@@ -606,8 +606,8 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
 		if (!npc_check_field(rvu, blkaddr, NPC_LB, intf))
 			*features &= ~BIT_ULL(NPC_OUTER_VID);
 
-	/* Set SPI flag only if AH/ESP and IPSEC_SPI are in the key */
-	if (npc_check_field(rvu, blkaddr, NPC_IPSEC_SPI, intf) &&
+	/* Allow extracting SPI field from AH and ESP headers at same offset */
+	if (npc_is_field_present(rvu, NPC_IPSEC_SPI, intf) &&
 	    (*features & (BIT_ULL(NPC_IPPROTO_ESP) | BIT_ULL(NPC_IPPROTO_AH))))
 		*features |= BIT_ULL(NPC_IPSEC_SPI);
 

index b7102e14d23d..c33accadae0f 100644
@@ -47,10 +47,12 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 		devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum,
 					      vport_num - 1, external);
 	}  else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) {
+		u16 base_vport = mlx5_core_ec_vf_vport_base(dev);
+
 		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
 		devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum,
-					      vport_num - 1, false);
+					      vport_num - base_vport, false);
 	}
 }
 

index 2c09df4ee574..83288df7bb45 100644
@@ -10460,8 +10460,16 @@ struct mlx5_ifc_pifr_reg_bits {
 	u8         port_filter_update_en[8][0x20];
 };
 
+enum {
+	MLX5_BUF_OWNERSHIP_UNKNOWN	= 0x0,
+	MLX5_BUF_OWNERSHIP_FW_OWNED	= 0x1,
+	MLX5_BUF_OWNERSHIP_SW_OWNED	= 0x2,
+};
+
 struct mlx5_ifc_pfcc_reg_bits {
-	u8         reserved_at_0[0x8];
+	u8         reserved_at_0[0x4];
+	u8	   buf_ownership[0x2];
+	u8	   reserved_at_6[0x2];
 	u8         local_port[0x8];
 	u8         reserved_at_10[0xb];
 	u8         ppan_mask_n[0x1];

@@ -10597,7 +10605,9 @@ struct mlx5_ifc_pcam_enhanced_features_bits {
 	u8         fec_200G_per_lane_in_pplm[0x1];
 	u8         reserved_at_1e[0x2a];
 	u8         fec_100G_per_lane_in_pplm[0x1];
-	u8         reserved_at_49[0x1f];
+	u8         reserved_at_49[0xa];
+	u8	   buffer_ownership[0x1];
+	u8	   resereved_at_54[0x14];
 	u8         fec_50G_per_lane_in_pplm[0x1];
 	u8         reserved_at_69[0x4];
 	u8         rx_icrc_encapsulated_counter[0x1];

index b59aee75de94..2c98a5299df3 100644
@@ -26,7 +26,6 @@ struct mlx5e_dcbx {
 	u8                         cap;
 
 	/* Buffer configuration */
-	bool                       manual_buffer;
 	u32                        cable_len;
 	u32                        xoff;
 	u16                        port_buff_cell_sz;

index 5fe016e477b3..d166c0d5189e 100644
@@ -362,6 +362,7 @@ static int mlx5e_dcbnl_ieee_getpfc(struct net_device *dev,
 static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
+	u8 buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN;
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 old_cable_len = priv->dcbx.cable_len;

@@ -389,7 +390,14 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 
 	if (MLX5_BUFFER_SUPPORTED(mdev)) {
 		pfc_new.pfc_en = (changed & MLX5E_PORT_BUFFER_PFC) ? pfc->pfc_en : curr_pfc_en;
-		if (priv->dcbx.manual_buffer)
+		ret = mlx5_query_port_buffer_ownership(mdev,
+						       &buffer_ownership);
+		if (ret)
+			netdev_err(dev,
+				   "%s, Failed to get buffer ownership: %d\n",
+				   __func__, ret);
+
+		if (buffer_ownership == MLX5_BUF_OWNERSHIP_SW_OWNED)
 			ret = mlx5e_port_manual_buffer_config(priv, changed,
 							      dev->mtu, &pfc_new,
 							      NULL, NULL);

@@ -982,7 +990,6 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev,
 	if (!changed)
 		return 0;
 
-	priv->dcbx.manual_buffer = true;
 	err = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, NULL,
 					      buffer_size, prio2buffer);
 	return err;

@@ -1252,7 +1259,6 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv)
 		priv->dcbx.cap |= DCB_CAP_DCBX_HOST;
 
 	priv->dcbx.port_buff_cell_sz = mlx5e_query_port_buffers_cell_size(priv);
-	priv->dcbx.manual_buffer = false;
 	priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN;
 
 	mlx5e_ets_init(priv);

index 2e02bdea8361..c2f6d205ddb1 100644
@@ -358,6 +358,8 @@ int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
 int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
 int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
 int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
+int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev,
+				     u8 *buffer_ownership);
 int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
 int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
 

index 549f1066d2a5..2d7adf7444ba 100644
@@ -968,6 +968,26 @@ int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state)
 	return err;
 }
 
