diff --git a/llvm/lib/Target/BPF/BPFISelLowering.cpp b/llvm/lib/Target/BPF/BPFISelLowering.cpp
--- a/llvm/lib/Target/BPF/BPFISelLowering.cpp
+++ b/llvm/lib/Target/BPF/BPFISelLowering.cpp
@@ -140,10 +140,6 @@
     setLoadExtAction(ISD::EXTLOAD, VT, MVT::i1, Promote);
     setLoadExtAction(ISD::ZEXTLOAD, VT, MVT::i1, Promote);
     setLoadExtAction(ISD::SEXTLOAD, VT, MVT::i1, Promote);
-
-    setLoadExtAction(ISD::SEXTLOAD, VT, MVT::i8, Expand);
-    setLoadExtAction(ISD::SEXTLOAD, VT, MVT::i16, Expand);
-    setLoadExtAction(ISD::SEXTLOAD, VT, MVT::i32, Expand);
   }
 
   setBooleanContents(ZeroOrOneBooleanContent);
diff --git a/llvm/lib/Target/BPF/BPFInstrFormats.td b/llvm/lib/Target/BPF/BPFInstrFormats.td
--- a/llvm/lib/Target/BPF/BPFInstrFormats.td
+++ b/llvm/lib/Target/BPF/BPFInstrFormats.td
@@ -90,6 +90,7 @@
 def BPF_ABS  : BPFModeModifer<0x1>;
 def BPF_IND  : BPFModeModifer<0x2>;
 def BPF_MEM  : BPFModeModifer<0x3>;
+def BPF_MEM_SEXT : BPFModeModifer<0x4>;
 def BPF_ATOMIC : BPFModeModifer<0x6>;
 
 class BPFAtomicFlag<bits<4> val> {
diff --git a/llvm/lib/Target/BPF/BPFInstrInfo.td b/llvm/lib/Target/BPF/BPFInstrInfo.td
--- a/llvm/lib/Target/BPF/BPFInstrInfo.td
+++ b/llvm/lib/Target/BPF/BPFInstrInfo.td
@@ -421,8 +421,8 @@
 def STD : STOREi64<BPF_DW, "u64", store>;
 
 // LOAD instructions
-class LOAD<BPFWidthModifer SizeOp, string OpcodeStr, list<dag> Pattern>
-    : TYPE_LD_ST<BPF_MEM.Value, SizeOp.Value,
+class LOAD<BPFWidthModifer SizeOp, BPFModeModifer ModOp, string OpcodeStr, list<dag> Pattern>
+    : TYPE_LD_ST<ModOp.Value, SizeOp.Value,
                  (outs GPR:$dst),
                  (ins MEMri:$addr),
                  "$dst = *("#OpcodeStr#" *)($addr)",
@@ -436,8 +436,8 @@
   let BPFClass = BPF_LDX;
 }
 
-class LOADi64<BPFWidthModifer SizeOp, string OpcodeStr, PatFrag OpNode>
-    : LOAD<SizeOp, OpcodeStr, [(set i64:$dst, (OpNode ADDRri:$addr))]>;
+class LOADi64<BPFWidthModifer SizeOp, BPFModeModifer ModOp, string OpcodeStr, PatFrag OpNode>
+    : LOAD<SizeOp, ModOp, OpcodeStr, [(set i64:$dst, (OpNode ADDRri:$addr))]>;
 
 let isCodeGenOnly = 1 in {
   def CORE_MEM : TYPE_LD_ST<BPF_MEM.Value, BPF_W.Value,
@@ -460,12 +460,16 @@
 }
 
 let Predicates = [BPFNoALU32] in {
-  def LDW : LOADi64<BPF_W, "u32", zextloadi32>;
-  def LDH : LOADi64<BPF_H, "u16", zextloadi16>;
-  def LDB : LOADi64<BPF_B, "u8", zextloadi8>;
+  def LDW : LOADi64<BPF_W, BPF_MEM, "u32", zextloadi32>;
+  def LDH : LOADi64<BPF_H, BPF_MEM, "u16", zextloadi16>;
+  def LDB : LOADi64<BPF_B, BPF_MEM, "u8", zextloadi8>;
+
+  def LDWS : LOADi64<BPF_W, BPF_MEM_SEXT, "s32", sextloadi32>;
+  def LDHS : LOADi64<BPF_H, BPF_MEM_SEXT, "s16", sextloadi16>;
+  def LDBS : LOADi64<BPF_B, BPF_MEM_SEXT, "s8",  sextloadi8>;
 }
 
-def LDD : LOADi64<BPF_DW, "u64", load>;
+def LDD : LOADi64<BPF_DW, BPF_MEM, "u64", load>;
 
 class BRANCH<BPFJumpOp Opc, string OpcodeStr, list<dag> Pattern>
     : TYPE_ALU_JMP<Opc.Value, BPF_K.Value,
@@ -940,8 +944,8 @@
   def STB32 : STOREi32<BPF_B, "u8", truncstorei8>;
 }
 