+int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev,
+				     u8 *buffer_ownership)
+{
+	u32 out[MLX5_ST_SZ_DW(pfcc_reg)] = {};
+	int err;
+
+	if (!MLX5_CAP_PCAM_FEATURE(mdev, buffer_ownership)) {
+		*buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN;
+		return 0;
+	}
+
+	err = mlx5_query_pfcc_reg(mdev, out, sizeof(out));
+	if (err)
+		return err;
+
+	*buffer_ownership = MLX5_GET(pfcc_reg, out, buf_ownership);
+
+	return 0;
+}
+
 int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio)
 {
 	int sz = MLX5_ST_SZ_BYTES(qpdpm_reg);

index 5ae787656a7c..3efa8bf1d14e 100644
@@ -272,8 +272,8 @@ static int port_update_shared_buffer(struct mlx5_core_dev *mdev,
 	/* Total shared buffer size is split in a ratio of 3:1 between
 	 * lossy and lossless pools respectively.
 	 */
-	lossy_epool_size = (shared_buffer_size / 4) * 3;
 	lossless_ipool_size = shared_buffer_size / 4;
+	lossy_epool_size    = shared_buffer_size - lossless_ipool_size;
 
 	mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0,
 			    lossy_epool_size);

@@ -288,14 +288,12 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int sz = MLX5_ST_SZ_BYTES(pbmc_reg);
-	u32 new_headroom_size = 0;
-	u32 current_headroom_size;
+	u32 current_headroom_cells = 0;
+	u32 new_headroom_cells = 0;
 	void *in;
 	int err;
 	int i;
 
-	current_headroom_size = port_buffer->headroom_size;
-
 	in = kzalloc(sz, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;

@@ -306,12 +304,14 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 
 	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
+		current_headroom_cells += MLX5_GET(bufferx_reg, buffer, size);
+
 		u64 size = port_buffer->buffer[i].size;
 		u64 xoff = port_buffer->buffer[i].xoff;
 		u64 xon = port_buffer->buffer[i].xon;
 
-		new_headroom_size += size;
 		do_div(size, port_buff_cell_sz);
+		new_headroom_cells += size;
 		do_div(xoff, port_buff_cell_sz);
 		do_div(xon, port_buff_cell_sz);
 		MLX5_SET(bufferx_reg, buffer, size, size);

@@ -320,10 +320,8 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 		MLX5_SET(bufferx_reg, buffer, xon_threshold, xon);
 	}
 
-	new_headroom_size /= port_buff_cell_sz;
-	current_headroom_size /= port_buff_cell_sz;
-	err = port_update_shared_buffer(priv->mdev, current_headroom_size,
-					new_headroom_size);
+	err = port_update_shared_buffer(priv->mdev, current_headroom_cells,
+					new_headroom_cells);
 	if (err)
 		goto out;
 

index 4f4e8e87a14c..a0d55b77c994 100644
@@ -285,7 +285,7 @@ static const struct usb_desc_validator audio_validators[] = {
 	/* UAC_VERSION_3, UAC3_EXTENDED_TERMINAL: not implemented yet */
 	FUNC(UAC_VERSION_3, UAC3_MIXER_UNIT, validate_mixer_unit),
 	FUNC(UAC_VERSION_3, UAC3_SELECTOR_UNIT, validate_selector_unit),
-	FUNC(UAC_VERSION_3, UAC_FEATURE_UNIT, validate_uac3_feature_unit),
+	FUNC(UAC_VERSION_3, UAC3_FEATURE_UNIT, validate_uac3_feature_unit),
 	/*  UAC_VERSION_3, UAC3_EFFECT_UNIT: not implemented yet */
 	FUNC(UAC_VERSION_3, UAC3_PROCESSING_UNIT, validate_processing_unit),
 	FUNC(UAC_VERSION_3, UAC3_EXTENSION_UNIT, validate_processing_unit),

index 5d9effb0867c..e74eb8f9b23a 100644
@@ -66,23 +66,27 @@ static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	long rc;
 
 	mutex_lock(&df->lock);
-	if (df->unlocked_ioctl)
-		rc = df->unlocked_ioctl(file, cmd, arg);
-	else
-		rc = -ENOTTY;
+	rc = df->unlocked_ioctl(file, cmd, arg);
 	mutex_unlock(&df->lock);
 	return rc;
 }
 
-static const struct file_operations dbfs_ops = {
+static const struct file_operations dbfs_ops_ioctl = {
 	.read		= dbfs_read,
 	.unlocked_ioctl = dbfs_ioctl,
 };
 
+static const struct file_operations dbfs_ops = {
+	.read		= dbfs_read,
+};
+
 void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df)
 {
-	df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df,
-					 &dbfs_ops);
+	const struct file_operations *fops = &dbfs_ops;
+
+	if (df->unlocked_ioctl)
+		fops = &dbfs_ops_ioctl;
+	df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df, fops);
 	mutex_init(&df->lock);
 }
 

index e74eb8f9b23a..41a0d2066fa0 100644
@@ -6,6 +6,7 @@
  * Author(s): Michael Holzheu <[email protected]>
  */
 
+#include <linux/security.h>
 #include <linux/slab.h>
 #include "hypfs.h"
 

@@ -84,7 +85,7 @@ void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df)
 {
 	const struct file_operations *fops = &dbfs_ops;
 
-	if (df->unlocked_ioctl)
+	if (df->unlocked_ioctl && !security_locked_down(LOCKDOWN_DEBUGFS))
 		fops = &dbfs_ops_ioctl;
 	df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df, fops);
 	mutex_init(&df->lock);

index 87fd945a0d27..0d3cb2ba6fc8 100644
@@ -247,8 +247,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	if (!oth)
 		return;
 
-	if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
-	    nf_reject_fill_skb_dst(oldskb) < 0)
+	if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0)
 		return;
 
 	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))

@@ -321,8 +320,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
 	if (iph->frag_off & htons(IP_OFFSET))
 		return;
 
-	if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
-	    nf_reject_fill_skb_dst(skb_in) < 0)
+	if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0)
 		return;
 
 	if (skb_csum_unnecessary(skb_in) ||

index 9ae2b2725bf9..c3d64c4b69d7 100644
@@ -293,7 +293,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	fl6.fl6_sport = otcph->dest;
 	fl6.fl6_dport = otcph->source;
 
-	if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) {
+	if (!skb_dst(oldskb)) {
 		nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
 		if (!dst)
 			return;

@@ -397,8 +397,7 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
 	if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
 		skb_in->dev = net->loopback_dev;
 
-	if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) &&
-	    nf_reject6_fill_skb_dst(skb_in) < 0)
+	if (!skb_dst(skb_in) && nf_reject6_fill_skb_dst(skb_in) < 0)
 		return;
 
 	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);

index 7251f23b919c..3135de124c18 100644
@@ -1767,6 +1767,20 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef)
 	if (number_tiles > 1)
 		vm->composite_fence_ctx = dma_fence_context_alloc(1);
 
+	if (xef && xe->info.has_asid) {
+		u32 asid;
+
+		down_write(&xe->usm.lock);
+		err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm,
+				      XA_LIMIT(1, XE_MAX_ASID - 1),
+				      &xe->usm.next_asid, GFP_KERNEL);
+		up_write(&xe->usm.lock);
+		if (err < 0)
+			goto err_unlock_close;
+
+		vm->usm.asid = asid;
+	}
+
 	trace_xe_vm_create(vm);
 
 	return vm;

@@ -2034,9 +2048,8 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	struct xe_device *xe = to_xe_device(dev);
 	struct xe_file *xef = to_xe_file(file);
 	struct drm_xe_vm_create *args = data;
-	struct xe_tile *tile;
 	struct xe_vm *vm;
-	u32 id, asid;
+	u32 id;
 	int err;
 	u32 flags = 0;
 

@@ -2076,23 +2089,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (IS_ERR(vm))
 		return PTR_ERR(vm);
 
-	if (xe->info.has_asid) {
-		down_write(&xe->usm.lock);
-		err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm,
-				      XA_LIMIT(1, XE_MAX_ASID - 1),
-				      &xe->usm.next_asid, GFP_KERNEL);
-		up_write(&xe->usm.lock);
-		if (err < 0)
-			goto err_close_and_put;
-
-		vm->usm.asid = asid;
-	}
-
-	/* Record BO memory for VM pagetable created against client */
-	for_each_tile(tile, xe, id)
-		if (vm->pt_root[id])
-			xe_drm_client_add_bo(vm->xef->client, vm->pt_root[id]->bo);
-
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_MEM)
 	/* Warning: Security issue - never enable by default */
 	args->reserved[0] = xe_bo_main_addr(vm->pt_root[0]->bo, XE_PAGE_SIZE);

index 3135de124c18..3b11b1d52bee 100644
@@ -3200,6 +3200,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm,
 free_bind_ops:
 	if (args->num_binds > 1)
 		kvfree(*bind_ops);
+	*bind_ops = NULL;
 	return err;
 }