-class LOAD32<BPFWidthModifer SizeOp, string OpcodeStr, list<dag> Pattern>
-    : TYPE_LD_ST<BPF_MEM.Value, SizeOp.Value,
+class LOAD32<BPFWidthModifer SizeOp, BPFModeModifer ModOp, string OpcodeStr, list<dag> Pattern>
+    : TYPE_LD_ST<ModOp.Value, SizeOp.Value,
                 (outs GPR32:$dst),
                 (ins MEMri:$addr),
                 "$dst = *("#OpcodeStr#" *)($addr)",
@@ -955,13 +959,16 @@
   let BPFClass = BPF_LDX;
 }
 
-class LOADi32<BPFWidthModifer SizeOp, string OpcodeStr, PatFrag OpNode>
-    : LOAD32<SizeOp, OpcodeStr, [(set i32:$dst, (OpNode ADDRri:$addr))]>;
+class LOADi32<BPFWidthModifer SizeOp, BPFModeModifer ModOp, string OpcodeStr, PatFrag OpNode>
+    : LOAD32<SizeOp, ModOp, OpcodeStr, [(set i32:$dst, (OpNode ADDRri:$addr))]>;
 
 let Predicates = [BPFHasALU32], DecoderNamespace = "BPFALU32" in {
-  def LDW32 : LOADi32<BPF_W, "u32", load>;
-  def LDH32 : LOADi32<BPF_H, "u16", zextloadi16>;
-  def LDB32 : LOADi32<BPF_B, "u8", zextloadi8>;
+  def LDW32 : LOADi32<BPF_W, BPF_MEM, "u32", load>;
+  def LDH32 : LOADi32<BPF_H, BPF_MEM, "u16", zextloadi16>;
+  def LDB32 : LOADi32<BPF_B, BPF_MEM, "u8", zextloadi8>;
+
+  def LDH32S : LOADi32<BPF_H, BPF_MEM_SEXT, "s16", sextloadi16>;
+  def LDB32S : LOADi32<BPF_B, BPF_MEM_SEXT, "s8", sextloadi8>;
 }
 
 let Predicates = [BPFHasALU32] in {
@@ -973,6 +980,8 @@
             (STW32 (EXTRACT_SUBREG GPR:$src, sub_32), ADDRri:$dst)>;
   def : Pat<(i32 (extloadi8 ADDRri:$src)), (i32 (LDB32 ADDRri:$src))>;
   def : Pat<(i32 (extloadi16 ADDRri:$src)), (i32 (LDH32 ADDRri:$src))>;
+  def : Pat<(i32 (sextloadi8 ADDRri:$src)), (i32 (LDB32S ADDRri:$src))>;
+  def : Pat<(i32 (sextloadi16 ADDRri:$src)), (i32 (LDH32S ADDRri:$src))>;
   def : Pat<(i64 (zextloadi8  ADDRri:$src)),
             (SUBREG_TO_REG (i64 0), (LDB32 ADDRri:$src), sub_32)>;
   def : Pat<(i64 (zextloadi16 ADDRri:$src)),
@@ -985,6 +994,9 @@
             (SUBREG_TO_REG (i64 0), (LDH32 ADDRri:$src), sub_32)>;
   def : Pat<(i64 (extloadi32 ADDRri:$src)),
             (SUBREG_TO_REG (i64 0), (LDW32 ADDRri:$src), sub_32)>;
+  def : Pat<(i64 (sextloadi8 ADDRri:$src)), (i64 (LDBS ADDRri:$src))>;
+  def : Pat<(i64 (sextloadi16 ADDRri:$src)), (i64 (LDHS ADDRri:$src))>;
+  def : Pat<(i64 (sextloadi32 ADDRri:$src)), (i64 (LDWS ADDRri:$src))>;
 }
 
 let usesCustomInserter = 1, isCodeGenOnly = 1 in {
diff --git a/llvm/lib/Target/BPF/Disassembler/BPFDisassembler.cpp b/llvm/lib/Target/BPF/Disassembler/BPFDisassembler.cpp
--- a/llvm/lib/Target/BPF/Disassembler/BPFDisassembler.cpp
+++ b/llvm/lib/Target/BPF/Disassembler/BPFDisassembler.cpp
@@ -57,6 +57,7 @@
     BPF_ABS = 0x1,
     BPF_IND = 0x2,
     BPF_MEM = 0x3,
+    BPF_MEM_SEXT = 0x4,
     BPF_LEN = 0x4,
     BPF_MSH = 0x5,
     BPF_ATOMIC = 0x6
diff --git a/llvm/test/CodeGen/BPF/sext.ll b/llvm/test/CodeGen/BPF/sext.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/BPF/sext.ll
@@ -0,0 +1,112 @@
+; RUN: llc -O2 -march=bpfel -mcpu=v1 < %s | FileCheck -check-prefixes=CHECK -check-prefixes=CHECKV1 %s
+; RUN: llc -O2 -march=bpfel -mcpu=v3 < %s | FileCheck -check-prefixes=CHECK -check-prefixes=CHECKV3 %s
+; Source:
+;  int f1(char *p) {
+;    return *p;
+;  }
+;  int f2(short *p) {
+;    return *p;
+;  }
+;  int f3(int *p) {
+;    return *p;
+;  }
+;  long f4(char *p) {
+;    return *p;
+;  }
+;  long f5(short *p) {
+;    return *p;
+;  }
+;  long f6(int *p) {
+;    return *p;
+;  }
+;  long f7(long *p) {
+;    return *p;
+;  }
+; Compilation flags:
+;   clang -target bpf -O2 -S -emit-llvm -Xclang -disable-llvm-passes t.c
+
+; Function Attrs: argmemonly mustprogress nofree norecurse nosync nounwind readonly willreturn
+define dso_local i32 @f1(ptr nocapture noundef readonly %p) local_unnamed_addr #0 {
+entry:
+  %0 = load i8, ptr %p, align 1, !tbaa !3
+  %conv = sext i8 %0 to i32
+; CHECKV1:  r0 = *(s8 *)(r1 + 0)
+; CHECKV3:  w0 = *(s8 *)(r1 + 0)
+  ret i32 %conv
+}
+
+; Function Attrs: argmemonly mustprogress nofree norecurse nosync nounwind readonly willreturn
+define dso_local i32 @f2(ptr nocapture noundef readonly %p) local_unnamed_addr #0 {
+entry:
+  %0 = load i16, ptr %p, align 2, !tbaa !6
+  %conv = sext i16 %0 to i32
+; CHECKV1:  r0 = *(s16 *)(r1 + 0)
+; CHECKV3:  w0 = *(s16 *)(r1 + 0)
+  ret i32 %conv
+}
+
+; Function Attrs: argmemonly mustprogress nofree norecurse nosync nounwind readonly willreturn
+define dso_local i32 @f3(ptr nocapture noundef readonly %p) local_unnamed_addr #0 {
+entry:
+  %0 = load i32, ptr %p, align 4, !tbaa !8
+; CHECKV1:  r0 = *(u32 *)(r1 + 0)
+; CHECKV3:  w0 = *(u32 *)(r1 + 0)
+  ret i32 %0
+}
+
+; Function Attrs: argmemonly mustprogress nofree norecurse nosync nounwind readonly willreturn
+define dso_local i64 @f4(ptr nocapture noundef readonly %p) local_unnamed_addr #0 {
+entry:
+  %0 = load i8, ptr %p, align 1, !tbaa !3
+  %conv = sext i8 %0 to i64
+  ret i64 %conv
+; CHECK:      r0 = *(s8 *)(r1 + 0)
+; CHECK-NEXT: exit
+}
+
+; Function Attrs: argmemonly mustprogress nofree norecurse nosync nounwind readonly willreturn
+define dso_local i64 @f5(ptr nocapture noundef readonly %p) local_unnamed_addr #0 {
+entry:
+  %0 = load i16, ptr %p, align 2, !tbaa !6
+  %conv = sext i16 %0 to i64
+  ret i64 %conv
+; CHECK:      r0 = *(s16 *)(r1 + 0)
+; CHECK-NEXT: exit
+}
+
+; Function Attrs: argmemonly mustprogress nofree norecurse nosync nounwind readonly willreturn
+define dso_local i64 @f6(ptr nocapture noundef readonly %p) local_unnamed_addr #0 {
+entry:
+  %0 = load i32, ptr %p, align 4, !tbaa !8
+  %conv = sext i32 %0 to i64
+  ret i64 %conv
+; CHECK:      r0 = *(s32 *)(r1 + 0)
+; CHECK-NEXT: exit
+}
+
+; Function Attrs: argmemonly mustprogress nofree norecurse nosync nounwind readonly willreturn
+define dso_local i64 @f7(ptr nocapture noundef readonly %p) local_unnamed_addr #0 {
+entry:
+  %0 = load i64, ptr %p, align 8, !tbaa !10
+  ret i64 %0
+; CHECK:      r0 = *(u64 *)(r1 + 0)
+; CHECK-NEXT: exit
+}
+
+attributes #0 = { argmemonly mustprogress nofree norecurse nosync nounwind readonly willreturn "frame-pointer"="all" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+
+!llvm.module.flags = !{!0, !1}
+!llvm.ident = !{!2}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 7, !"frame-pointer", i32 2}
+!2 = !{!"clang version 16.0.0 (https://github.com/llvm/llvm-project.git 68665544c7d59735e9c0bb32b08829c006c7c594)"}
+!3 = !{!4, !4, i64 0}
+!4 = !{!"omnipotent char", !5, i64 0}
+!5 = !{!"Simple C/C++ TBAA"}
+!6 = !{!7, !7, i64 0}
+!7 = !{!"short", !4, i64 0}
+!8 = !{!9, !9, i64 0}
+!9 = !{!"int", !4, i64 0}
+!10 = !{!11, !11, i64 0}
+!11 = !{!"long", !4, i64 0}